Parcel positioning method and system based on synthesis algorithm

Abstract

The invention discloses a parcel positioning method and system based on a synthesis algorithm, and the method comprises the following steps: S1, obtaining three base stations which are closest to the current positioning of a parcel, taking the three base stations as first base stations, and calculating an error radius through the distances between the three first base stations and the parcel; s2, modeling is carried out on trucks in the truck area, and each truck is represented by a rectangle; and S3, constructing a circular judgment range according to the current location of the parcel and the error radius, and judging the lorry where the parcel is located based on the geometric relationship between the judgment range and the modeling area of the lorry. A weight segmentation mechanism based on base station signal strength is introduced, the error radius of a package is dynamically calculated to represent position uncertainty, truck geometric modeling is combined, the problem of attribution ambiguity of the package in an overlapping area is effectively solved, and the distribution robustness of outliers is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transport cargo management, and in particular to a package positioning method and system based on a synthesis algorithm. Background Art

[0002] Freight vehicles form a vital component of logistics and transportation systems. Their function is to transport goods and packages from one location to another. However, delivery personnel often spend considerable time and effort locating specific packages within the vehicle during the entire freight transportation process. This process is not only cumbersome but also susceptible to numerous factors, leading to inefficient delivery and even incorrect deliveries.

[0003] For example, in outdoor parking lots, the ambiguity of express package location is particularly prominent when multiple trucks are parked adjacent to each other. Due to the limited space between trucks, their similar appearance, and the varying stacking of cargo within them, delivery personnel find it difficult to visually identify the vehicle where the target package is located.

[0004] This location ambiguity not only makes it difficult for delivery personnel to quickly and accurately obtain the cargo's location information, but also severely impacts the status updates and subsequent processing of the corresponding cargo. In a logistics information system, cargo location and status information is updated and shared in real time, allowing all parties to keep abreast of the cargo's transportation progress. Summary of the Invention

[0005] In view of the above-mentioned defects, the purpose of the present invention is to propose a package positioning method and system based on a synthesis algorithm to solve the problem of inaccurate package positioning.

[0006] To achieve this purpose, the present invention adopts the following technical solution: a package positioning method based on a synthesis algorithm, comprising the following steps:

[0007] Step S1: Obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package;

[0008] Step S2: Model the trucks in the truck area, and represent each truck with a rectangle;

[0009] Step S3: A circular judgment range is constructed based on the current location of the package and the error radius, and the truck where the package is located is determined based on the geometric relationship between the judgment range and the truck's modeling area.

[0010] Preferably, the process of calculating the error radius by the distance between the three first base stations and the package in step S1 is as follows:

[0011] Step S11: Based on a preset distance range, define a distance weight corresponding to each distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package;

[0012] Step S12: using the distance weight to adjust the distance between the first base station and the package to obtain a first distance, and obtaining the error radius according to the first distance and the distance weight;

[0013] The error radius is obtained as follows:

[0014]

[0015] where w i is the distance weight, d i ' is the first distance, d' i =w i *d i , d i is the distance between the first base station and the package.

[0016] Preferably, the modeling rules for the trucks in the truck area in step S2 are as follows:

[0017] The spatial region model of the truck is constructed based on its geometric parameters; its vertex coordinates are calculated using the following formula:

[0018]

[0019] Where (x c ,y c ) are the horizontal and vertical coordinates of the center of the truck, L and W are the length and width of the truck, and θ is the rotation angle.

[0020] Preferably, the rule for determining the truck where the package is located based on the geometric relationship between the judgment range and the modeling area of ​​the truck in step S3 is as follows:

[0021] If the judgment range of all packages only intersects with the same truck model, the location of the package is defined as the vertex of the truck;

[0022] If the number of intersections between the judgment range of a package and the truck model is not unique, perform the following steps:

[0023] Step S31: Count the trucks that intersect with the judgment range as candidate trucks;

[0024] Treat all packages as points of ambiguity;

[0025] Step S32: Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center;

[0026] Step S33: For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected;

[0027] Step S34: reselecting a new first truck for each ambiguous point using the category selection algorithm, and recording the number of times the first truck is selected;

[0028] Step S35: The location of the package is defined as the vertex of the first truck that is selected the most times.

[0029] Preferably, the type selection algorithm steps are as follows:

[0030] Step A: Get the center coordinates of the candidate trucks as the cluster center points;

[0031] Step B: Calculate the distance from each ambiguous point to each cluster center, associate the ambiguous point with the nearest cluster center, and locate the associated ambiguous points as category points. Obtain the cluster center with the most associated category points, and use its corresponding candidate truck as the first truck. Record the number of times the first truck is selected.

[0032] Step C: Obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position;

[0033] Step D: Repeat steps B to C until the number of iterations is greater than the loop threshold.

[0034] A package positioning system based on a synthesis algorithm, using the package positioning method based on a synthesis algorithm, comprising a data acquisition module, a modeling module, and a determination module;

[0035] The data acquisition module is used to obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package;

[0036] The modeling module is used to model the trucks in the truck area, and each truck is represented by a rectangle;

[0037] The determination module is used to construct a circular judgment range based on the current location of the package and the error radius, and determine the truck where the package is located based on the geometric relationship between the judgment range and the truck's modeling area.

[0038] Preferably, the data acquisition module includes a weight submodule and a radius acquisition submodule;

[0039] The weight submodule is used to define a distance weight corresponding to each distance range based on a preset distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package;

[0040] The radius acquisition submodule is used to adjust the distance between the first base station and the package using the distance weight to obtain a first distance, and obtain the error radius according to the first distance and the distance weight.

[0041] Preferably, the determination module includes a first submodule and a second submodule;

[0042] When the judgment ranges of all packages intersect only with the same truck model, the first submodule is called, and the first submodule defines the location of the package as the vertex of the truck;

[0043] When the number of truck models intersecting the judgment range is not unique, calling the second submodule, the second submodule is used to count the trucks intersecting the judgment range as candidate trucks;

[0044] Treat all packages as points of ambiguity;

[0045] Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center;

[0046] For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected;

[0047] Reselect a new first truck for each ambiguous point using the category selection algorithm, and record the number of times the first truck is selected;

[0048] Define the location of a package as the vertex of the first truck that was selected the most times.

[0049] Preferably, the second submodule includes a first definition unit, a clustering unit, a second definition unit and a loop unit;

[0050] The first definition unit is used to obtain the center coordinates of the candidate truck as the cluster center point

[0051] The clustering unit is used to calculate the distance between each ambiguous point and each cluster center point, associate the ambiguous point with the nearest cluster center point, locate the associated ambiguous point as a category point, obtain the cluster center point with the most associated category points, and use the candidate truck corresponding to it as the first truck, and record the number of times the first truck is selected;

[0052] The second definition unit is used to obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position;

[0053] The loop unit is used to repeatedly call the clustering unit and the second definition unit until the number of iterations is greater than the loop threshold.

[0054] One of the aforementioned technical solutions offers the following advantages or beneficial effects: It introduces a weighted segmentation mechanism based on base station signal strength, dynamically calculates the error radius of a package to characterize location uncertainty, and, combined with truck geometry modeling, effectively resolves the ambiguity of package ownership in overlapping areas and improves the robustness of outlier allocation. Through dynamic error modeling, spatial preference weighting, and parallel computation optimization, this algorithm significantly reduces the impact of signal attenuation and multi-vehicle competition on positioning accuracy, providing a high-precision, low-latency technical solution for package traceability in complex logistics scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of an embodiment of the method of the present invention.

[0056] Figure 2 It is a structural diagram of an embodiment of the system of the present invention.

[0057] Figure 3 FIG. 4 is a schematic diagram of a category selection algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention.

[0059] In the description of the embodiments of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present invention, "plurality" means two or more, unless otherwise specifically specified.

[0060] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0061] like Figures 1 to 3 As shown, a package positioning method based on a synthesis algorithm includes the following steps:

[0062] Step S1: Obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package;

[0063] Step S2: Model the trucks in the truck area, and represent each truck with a rectangle;

[0064] Step S3: A circular judgment range is constructed based on the current location of the package and the error radius, and the truck where the package is located is determined based on the geometric relationship between the judgment range and the truck's modeling area.

[0065] This method introduces a weighted segmentation mechanism based on base station signal strength, dynamically calculates the error radius of a package to characterize location uncertainty, and combines this with truck geometry modeling to effectively resolve the ambiguity of package ownership in overlapping areas and improve the robustness of outlier allocation. Through dynamic error modeling, spatial preference weight allocation, and parallel computation optimization, this algorithm significantly reduces the impact of signal attenuation and multi-vehicle competition on positioning accuracy, providing a high-precision, low-latency technical solution for package traceability in complex logistics scenarios.

[0066] Preferably, the process of calculating the error radius by the distance between the three first base stations and the package in step S1 is as follows:

[0067] Step S11: Based on the preset distance range, define the distance weight corresponding to each distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package, wherein the distance weight is set as follows;

[0068]

[0069] Step S12: using the distance weight to adjust the distance between the first base station and the package to obtain a first distance, and obtaining the error radius according to the first distance and the distance weight;

[0070] The error radius is obtained as follows:

[0071]

[0072] where w i is the distance weight, d′ i is the first distance, d′ i =w i *d i , d i is the distance between the first base station and the package.

[0073] In this invention, the error radius is calculated based on the distance from the package to the first base station to quantify the package's location uncertainty. This provides a quantitative basis for subsequent location determination. In outdoor parking scenarios, the package's positioning error is primarily affected by base station signal attenuation, which is typically related to distance. To this end, this invention dynamically models the relationship between signal strength and distance to calculate the error radius of the package to characterize its location uncertainty.

[0074] Preferably, the modeling rules for the trucks in the truck area in step S2 are as follows:

[0075] The spatial region model of the truck is constructed based on its geometric parameters (length, width, and rotation angle); its vertex coordinates are calculated using the following formula:

[0076]

[0077] Where (x c ,y c ) are the horizontal and vertical coordinates of the center of the truck, L and W are the length and width of the truck, and θ is the rotation angle.

[0078] Preferably, the rule for determining the truck where the package is located based on the geometric relationship between the judgment range and the modeling area of ​​the truck in step S3 is as follows:

[0079] If the judgment range of all packages only intersects with the same truck model, the location of the package is defined as the vertex of the truck;

[0080] If the number of intersections between the judgment range of a package and the truck model is not unique, perform the following steps:

[0081] Step S31: Count the trucks that intersect with the judgment range as candidate trucks;

[0082] Treat all packages as points of ambiguity;

[0083] Step S32: Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center;

[0084] Step S33: For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected;

[0085] Step S34: reselecting a new first truck for each ambiguous point using the category selection algorithm, and recording the number of times the first truck is selected;

[0086] Step S35: The location of the package is defined as the vertex of the first truck that is selected the most times.

[0087] First, during positioning, a dynamic error radius calculation based on signal strength more accurately reflects the uncertainty range of the package's location, avoiding the over-segmentation problem caused by fixed thresholds. Then, corresponding candidate trucks are selected using Euclidean distance, giving closer trucks higher priority in competitive allocation and reducing the occurrence of long-distance mismatches. Experimental data shows that this algorithm reduces the misclassification rate of outliers by approximately 40% compared to traditional methods, validating its robustness. Finally, a category selection algorithm enforces local spatial consistency constraints after the initial attribution judgment, speeding up the processing of ambiguous points, especially in areas with high truck density.

[0088] The following example illustrates this: For example, in a truck area, there are trucks A, B, and C, and in the same order batch, there are packages 1, 2, 3, 4, and 5. If the judgment ranges of all five packages intersect only with truck A, the order batch is defined as including truck A. If the judgment range of one package intersects multiple trucks, or if the judgment range of any package differs from the candidate truck that intersects the judgment ranges of the others, the five packages are defined as ambiguous points. The Euclidean distance Di between each ambiguous point and the center of the candidate truck is then calculated. Assuming that three packages have the shortest Euclidean distance Di with truck A, truck A is associated with all three packages and is therefore selected as the first truck. The number of times truck A is selected increases by 1. However, if truck A is directly included, the local spatial consistency constraint is ignored, which can lead to positioning errors, especially in high-density areas where trucks are less than 5 meters apart. Therefore, in the present invention, step S34 is also executed to continuously update the number of times the first truck and each truck are selected through the category selection algorithm. After selection by the category selection algorithm, the local spatial consistency constraint can be strengthened and the processing accuracy of ambiguous points can be improved. Assume that truck A is selected 10 times and trucks B and C are selected 8 times. Finally, the location of the package is defined as the vertex of truck A.

[0089] It is worth mentioning that when multiple trucks are associated with the same number of packages, the multiple trucks will be considered as the first truck.

[0090] Preferably, the type selection algorithm steps are as follows:

[0091] Step A: Get the center coordinates of the candidate trucks as the cluster center points;

[0092] Step B: Calculate the distance from each ambiguous point to each cluster center, associate the ambiguous point with the nearest cluster center, and locate the associated ambiguous points as category points. Obtain the cluster center with the most associated category points, and use its corresponding candidate truck as the first truck. Record the number of times the first truck is selected.

[0093] Step C: Obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position;

[0094] Step D: Repeat steps B to C until the number of iterations is greater than the loop threshold.

[0095] like Figure 3 As shown in (2), the center coordinates of truck A, truck B, and truck C are represented by green, blue, and yellow ×, respectively, and the circles are ambiguous points. Figure 3 (3) Then calculate the distance between each ambiguous point and each cluster center point, and associate the ambiguous point with the nearest cluster center point. At this time, the green × is associated with the most type points, and the green × corresponds to truck A. At this time, truck A is selected as the first truck, and the number of times truck A is selected is +1. Then obtain the average position of the type points associated with the cluster center point, and update the cluster center point with the average position, as shown in the following example: Figure 3 As shown in (4), the position of the cluster center changes, and the distance between the ambiguous point and it also changes. Therefore, step B needs to be re-executed to re-associate the ambiguous point with the cluster center according to the distance between the ambiguous point and the cluster center, as shown in Figure 3 As shown in (5), at this point, the green × is still associated with the most category points, and the green × corresponds to Truck A. Truck A is now selected as the first truck, and the number of times Truck A is selected is increased by 1. Steps B to C are repeated continuously until the number of iterations exceeds the loop threshold. At this time, the number of times the truck is selected is pushed out, and the number of times it is selected once in step S33 is added to get the total number of times it is selected. The truck with the most total selections is used as the location definition of the package.

[0096] A package positioning system based on a synthesis algorithm, using the package positioning method based on a synthesis algorithm, comprising a data acquisition module, a modeling module, and a determination module;

[0097] The data acquisition module is used to obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package;

[0098] The modeling module is used to model the trucks in the truck area, and each truck is represented by a rectangle;

[0099] The determination module is used to construct a circular judgment range based on the current location of the package and the error radius, and determine the truck where the package is located based on the geometric relationship between the judgment range and the truck's modeling area.

[0100] Preferably, the data acquisition module includes a weight submodule and a radius acquisition submodule;

[0101] The weight submodule is used to define a distance weight corresponding to each distance range based on a preset distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package;

[0102] The radius acquisition submodule is used to adjust the distance between the first base station and the package using the distance weight to obtain a first distance, and obtain the error radius according to the first distance and the distance weight.

[0103] Preferably, the determination module includes a first submodule and a second submodule;

[0104] When the judgment ranges of all packages intersect only with the same truck model, the first submodule is called, and the first submodule defines the location of the package as the vertex of the truck;

[0105] When the number of truck models intersecting the judgment range is not unique, calling the second submodule, the second submodule is used to count the trucks intersecting the judgment range as candidate trucks;

[0106] Treat all packages as points of ambiguity;

[0107] Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center;

[0108] For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected;

[0109] Reselect a new first truck for each ambiguous point using the category selection algorithm, and record the number of times the first truck is selected;

[0110] Define the location of a package as the vertex of the first truck that was selected the most times.

[0111] Preferably, the second submodule includes a first definition unit, a clustering unit, a second definition unit and a loop unit;

[0112] The first definition unit is used to obtain the center coordinates of the candidate truck as the cluster center point

[0113] The clustering unit is used to calculate the distance between each ambiguous point and each cluster center point, associate the ambiguous point with the nearest cluster center point, locate the associated ambiguous point as a category point, obtain the cluster center point with the most associated category points, and use the candidate truck corresponding to it as the first truck, and record the number of times the first truck is selected;

[0114] The second definition unit is used to obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position;

[0115] The loop unit is used to repeatedly call the clustering unit and the second definition unit until the number of iterations is greater than the loop threshold.

[0116] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative uses of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0117] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A package positioning method based on a synthesis algorithm, characterized in that: The steps include: Step S1: Obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package; Step S2: Model the trucks in the truck area, and represent each truck with a rectangle; Step S3: A circular judgment range is constructed based on the current location of the package and the error radius, and the truck where the package is located is determined based on the geometric relationship between the judgment range and the truck's modeling area.

2. The package positioning method based on the synthesis algorithm according to claim 1, characterized in that: The process of calculating the error radius in step S1 by using the distances between the three first base stations and the package is as follows: Step S11: Based on a preset distance range, define a distance weight corresponding to each distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package; Step S12: using the distance weight to adjust the distance between the first base station and the package to obtain a first distance, and obtaining the error radius according to the first distance and the distance weight; The error radius is obtained as follows: where w i is the distance weight, d i ' is the first distance, d' i =w i *d i , d i is the distance between the first base station and the package.

3. The package positioning method based on the synthesis algorithm according to claim 1, characterized in that: The modeling rules for trucks in the truck area in step S2 are as follows: The spatial region model of the truck is constructed based on its geometric parameters; its vertex coordinates are calculated using the following formula: Where (x c ,y c ) are the horizontal and vertical coordinates of the center of the truck, L and W are the length and width of the truck, and θ is the rotation angle.

4. The package positioning method based on a synthesis algorithm as described in claim 3, characterized in that: The rules for determining the truck where the package is located based on the geometric relationship between the judgment range and the truck modeling area in step S3 are as follows: If the judgment range of all packages only intersects with the same truck model, the location of the package is defined as the vertex of the truck; If the number of intersections between the judgment range of a package and the truck model is not unique, perform the following steps: Step S31: Count the trucks that intersect with the judgment range as candidate trucks; Treat all packages as points of ambiguity; Step S32: Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center; Step S33: For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected; Step S34: reselecting a new first truck for each ambiguous point using the category selection algorithm, and recording the number of times the first truck is selected; Step S35: The location of the package is defined as the vertex of the first truck that is selected the most times.

5. The package positioning method based on the synthesis algorithm according to claim 4, characterized in that: The steps of the category selection algorithm are as follows: Step A: Get the center coordinates of the candidate trucks as the cluster center points; Step B: Calculate the distance from each ambiguous point to each cluster center, associate the ambiguous point with the nearest cluster center, and locate the associated ambiguous points as category points. Obtain the cluster center with the most associated category points, and use its corresponding candidate truck as the first truck. Record the number of times the first truck is selected. Step C: Obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position; Step D: Repeat steps B to C until the number of iterations is greater than the loop threshold.

6. A package positioning system based on a synthesis algorithm, characterized in that: A package positioning method based on a synthetic algorithm according to any one of claims 1 to 5, comprising a data acquisition module, a modeling module, and a determination module; The data acquisition module is used to obtain the three base stations closest to the current location of the package as the first base station, and calculate the error radius based on the distance between the three first base stations and the package; The modeling module is used to model the trucks in the truck area, and each truck is represented by a rectangle; The determination module is used to construct a circular judgment range based on the current location of the package and the error radius, and determine the truck where the package is located based on the geometric relationship between the judgment range and the truck's modeling area.

7. The package positioning system based on the synthesis algorithm according to claim 6, characterized in that: The data acquisition module includes a weight submodule and a radius acquisition submodule; The weight submodule is used to define a distance weight corresponding to each distance range based on a preset distance range, and assign a distance weight to each first base station according to the distance between each first base station and the package; The radius acquisition submodule is used to adjust the distance between the first base station and the package using the distance weight to obtain a first distance, and obtain the error radius according to the first distance and the distance weight.

8. The package positioning system based on synthesis algorithm according to claim 6, characterized in that: The determination module includes a first submodule and a second submodule; When the judgment ranges of all packages intersect only with the same truck model, the first submodule is called, and the first submodule defines the location of the package as the vertex of the truck; When the number of truck models intersecting the judgment range is not unique, calling the second submodule, the second submodule is used to count the trucks intersecting the judgment range as candidate trucks; Treat all packages as points of ambiguity; Calculate the Euclidean distance Di between each ambiguous point and each candidate truck center; For each ambiguous point, select the candidate truck corresponding to the smallest Euclidean distance Di, obtain the candidate truck with the most associations as the first truck, and record the number of times the first truck is selected; Reselect a new first truck for each ambiguous point using the category selection algorithm, and record the number of times the first truck is selected; Define the location of a package as the vertex of the first truck that was selected the most times.

9. The package positioning system based on the synthesis algorithm according to claim 8, characterized in that: The second submodule includes a first definition unit, a clustering unit, a second definition unit and a loop unit; The first definition unit is used to obtain the center coordinates of the candidate truck as the cluster center point The clustering unit is used to calculate the distance between each ambiguous point and each cluster center point, associate the ambiguous point with the nearest cluster center point, locate the associated ambiguous point as a category point, obtain the cluster center point with the most associated category points, and use the candidate truck corresponding to it as the first truck, and record the number of times the first truck is selected; The second definition unit is used to obtain the average position of the category points associated with the cluster center point, and update the cluster center point with the average position; The loop unit is used to repeatedly call the clustering unit and the second definition unit until the number of iterations is greater than the loop threshold.

Images