Signal intensity processing method and device and vehicle key positioning method
By collecting and processing signal strength during the vehicle key movement, the problem of low positioning accuracy in the prior art is solved, and more efficient and accurate vehicle key positioning is achieved.
Patent Information
- Application Number
- CN202510180743.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-18
- Publication Date
- 2025-05-27
AI Technical Summary
In the prior art, the positioning accuracy of the vehicle key positioning algorithm model is not high, mainly due to the insufficient density of point settings, resulting in insufficient collection efficiency and accuracy of signal strength data.
By receiving signals during the process of moving the vehicle key according to the preset path, multiple initial signal strengths are obtained, and smoothing and clustering are performed to obtain the target signal strength and its corresponding position data, which are used to train the positioning algorithm model.
The positioning accuracy of the training positioning algorithm model is improved, higher training efficiency and effect are achieved, and the accuracy of vehicle key positioning is enhanced.
Smart Images
Figure CN120050595A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicles, and in particular, to a method for processing signal strength, a device, a method for locating a vehicle key, a computer device, a computer-readable storage medium, and a computer program product. Background Art
[0002] With the development of vehicle technology, vehicle keys are also iteratively updated. Currently, the adoption rate of in-vehicle Bluetooth keys is continuously increasing. The vehicle can execute different functions corresponding to the position where the in-vehicle Bluetooth key is located.
[0003] In the related art, multiple points are usually set at different positions in the surrounding area of the vehicle, and the signal strength when the in-vehicle Bluetooth key is placed at these points is collected by the listening nodes on the vehicle, and then the positioning algorithm model is trained based on these signal strengths. However, the setting of points in the related art is not dense enough, resulting in low positioning accuracy of the trained positioning algorithm model. Summary of the Invention
[0004] Based on this, it is necessary to provide a method for processing signal strength, a device, a method for locating a vehicle key, a computer device, a computer-readable storage medium, and a computer program product that can improve the positioning accuracy of the trained positioning algorithm model for the above technical problems.
[0005] In a first aspect, the present application provides a method for processing signal strength, including:
[0006] Obtain a plurality of initial signal strengths; the plurality of initial signal strengths are determined based on the signals received during the movement of the vehicle key along a preset path, and each initial signal strength in the plurality of initial signal strengths corresponds to a position point in the preset path;
[0007] Perform smoothing processing on the plurality of initial signal strengths to obtain a plurality of intermediate signal strengths;
[0008] Perform clustering processing on the plurality of intermediate signal strengths to obtain a plurality of clusters; the intermediate signal strengths in the plurality of clusters belong to different signal strength ranges;
[0009] Respectively determine the target signal strengths corresponding to the plurality of clusters; the target signal strengths and the position data corresponding to the target signal strengths are used to train the positioning algorithm model.
[0010] In one embodiment, the obtaining of the plurality of initial signal strengths includes:
[0011] Divide the surrounding area of the vehicle into a plurality of sub-regions; the plurality of sub-regions respectively correspond to response functions for the vehicle key;
[0012] Obtain multiple initial signal strengths corresponding to each of the multiple sub-regions; the multiple initial signal strengths corresponding to each sub-region are determined based on signals sent during the process of a receiving vehicle key moving along a preset path in each sub-region.
[0013] In one embodiment, the obtaining multiple initial signal strengths corresponding to each of the multiple sub-regions includes:
[0014] Switch the carrying manner of the vehicle key;
[0015] Obtain multiple initial signal strengths corresponding to each of the multiple sub-regions in the current carrying manner, and establish an association relationship between the multiple initial signal strengths and the current carrying manner.
[0016] In one embodiment, the respectively determining target signal strengths corresponding to the multiple clusters includes:
[0017] Based on the intermediate signal strengths in the multiple clusters, respectively calculate the target signal strengths corresponding to the multiple clusters.
[0018] In one embodiment, the based on the intermediate signal strengths in the multiple clusters, respectively calculating the target signal strengths corresponding to the multiple clusters includes:
[0019] Respectively calculate the average value of the intermediate signal strengths in the multiple clusters to obtain the target signal strengths corresponding to the multiple clusters.
[0020] In one embodiment, the smoothing the multiple initial signal strengths to obtain multiple intermediate signal strengths includes:
[0021] Based on the adjacent relationship between position points in the preset path, smooth the multiple initial signal strengths to obtain multiple intermediate signal strengths.
[0022] In one embodiment, the based on the adjacent relationship between position points in the preset path, smoothing the multiple initial signal strengths to obtain multiple intermediate signal strengths includes:
[0023] Based on the adjacent relationship between position points in the preset path, perform filtering processing on the multiple initial signal strengths to obtain multiple intermediate signal strengths; the manner of performing filtering processing on the multiple initial signal strengths includes at least one of mean filtering, median filtering, Gaussian filtering, and Kalman filtering.
[0024] In a second aspect, the present application further provides a vehicle key positioning method, including:
[0025] In response to receiving a signal sent by a vehicle key, determine the signal strength of the signal;
[0026] Invoke a pre-trained positioning algorithm model to process the signal strength and obtain position data corresponding to the signal strength; the positioning algorithm model is trained based on the target signal strength and the position data corresponding to the target signal strength described in any one of the above.
[0027] In a third aspect, the present application also provides a signal strength processing device, including:
[0028] An initial value acquisition module for acquiring a plurality of initial signal strengths; the plurality of initial signal strengths are determined based on signals sent by a vehicle key during movement along a preset path, and each initial signal strength in the plurality of initial signal strengths corresponds to a position point in the preset path;
[0029] A smoothing processing module for smoothing the plurality of initial signal strengths to obtain a plurality of intermediate signal strengths;
[0030] A clustering processing module for clustering the plurality of intermediate signal strengths to obtain a plurality of clusters; the intermediate signal strengths in the plurality of clusters belong to different signal strength ranges;
[0031] A target value determination module for respectively determining the target signal strengths corresponding to the plurality of clusters; the target signal strength and the position data corresponding to the target signal strength are used to train a positioning algorithm model.
[0032] In a fourth aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any one of the above are implemented.
[0033] In a fifth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.
[0034] In a sixth aspect, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.
[0035] The above-mentioned signal strength processing method, device, vehicle key positioning method, computer device, computer-readable storage medium, and computer program product can obtain dynamic signal strength by receiving the signal of the vehicle key during the movement of the vehicle key along a preset path, and can densely and efficiently collect the signal strength corresponding to the position points in the area around the vehicle. By performing smoothing processing on the collected dynamic signal strength to reduce the jump of the signal strength between position points, the correction of the dynamic signal strength can be achieved. The amount of data of the dynamic signal strength is usually large. By dividing the corrected dynamic signal strength into multiple clusters and taking the target signal strength corresponding to each cluster, the scale of the training data can be reduced, and at the same time, the uniform distribution of the position points corresponding to the target signal strength can be achieved. Therefore, using the target signal strength and its corresponding position data to train the positioning algorithm model can achieve high training efficiency and good training effect. Furthermore, the accuracy of vehicle key positioning by training the positioning algorithm model can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0037] Figure 1 It is a schematic diagram of the signal strength obtained by one static acquisition and the signal strength obtained by one dynamic acquisition in an embodiment;
[0038] Figure 2 It is a schematic flowchart of the signal strength processing in an embodiment;
[0039] Figure 3 It is a schematic diagram of the distribution of listening nodes on the vehicle in an embodiment;
[0040] Figure 4 It is a schematic diagram of multiple initial signal strengths and multiple intermediate signal strengths obtained by performing hybrid filtering processing on the multiple initial signal strengths in an embodiment;
[0041] Figure 5 It is a schematic flowchart of step S102 in an embodiment;
[0042] Figure 6 It is a schematic diagram of multiple sub-regions in the area around the vehicle in an embodiment;
[0043] Figure 7 It is a schematic flowchart of step S220 in an embodiment;
[0044] Figure 8 A schematic diagram of multiple intermediate signal strengths and target signal strengths corresponding to multiple clusters obtained by clustering the multiple intermediate signal strengths in an embodiment;
[0045] Figure 9 A structural block diagram of a signal strength processing device in an embodiment;
[0046] Figure 10 An internal structure diagram of a computer device in an embodiment. Detailed implementation manners
[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.
[0048] In the static acquisition method, the vehicle key is placed at different points set in the surrounding area of the vehicle, and the signal strength of the vehicle key is acquired at each point. There are problems such as insufficient density of points, cumbersome acquisition process, and long acquisition time. In this case, in the dynamic acquisition method, the vehicle key is moved along a planned path while continuously acquiring the signal strength of the vehicle key, which can achieve a wide coverage of acquisition points and high acquisition efficiency. However, please refer to Figure 1 , Figure 1 A schematic diagram of the signal strength obtained by one static acquisition and the signal strength obtained by one dynamic acquisition in an embodiment. Among them, R01 is the signal strength obtained by one static acquisition, and R02 is the signal strength obtained by one dynamic acquisition. The signal strength obtained by dynamic acquisition has the following problems: large dynamic range, large fluctuation, and large interference; the large amount of data will slow down the speed of training the positioning algorithm model; if the vehicle key does not move at a uniform speed during the dynamic acquisition process, the position distribution of the data is unbalanced, which will affect the training effect of the positioning algorithm model.
[0049] In an embodiment, as Figure 2 shown, a signal strength processing method is provided. In this embodiment, an example is given in which the method is applied to a terminal. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:
[0050] Step S102, obtain multiple initial signal strengths; the multiple initial signal strengths are determined based on signals received during the movement of the vehicle key along a preset path, and each initial signal strength in the multiple initial signal strengths corresponds to a position point in the preset path.
[0051] Among them, the preset path at least includes position points at various distances from the vehicle (for example, 1 meter, 2 meters, 3 meters, etc.) and intermediate position points between these position points. The preset path can cover any position in the area around the vehicle. For example, the number of preset paths can be one or more. Each preset path can first approach the vehicle and then move away from the vehicle. The vehicle key can be carried by a tester or a robot and move along the preset path at a certain speed.
[0052] Specifically, the vehicle key can be an in-vehicle Bluetooth key or other types of wireless signal transmitting devices. The vehicle key can be devices such as a digital key, a smart terminal, etc. The initial signal strength can be the Received Signal Strength Indicator (RSSI). The initial signal strength can be collected by one or more listening nodes on the vehicle. For example, please refer to Figure 3 , Figure 3 which is a schematic diagram of the distribution of listening nodes on the vehicle in an embodiment. Among them, B01 is the main listening node, and B02 is other listening nodes.
[0053] Exemplarily, during the process of the vehicle key moving along the preset path in the area around the vehicle, the listening nodes on the vehicle can receive the signal of the vehicle key and determine its signal strength at regular intervals (for example, 50 milliseconds for a mobile phone key and 200 milliseconds for a remote control key), obtaining multiple initial signal strengths. At the same time, the position data of each initial signal strength and its corresponding position point can be stored. The position data of the position point can include the area where it is located, the distance, the direction, etc.
[0054] Step S104, perform smoothing processing on the multiple initial signal strengths to obtain multiple intermediate signal strengths.
[0055] Please refer to Figure 4 , Figure 4 which is a schematic diagram of multiple initial signal strengths and multiple intermediate signal strengths obtained by performing hybrid filtering processing on the multiple initial signal strengths in an embodiment. Among them, R03 is the multiple initial signal strengths, and R04 is the multiple intermediate signal strengths obtained by performing hybrid filtering processing on R03. Since the actually collected initial signal strengths (as shown by R03), for adjacent position points, there are cases where the intensity values jump. Therefore, the multiple collected initial signal strengths can be smoothed to reduce the jump amplitude of the initial signal strengths corresponding to adjacent position points, making the changes of the multiple initial signal strengths smoother and closer to the actual situation.
[0056] Exemplarily, multiple initial signal strengths can be sorted according to the adjacent relationship of the corresponding position points in the preset path. Alternatively, during the movement of the vehicle key along the preset path, the initially collected signal strengths are sequentially stored to obtain multiple initial signal strengths arranged in time sequence. At this time, the position points corresponding to adjacent initial signal strengths are also adjacent in the preset path.
[0057] Step S106: Perform clustering processing on multiple intermediate signal strengths to obtain multiple clusters; the intermediate signal strengths in the multiple clusters belong to different signal strength ranges.
[0058] Exemplarily, the method of performing clustering processing on multiple intermediate signal strengths may include at least one of the following: K-means clustering algorithm, hierarchical clustering, spectral clustering, Gaussian mixture model. Specifically, when performing clustering processing on m intermediate signal strengths to obtain n clusters, n is less than m.
[0059] Step S108: Determine the target signal strengths corresponding to the multiple clusters respectively; the target signal strengths and the position data corresponding to the target signal strengths are used to train the positioning algorithm model.
[0060] Among them, the target signal strength corresponding to a cluster can be determined in advance according to the signal strength range corresponding to it. For example, the target signal strength can be the maximum value, minimum value or median value within the signal strength range. Alternatively, it can also be calculated based on the intermediate signal strengths included therein. A cluster can correspond to one or a relatively small number of target signal strengths.
[0061] In the above method for processing signal strengths, by receiving the signal of the vehicle key during the movement of the vehicle key along the preset path, dynamic signal strengths can be obtained, realizing dense and efficient acquisition of the signal strengths corresponding to the position points in the surrounding area of the vehicle; by performing smoothing processing on the collected dynamic signal strengths to reduce the jump of the signal strengths between position points, correction of the dynamic signal strengths can be realized; the data volume of the dynamic signal strengths is usually large. By dividing the corrected dynamic signal strengths into multiple clusters and taking the target signal strength corresponding to each cluster, the scale of the training data can be reduced, and at the same time, the uniform distribution of the position points corresponding to the target signal strengths can be realized. Therefore, using the target signal strengths and their corresponding position data to train the positioning algorithm model can achieve high training efficiency and good training effect. Furthermore, it can improve the accuracy of vehicle key positioning by training the positioning algorithm model.
[0062] In an exemplary embodiment, as Figure 5 shown, the above step S102 may include:
[0063] Step S210: Divide the area around the vehicle into multiple sub - areas; each of the multiple sub - areas corresponds to a response function for the vehicle key.
[0064] Step S220: Obtain multiple initial signal strengths corresponding to each sub - area among the multiple sub - areas; the multiple initial signal strengths corresponding to each sub - area are determined based on the signals sent during the process of receiving the vehicle key moving along a preset path in each sub - area.
[0065] Please refer to Figure 6 , Figure 6 For a schematic diagram of multiple sub - areas of the area around the vehicle in an embodiment. Among them, divided according to the orientation of the vehicle, Z01 is the area inside the vehicle, Z10 is the driver's area, Z20 is the co - driver's area, Z30 is the front - end area of the vehicle, Z40 is the rear - end area of the vehicle; divided according to the distance from the vehicle, Z11 is the wake - up area, Z12 is the welcome area, and Z13 is the unlocking area.
[0066] Exemplarily, in response to establishing a connection with the vehicle key, a sub - area can be selected as the data collection area; plan a path within this sub - area to ensure that the path fully covers this sub - area; obtain the multiple initial signal strengths corresponding to this sub - area by means of manual collection or automatic collection; until reaching the end of the path, this collection is completed, and then switch to other sub - areas.
[0067] Among them, the way of manual collection can be that while the tester carries the vehicle key and moves along the preset path in the sub - area, the listening nodes on the vehicle synchronously collect the initial signal strengths. The way of automatic collection can be to use a calibration robot to map the area around the vehicle in advance so that the robot can drive along the preset path. While the robot carries the vehicle key and drives along the preset path, the listening nodes on the vehicle synchronously collect the initial signal strengths. For the way of automatic collection, the position information of the robot can also be synchronously collected, and the initial signal strengths can be classified into different sub - areas according to the position information.
[0068] In a possible implementation, the intermediate signal strengths obtained after smoothing multiple initial signals collected for the same sub - area can be clustered together. In this way, the balanced distribution of the target signal strength among regions can be achieved.
[0069] Furthermore, as Figure 7 shown, the above - mentioned step S220 may include:
[0070] Step S221: Switch the carrying mode of the vehicle key.
[0071] Step S222: Obtain the multiple initial signal strengths corresponding to each sub-region among the multiple sub-regions in the current carrying manner, and establish an association relationship between the multiple initial signal strengths and the current carrying manner.
[0072] Exemplarily, after selecting a sub-region as the data collection area, the carrying manner can be switched, and the vehicle key can be repeatedly carried and moved along a preset path within the sub-region. The initial signal strength of the vehicle key is collected multiple times to obtain multiple initial signal strengths associated with each carrying manner until all carrying manners are switched, and then switch to other sub-regions. Among them, the carrying manners of the vehicle key can include: held in hand, placed in a pocket, placed in a backpack, etc.
[0073] In this embodiment, by collecting dynamic signal strengths in partitions, the distribution balance of the target signal strength among regions can be achieved, and higher training efficiency and effects can be realized. Further, by repeatedly collecting dynamic signal strengths in multiple carrying manners in each sub-region, more comprehensive and reliable dynamic signal strengths can be obtained to adapt to different usage scenarios and improve the application performance of the positioning algorithm model in the actual environment.
[0074] In an exemplary embodiment, the above step S108 may include:
[0075] Step S810: Calculate the target signal strengths corresponding to the multiple clusters respectively based on the intermediate signal strengths in the multiple clusters.
[0076] Among them, the target signal strength corresponding to a cluster can be a typical value calculated based on the intermediate signal strengths it includes. For example, the target signal strength can be the maximum, minimum, average, or median value of the intermediate signal strengths included in this cluster, etc.
[0077] Please refer to Figure 8 , Figure 8 which is a schematic diagram of multiple intermediate signal strengths and the target signal strengths corresponding to multiple clusters obtained by clustering the multiple intermediate signal strengths in an embodiment. Among them, R11, R12, R13, and R14 are the multiple intermediate signal strengths corresponding to different listening nodes respectively, and R21 is the clustering result of the multiple clusters obtained by clustering these intermediate signal strengths. The value of R21 represents the cluster identifier, and the intermediate signal strengths of the listening nodes corresponding to the same R21 value can be classified into the same cluster. It can be understood that Figure 8 taking the example of clustering the multiple intermediate signal strengths corresponding to different listening nodes together, the multiple intermediate signal strengths corresponding to different listening nodes can also be clustered separately. The embodiments of the present application do not make limitations in this regard.
[0078] Further, the above step S810 may include:
[0079] Step S811 , respectively calculating the average values of the intermediate signal strengths in the multiple clusters to obtain the target signal strengths corresponding to the multiple clusters.
[0080] In this embodiment, the target signal strength is calculated in real time based on the intermediate signal strengths contained in each cluster, so that the target signal strength can more accurately reflect the overall position of each cluster. For example, the average value of the intermediate signal strengths is used as the target signal strength, which can remove the interference value after filtering.
[0081] In an exemplary embodiment, the above step S104 may include:
[0082] Step S410: Based on the neighbor relationship between the position points in the preset path, a plurality of initial signal strengths are smoothed to obtain a plurality of intermediate signal strengths.
[0083] For example, hybrid filtering (such as Figure 4 As shown in FIG. 1 ), moving average, wavelet transform, etc. are used to smooth multiple initial signal intensities to obtain multiple intermediate signal intensities.
[0084] Furthermore, the above step S410 may include:
[0085] Step S411, based on the adjacent relationship between the position points in the preset path, multiple initial signal strengths are filtered to obtain multiple intermediate signal strengths; the method of filtering the multiple initial signal strengths includes at least one of mean filtering, median filtering, Gaussian filtering, and Kalman filtering.
[0086] Exemplarily, when multiple initial signal strengths are sorted according to the adjacent relationship between corresponding position points, a sliding window can be used to slide on a sequence of multiple initial signal strengths to obtain the initial signal strengths covered by the position of the sliding window. First, the maximum and minimum values are eliminated, and then the mean or median of the remaining initial signal strengths is calculated to obtain the intermediate processing result corresponding to the current sliding window position. Finally, the intermediate processing result corresponding to the current sliding window position is combined with the intermediate processing result corresponding to the previous sliding window position to perform Kalman filtering and output the intermediate signal strength.
[0087] In this embodiment, by adopting a filtering method to perform smoothing processing, it is possible to simply and conveniently make the dynamic signal strength more stable, thereby improving the effect of subsequent processing.
[0088] In one embodiment, a vehicle key positioning method is provided. This embodiment uses the method applied to a vehicle terminal as an example for illustration. It is understandable that the method can also be applied to a system including a vehicle terminal and a server, and is implemented through the interaction between the vehicle terminal and the server. The method includes the following steps:
[0089] Step S301: In response to receiving a signal sent by a vehicle key, determine the signal strength of the signal.
[0090] Step S302: Invoke a pre-trained positioning algorithm model to process the signal strength and obtain position data corresponding to the signal strength; the positioning algorithm model is trained based on the target signal strength and the position data corresponding to the target signal strength obtained by the signal strength processing method described in any one of the above.
[0091] Exemplarily, the vehicle terminal can input the signal strengths collected by each listening node into the pre-trained positioning algorithm model for processing, so that the positioning algorithm model can accurately output the area where the vehicle key is currently located. Further, the vehicle terminal can perform different response functions according to the area where the vehicle key is currently located (for example, welcome, automatic unlocking / locking, keyless start, opening the trunk, etc.).
[0092] In summary, in the above signal strength processing method, by receiving the signal of the vehicle key during the process of the vehicle key moving along a preset path, a dynamic signal strength can be obtained, realizing dense and efficient acquisition of the signal strength corresponding to the position points in the surrounding area of the vehicle; by performing smoothing processing on the collected dynamic signal strength to reduce the jump of the signal strength between position points, calibration of the dynamic signal strength can be achieved; the data volume of the dynamic signal strength is usually large, by dividing the calibrated dynamic signal strength into multiple clusters and taking the target signal strength corresponding to each cluster, the scale of the training data can be reduced, and at the same time, the uniform distribution of the position points corresponding to the target signal strength can be realized. Therefore, using the target signal strength and its corresponding position data to train the positioning algorithm model can achieve high training efficiency and good training effect, and further, can improve the accuracy of vehicle key positioning by training the positioning algorithm model.
[0093] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.
[0094] Based on the same inventive concept, an embodiment of the present application further provides a signal strength processing device for implementing the signal strength processing method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the signal strength processing device provided below can refer to the limitations on the signal strength processing method in the above text, and will not be repeated here.
[0095] In an exemplary embodiment, as Figure 9 shown, a signal strength processing device 500 is provided, including: an initial value acquisition module 501, a smoothing processing module 502, a clustering processing module 503, and a target value determination module 504, where:
[0096] The initial value acquisition module 501 is configured to acquire multiple initial signal strengths; the multiple initial signal strengths are determined based on signals sent by a received vehicle key during movement along a preset path, and each initial signal strength in the multiple initial signal strengths corresponds to a position point in the preset path.
[0097] The smoothing processing module 502 is configured to perform smoothing processing on the multiple initial signal strengths to obtain multiple intermediate signal strengths.
[0098] The clustering processing module 503 is configured to perform clustering processing on the multiple intermediate signal strengths to obtain multiple clusters; the intermediate signal strengths in the multiple clusters belong to different signal strength ranges.
[0099] The target value determination module 504 respectively determines the target signal strengths corresponding to the multiple clusters; the target signal strengths and the position data corresponding to the target signal strengths are used to train a positioning algorithm model.
[0100] In an exemplary embodiment, the above initial value acquisition module 501 may include:
[0101] A region division sub-module, configured to divide the area around the vehicle into multiple sub-regions; each of the multiple sub-regions corresponds to a response function for the vehicle key.
[0102] A partition acquisition sub-module, configured to acquire multiple initial signal strengths corresponding to each sub-region among the multiple sub-regions; the multiple initial signal strengths corresponding to each sub-region are determined based on signals sent by a received vehicle key during movement along a preset path in each sub-region.
[0103] In an exemplary embodiment, the above partition acquisition sub-module may include:
[0104] A carrying mode switching unit, configured to switch the carrying mode of the vehicle key.
[0105] A repeated acquisition unit is configured to obtain multiple initial signal strengths corresponding to each sub-region in multiple sub-regions under the current carrying mode, and establish an association relationship between the multiple initial signal strengths and the current carrying mode.
[0106] In an exemplary embodiment, the above-mentioned target value determination module 504 may include:
[0107] A target value calculation sub-module is configured to calculate target signal strengths corresponding to multiple clusters respectively based on the intermediate signal strengths in the multiple clusters.
[0108] In an exemplary embodiment, the above-mentioned target value calculation sub-module may include:
[0109] An average value calculation unit is configured to calculate the average value of the intermediate signal strengths in the multiple clusters respectively to obtain the target signal strengths corresponding to the multiple clusters.
[0110] In an exemplary embodiment, the above-mentioned smoothing processing module 502 may include:
[0111] A smoothing processing module sub-module is configured to perform smoothing processing on the multiple initial signal strengths based on the adjacent relationship between the position points in the preset path to obtain multiple intermediate signal strengths.
[0112] In an exemplary embodiment, the above-mentioned smoothing processing module sub-module may include:
[0113] A filtering processing unit is configured to perform filtering processing on the multiple initial signal strengths based on the adjacent relationship between the position points in the preset path to obtain multiple intermediate signal strengths; the ways of performing filtering processing on the multiple initial signal strengths include at least one of mean filtering, median filtering, Gaussian filtering, and Kalman filtering.
[0114] Each module in the above-mentioned signal strength processing device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or be stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to the above-mentioned modules.
[0115] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the target signal strength, the position data corresponding to the target signal strength, and the positioning algorithm model. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for processing signal strength.
[0116] Those skilled in the art can understand that Figure 10 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.
[0117] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.
[0118] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.
[0119] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.
[0120] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.
[0121] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.
[0122] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims
1. A method for processing signal strength, characterized in that: include: obtaining multiple initial signal strengths; The multiple initial signal strengths are determined based on receiving a signal sent by the vehicle key during movement along a preset path, and each of the multiple initial signal strengths corresponds to a position point in the preset path; Smoothing the multiple initial signal strengths to obtain multiple intermediate signal strengths; Clustering the multiple intermediate signal intensities to obtain multiple clusters; the intermediate signal intensities in the multiple clusters belong to different signal strength ranges; The target signal strengths corresponding to the multiple clusters are determined respectively; the target signal strengths and the position data corresponding to the target signal strengths are used to train a positioning algorithm model.
2. The method according to claim 1, characterized in that The obtaining of multiple initial signal strengths comprises: Dividing the area around the vehicle into a plurality of sub-areas; the plurality of sub-areas respectively correspond to response functions for the vehicle key; A plurality of initial signal strengths corresponding to each of the plurality of sub-areas are obtained; the plurality of initial signal strengths corresponding to each of the plurality of sub-areas are determined based on receiving a signal sent by a vehicle key during movement along a preset path in each of the plurality of sub-areas.
3. The method according to claim 2, characterized in that The acquiring a plurality of initial signal strengths corresponding to each of the plurality of sub-areas comprises: Switch the way you carry your vehicle keys; Acquire multiple initial signal strengths corresponding to each sub-area in the multiple sub-areas under the current carrying mode, and establish an association relationship between the multiple initial signal strengths and the current carrying mode.
4. The method according to claim 1, characterized in that: The respectively determining the target signal strengths corresponding to the plurality of clusters includes: Based on the intermediate signal strengths in the multiple clusters, target signal strengths corresponding to the multiple clusters are calculated respectively.
5. The method according to claim 4, characterized in that The calculating, based on the intermediate signal strengths in the multiple clusters, the target signal strengths corresponding to the multiple clusters respectively includes: The average values of the intermediate signal strengths in the multiple clusters are respectively calculated to obtain the target signal strengths corresponding to the multiple clusters.
6. The method according to claim 1, characterized in that The step of smoothing the multiple initial signal strengths to obtain multiple intermediate signal strengths includes: Based on the adjacent relationship between the position points in the preset path, the multiple initial signal strengths are smoothed to obtain multiple intermediate signal strengths.
7. The method according to claim 6, characterized in that The step of smoothing the multiple initial signal strengths based on the adjacent relationship between the position points in the preset path to obtain multiple intermediate signal strengths includes: Based on the adjacent relationship between the position points in the preset path, the multiple initial signal strengths are filtered to obtain multiple intermediate signal strengths; the method of filtering the multiple initial signal strengths includes at least one of mean filtering, median filtering, Gaussian filtering, and Kalman filtering.
8. A vehicle key positioning method, characterized in that: include: In response to receiving a signal transmitted by a vehicle key, determining a signal strength of the signal; Call a pre-trained positioning algorithm model to process the signal strength to obtain position data corresponding to the signal strength; the positioning algorithm model is trained based on the target signal strength and the position data corresponding to the target signal strength described in any one of claims 1 to 7.
9. A signal strength processing device, characterized in that: The device comprises: An initial value acquisition module, used to acquire a plurality of initial signal strengths; the plurality of initial signal strengths are determined based on receiving a signal sent by the vehicle key during movement along a preset path, each of the plurality of initial signal strengths corresponding to a position point in the preset path; A smoothing processing module, used for smoothing the multiple initial signal strengths to obtain multiple intermediate signal strengths; A clustering processing module, used for performing clustering processing on the multiple intermediate signal strengths to obtain multiple clusters; the intermediate signal strengths in the multiple clusters belong to different signal strength ranges; The target value determination module determines the target signal strengths corresponding to the multiple clusters respectively; the target signal strengths and the position data corresponding to the target signal strengths are used to train the positioning algorithm model.
10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.