Data processing method and device, equipment and storage medium
By acquiring sensor data, determining membership functions and trust levels, and calculating weights for fusion processing, the problem of inaccurate positioning by a single sensor is solved, and the accuracy of data fusion and positioning precision are improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2026-03-31
AI Technical Summary
The limitations of a single sensor lead to inaccurate positioning, and existing technologies have failed to effectively handle the uncertainties of data from different sensors, resulting in inaccurate fused data.
By acquiring sensor data from each sensor, determining the membership function, calculating the membership degree and confidence degree, obtaining the sensor weights, and performing fusion processing, fuzzy processing logic is used to improve data accuracy.
It improves the accuracy of sensor data fusion and enhances the precision of localization and obstacle recognition.
Smart Images
Figure CN121765612A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a data processing method, apparatus, device, and storage medium. Background Technology
[0002] Because individual sensors are often limited by their own limitations (such as weakened or blocked GPS signals, or accumulated errors in inertial navigation systems), using a single sensor can lead to inaccurate positioning. To address this issue, data from multiple sources, such as GPS and inertial measurement units (IMUs), can be fused, thereby enhancing the accuracy of positioning or obstacle detection modules. However, current technologies often fail to consider the varying degrees of uncertainty in data from different sensors during data fusion, resulting in inaccurate fused data. Summary of the Invention
[0003] In view of this, this application provides a data processing method, apparatus, device, and storage medium to improve the accuracy of data fusion from different sensors and improve the accuracy of positioning.
[0004] In a first aspect, embodiments of this application provide a data processing method, the method comprising:
[0005] Acquire sensor data for each sensor;
[0006] For each sensor: determine the membership function corresponding to the sensor based on the sensor data corresponding to the sensor; obtain the membership degree of the sensor based on the sensor data and the membership function; determine the trust degree of the sensor based on the membership degree; obtain the weight of the sensor based on the membership degree and the trust degree.
[0007] Based on the weights corresponding to each sensor and the sensor data corresponding to each sensor, fusion processing is performed to obtain fused data.
[0008] In this application, considering the inherent errors of the sensors themselves and the inherent ambiguity caused by changes in applicable conditions, fuzzy processing logic is adopted to fuse sensor data from different sensors. By determining the membership degree and confidence degree of each sensor, the exact weight of each sensor can be obtained, thereby ensuring the accuracy of the fused data.
[0009] In some possible embodiments, determining the membership function corresponding to the sensor based on the sensor data corresponding to the sensor includes:
[0010] Obtain the set of membership functions corresponding to the sensor data;
[0011] If the first information value in the sensor data is greater than the first preset value, then the membership function corresponding to the sensor is the first membership function in the membership function set;
[0012] If the first information value in the sensor data is greater than or equal to the second preset value and less than or equal to the first preset value, then the membership function corresponding to the sensor is the second membership function in the membership function set;
[0013] If the first information value in the sensor data is less than the second preset value, then the membership function corresponding to the sensor is the third membership function in the membership function set.
[0014] In this application, considering that the reasons for the different accuracy variations of different sensors are different, a corresponding membership function set is set for different sensors, thereby ensuring the accuracy of the constructed membership function set.
[0015] In some possible embodiments, if the sensor data is Global Positioning System (GPS) data, the first information value is the GPS signal strength; if the sensor data is high-precision map data, the first information value is the update time of the high-precision map.
[0016] In this application, corresponding first information values are set according to the reasons for the changes in the accuracy of different sensors, so as to ensure the accuracy of the calculation process.
[0017] In some possible embodiments, if the membership function is a second membership function, obtaining the membership degree of the sensor based on the sensor data and the membership function includes:
[0018] The first information value in the sensor data corresponding to the sensor is substituted into the second membership function to obtain the membership degree of the sensor.
[0019] In some possible embodiments, determining the trust level corresponding to the sensor based on the membership degree includes:
[0020] Determine the range of the membership degree in a preset reliability lookup table;
[0021] The trust level of the sensor is obtained by randomly selecting a value within the range.
[0022] In this application, by setting a trust level, the accuracy of the membership degree of each sensor obtained is further guaranteed.
[0023] In some possible embodiments, obtaining the weights corresponding to the sensor based on the membership degree and the trust degree includes:
[0024] Determine the product of the membership degree and the trust degree;
[0025] The product value is used as the weight corresponding to the sensor.
[0026] In some possible embodiments, before performing the fusion processing based on the weights corresponding to each sensor and the sensor data corresponding to each sensor, the method further includes:
[0027] The weights corresponding to each sensor are normalized to obtain the normalized weights of each sensor.
[0028] In this application, the accuracy of data processing is further improved by normalizing the weights.
[0029] Secondly, embodiments of this application provide a data processing apparatus, the apparatus comprising:
[0030] The data acquisition module is used to acquire sensor data corresponding to each sensor.
[0031] The data processing module is configured to, for each sensor,: determine the membership function corresponding to the sensor based on the sensor data corresponding to the sensor; obtain the membership degree of the sensor based on the sensor data and the membership function; determine the trust degree of the sensor based on the membership degree; and obtain the weight of the sensor based on the membership degree and the trust degree.
[0032] The data fusion module is used to perform fusion processing based on the weights corresponding to each sensor and the sensor data corresponding to each sensor to obtain fused data.
[0033] In some possible embodiments, the data processing module is specifically used for:
[0034] Obtain the set of membership functions corresponding to the sensor data;
[0035] If the first information value in the sensor data is greater than the first preset value, then the membership function corresponding to the sensor is the first membership function in the membership function set;
[0036] If the first information value in the sensor data is greater than or equal to the second preset value and less than or equal to the first preset value, then the membership function corresponding to the sensor is the second membership function in the membership function set;
[0037] If the first information value in the sensor data is less than the second preset value, then the membership function corresponding to the sensor is the third membership function in the membership function set.
[0038] In some possible embodiments, if the sensor data is Global Positioning System (GPS) data, the first information value is the GPS signal strength; if the sensor data is high-precision map data, the first information value is the update time of the high-precision map.
[0039] In some possible embodiments, the data processing module is specifically used for:
[0040] The first information value in the sensor data corresponding to the sensor is substituted into the second membership function to obtain the membership degree of the sensor.
[0041] In some possible embodiments, the data processing module is specifically used for:
[0042] Determine the range of the membership degree in a preset reliability lookup table;
[0043] The trust level of the sensor is obtained by randomly selecting a value within the range.
[0044] In some possible embodiments, the data processing module is specifically used for:
[0045] Determine the product of the membership degree and the trust degree;
[0046] The product value is used as the weight corresponding to the sensor.
[0047] In some possible embodiments, the data processing module is further configured to:
[0048] The weights corresponding to each sensor are normalized to obtain the normalized weights of each sensor.
[0049] Thirdly, another embodiment of this application also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the methods provided in the first aspect embodiment of this application.
[0050] Fourthly, another embodiment of this application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for causing a computer to perform any of the methods provided in the first aspect of this application.
[0051] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0053] Figure 1 This is a schematic diagram illustrating an application scenario of a data processing method provided in an embodiment of this application;
[0054] Figure 2 This is a schematic diagram of the overall flow of a data processing method provided in an embodiment of this application;
[0055] Figure 3 A flowchart illustrating a data processing method for determining the membership function of a sensor based on sensor data provided in this application embodiment;
[0056] Figure 4 A flowchart illustrating the determination of trust level in a data processing method provided in this application embodiment;
[0057] Figure 5 A schematic diagram of the reliability comparison of a GPS sensor for a data processing method provided in this application embodiment;
[0058] Figure 6 This application provides a schematic representation of the reliability comparison of a high-precision map sensor corresponding to a data processing method provided in an embodiment of the present application.
[0059] Figure 7 A schematic diagram illustrating the process of obtaining the weights corresponding to sensors based on membership and trust, as provided in an embodiment of this application;
[0060] Figure 8 A schematic diagram of an apparatus for a data processing method provided in an embodiment of this application;
[0061] Figure 9 This is a schematic diagram of an electronic device for a data processing method provided in an embodiment of this application. Detailed Implementation
[0062] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0063] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.
[0064] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.
[0065] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.
[0066] To facilitate understanding, the terms used in this application will first be explained, including:
[0067] Membership is a metric that indicates how much an element belongs to a fuzzy set. For example, within a temperature range, the membership function for "warm" can output a value between 0 and 1 to indicate how close the current temperature is to the concept of "warm".
[0068] Trustworthiness is an assessment of the reliability of a rule or inference.
[0069] The inventors discovered that because single sensors are often limited by their own limitations (such as weakened or blocked GPS signals, and accumulated errors in inertial navigation systems), using a single sensor can lead to inaccurate positioning. To address this issue, data from multiple sources such as GPS and IMU can be fused, thereby enhancing the accuracy of modules such as positioning or obstacle recognition. Related technologies, however, do not consider the varying degrees of uncertainty in data provided by different sensors during data fusion, resulting in inaccurate fused data.
[0070] To address the aforementioned problems, embodiments of this application provide a data processing method, apparatus, device, and storage medium to solve these problems. The inventive concept of this application can be summarized as follows: acquiring sensor data corresponding to each sensor; for each sensor: determining the membership function corresponding to the sensor based on the sensor data; obtaining the membership degree of the sensor based on the sensor data and the membership function; determining the trust degree of the sensor based on the membership function; obtaining the weight of the sensor based on the membership degree and the trust degree; and performing fusion processing based on the weight of each sensor and the sensor data corresponding to each sensor to obtain fused data.
[0071] In this application, considering the inherent errors of the sensors themselves and the inherent ambiguity caused by changes in applicable conditions, fuzzy processing logic is adopted to fuse sensor data from different sensors. By determining the membership degree and confidence degree of each sensor, the exact weight of each sensor can be obtained, thereby ensuring the accuracy of the fused data.
[0072] For ease of understanding, the data processing method provided in this application embodiment will be described in detail below with reference to the accompanying drawings:
[0073] like Figure 1 The diagram shown illustrates an application scenario of a data processing method according to an embodiment of this application. The diagram includes: a vehicle 10, a sensor 20, and an in-vehicle display 30; wherein:
[0074] Vehicle 10 acquires sensor data corresponding to each sensor 20; for each sensor 20: the membership function corresponding to sensor 20 is determined based on the sensor data corresponding to sensor 20; the membership degree of sensor 20 is obtained based on the sensor data and the membership function; the trust degree of sensor 20 is determined based on the membership function; the weight of sensor 20 is obtained based on the membership degree and the trust degree; the fusion processing is performed based on the weight of each sensor 20 and the sensor data corresponding to each sensor 20 to obtain fused data, and the fused data is displayed on the vehicle display 30.
[0075] The description in this application focuses only on a single vehicle 10, sensor 20, and in-vehicle display 30. However, those skilled in the art should understand that the illustrated vehicle 10, sensor 20, and in-vehicle display 30 are intended to illustrate the operation of the vehicle 10, sensor 20, and in-vehicle display 30 involved in the technical solution of this application, and are not intended to imply any limitation on the number, type, or location of the vehicle 10, sensor 20, and in-vehicle display 30. It should be noted that if... Figure 1 Adding additional modules or removing individual modules from the environment shown will not change the underlying concepts of the example embodiments of this application.
[0076] It should be noted that the data processing method proposed in this application is not only applicable to... Figure 1 The application scenarios shown are also applicable to any device with data processing needs.
[0077] like Figure 2 The diagram shown is a flowchart illustrating a data processing method provided in an embodiment of this application, wherein:
[0078] In step 201: Obtain the sensor data corresponding to each sensor.
[0079] In this application, if the goal is to use map positioning, the sensor data can be provided by sensors such as IMU and GPS; if the goal is to use the data processing method of this application to detect obstacles, the sensor data can be provided by sensors such as cameras and LiDAR. That is, this application does not limit the type or number of sensors; those skilled in the art can choose the type and number of sensors according to their needs.
[0080] In some possible embodiments, in order to improve the accuracy of data processing, after obtaining the sensor data corresponding to each sensor, the sensor data can be denoised or filtered to remove interference factors from the sensor data.
[0081] In step 202: For each sensor: Determine the membership function of the sensor based on the sensor data; Obtain the membership degree of the sensor based on the sensor data and the membership function; Determine the trust degree of the sensor based on the membership degree; Obtain the weight of the sensor based on the membership degree and the trust degree.
[0082] In this application, step 202 needs to be performed separately for the sensing data corresponding to each sensor, so as to obtain the weight corresponding to each sensor.
[0083] In some possible implementations, a set of membership functions for each sensor can be pre-built, as the reasons for the accuracy variations of different sensors differ. For example, the accuracy of a GPS sensor may fluctuate due to environmental factors, while the accuracy of a high-precision map sensor may fluctuate due to update intervals. Therefore, a separate set of membership functions is built for each sensor.
[0084] Because the accuracy of GPS sensors fluctuates due to environmental factors, a membership function can be designed to represent "high-precision" GPS readings. When the GPS signal is very strong, the membership degree of the GPS reading approaches 1 (completely reliable). However, when the signal is weak, this membership degree will decrease.
[0085] For example: when the GPS signal strength is greater than or equal to 30 dBHz, the membership degree of the GPS sensor is 1; when the GPS signal strength is less than 30 dBHz but greater than or equal to 20 dBHz, the membership degree of the GPS sensor changes linearly between 0 and 1; when the GPS signal strength is less than 20 dBHz, the membership degree of the GPS sensor is 0. Therefore, the set of membership functions corresponding to the GPS sensor can be obtained as shown in Formula 1, where:
[0086]
[0087] Where x is the GPS signal strength, μ GPS (x) represents the membership degree of the GPS sensor.
[0088] For example, for high-precision map sensors, when the map update time is less than one month, the membership degree of the high-precision map sensor is 1; when the map update time is greater than or equal to one month but less than six months, the membership degree of the high-precision map sensor changes linearly between 0 and 1; when the map update time is greater than six months, the membership degree of the high-precision map sensor is 0. Therefore, the set of membership functions corresponding to the high-precision map sensor can be obtained as shown in Formula 2, where:
[0089]
[0090] Where y is the GPS signal strength, μ MAP (y) represents the membership degree of the high-precision map sensor.
[0091] The stronger the GPS signal strength, the higher the accuracy of the GPS sensor, which is a direct proportional function; the shorter the map update time of the high-precision map sensor, the higher the accuracy of the high-precision map sensor, which is an inverse proportional function. Therefore, the membership function constructed in Formula 2 is the difference between Formula 1 and Formula 2.
[0092] Similarly, the set of membership functions corresponding to each sensor can be obtained, which will not be elaborated here.
[0093] It should be noted that the specific values mentioned above are only one embodiment given in this application and are not intended to limit Formula 1 and Formula 2. In specific implementation, the specific values of the first preset value and the second preset value can be set according to the properties of the sensor. This application does not limit the specific values of the first preset value and the second preset value.
[0094] In some possible embodiments, the membership function corresponding to the sensor is determined based on the sensor data corresponding to the sensor, which can be specifically implemented as follows: Figure 3 The steps shown are as follows:
[0095] In step 301: Obtain the set of membership functions corresponding to the sensor data.
[0096] In this application, a different set of membership functions is set for each sensor. Therefore, to determine the membership function corresponding to each sensor, it is first necessary to obtain the set of membership functions for each sensor. Then, the membership function corresponding to each sensor is determined based on the set of membership functions and the first information value in the sensor data corresponding to each sensor. In this application, the reasons for the accuracy variation of different sensors are different, therefore the first information values corresponding to different sensors are different.
[0097] In some possible embodiments, if the sensor data is GPS data, the first information value is the GPS signal strength; if the sensor data is high-precision map data, the first information value is the update time of the high-precision map.
[0098] In this application, a different first information value is set for each sensor, which can ensure that the determined membership function is more accurate.
[0099] In step 302: If the first information value in the sensor data is greater than the first preset value, then the membership function corresponding to the sensor is the first membership function in the membership function set.
[0100] For example: If the sensor is a GPS sensor, and the first information value corresponding to the GPS sensor is the GPS signal strength, and the GPS signal strength is determined to be 35, then the membership function set corresponding to the GPS sensor is shown in Formula 1. The first preset value is 30, and the second preset value is 20. Therefore, it can be determined that the first information value corresponding to the GPS sensor is greater than the first preset value, and the first membership function corresponding to the GPS sensor is μ. GPS (x) = 1.
[0101] For example: the sensor is a high-precision map sensor, and the first information value corresponding to the high-precision map sensor is the map update time. The map update time for the high-precision map sensor is determined to be 8 months. The membership function set corresponding to the high-precision map sensor is shown in Formula 2. The first preset value is 6, and the second preset value is 1. Therefore, it can be determined that the first information value corresponding to the high-precision map sensor is greater than the first preset value, and the first membership function corresponding to the high-precision map sensor is μ. MAP (y) = 0.
[0102] In step 303: If the first information value in the sensor data is greater than or equal to the second preset value and less than or equal to the first preset value, then the membership function corresponding to the sensor is the second membership function in the membership function set.
[0103] For example: The sensor is a GPS sensor. The first information value corresponding to the GPS sensor is the GPS signal strength. The GPS signal strength is determined to be 25. The membership function set corresponding to the GPS sensor is shown in Formula 1. The first preset value is 30, and the second preset value is 20. Therefore, it can be determined that the first information value corresponding to the GPS sensor is greater than or equal to the second preset value and less than or equal to the first preset value. The second membership function corresponding to the GPS sensor is...
[0104] For example: The sensor is a high-precision map sensor. The first information value corresponding to the high-precision map sensor is the map update time. The map update time for the high-precision map sensor is determined to be 3 months. The membership function set corresponding to the high-precision map sensor is shown in Formula 2. The first preset value is 6, and the second preset value is 1. Therefore, it can be determined that the first information value corresponding to the high-precision map sensor is greater than or equal to the second preset value and less than or equal to the first preset value. The second membership function corresponding to the high-precision map sensor is...
[0105] In step 304: If the first information value in the sensor data is less than the second preset value, then the membership function corresponding to the sensor is the third membership function in the membership function set.
[0106] For example: If the sensor is a GPS sensor, and the first information value corresponding to the GPS sensor is the GPS signal strength, and the GPS signal strength is determined to be 15, then the membership function set corresponding to the GPS sensor is shown in Formula 1. The first preset value is 30, and the second preset value is 20. Therefore, it can be determined that the first information value corresponding to the GPS sensor is less than the second preset value, and the third membership function corresponding to the GPS sensor is μ. GPS (x) = 0.
[0107] For example: The sensor is a high-precision map sensor. The first information value corresponding to the high-precision map sensor is the map update time. The map update time of the high-precision map sensor is determined to be 0.5 months. The membership function set corresponding to the high-precision map sensor is shown in Formula 2. The first preset value is 6, and the second preset value is 1. Therefore, it can be determined that the first information value corresponding to the high-precision map sensor is less than the second preset value, and the third membership function corresponding to the high-precision map sensor is μ. MAP (y) = 1.
[0108] What needs to be known is that Figure 3 Steps 302-304 are not executed sequentially or simultaneously, but rather one is selected for execution based on the first information value. Figure 3 The flowchart is shown for ease of explanation only and does not limit the execution order or the steps to be executed.
[0109] In some possible embodiments, after determining the membership function, the membership degree can be determined. Since the first membership function and the third membership function are constant functions, the constant value is the membership degree of the sensor. If the membership function is the second membership function, the following can be implemented: the first information value in the sensor data corresponding to the sensor is substituted into the second membership function to obtain the membership degree of the sensor.
[0110] For example: The sensor is a GPS sensor. The first information value corresponding to the GPS sensor is the GPS signal strength. The GPS signal strength is determined to be 28. The membership function set corresponding to the GPS sensor is shown in Formula 1. The first preset value is 30, and the second preset value is 20. Therefore, it can be determined that the first information value corresponding to the GPS sensor is greater than or equal to the second preset value and less than or equal to the first preset value. The second membership function corresponding to the GPS sensor is...
[0111] Substituting the GPS signal strength of 28 into the second membership function, we obtain a membership degree of 0.8 for the GPS sensor.
[0112] For example: The sensor is a high-precision map sensor. The first information value corresponding to the high-precision map sensor is the map update time. The map update time for the high-precision map sensor is determined to be 3 months. The membership function set corresponding to the high-precision map sensor is shown in Formula 2. The first preset value is 6, and the second preset value is 1. Therefore, the first information value corresponding to the high-precision map sensor is greater than or equal to the second preset value and less than or equal to the first preset value. The second membership function corresponding to the high-precision map sensor is μ. MAP (y)=1-
[0113]
[0114] Substituting the map update time of the high-precision map sensor, which is 3 months, into the second membership function, we obtain a membership degree of 0.6 for the high-precision map sensor.
[0115] In this application, to further ensure the accuracy of the membership degrees of each sensor, after determining the membership degree of each sensor, it is necessary to determine the trust degree of each sensor. Determining the trust degree can be specifically implemented as follows: Figure 4 The steps shown are as follows:
[0116] In step 401: Determine the range of membership degree in the preset reliability lookup table.
[0117] In this application, a reliability lookup table is pre-constructed, which stores the reliability range corresponding to the membership degree, such as... Figure 5 The table shown below is a reliability comparison table for GPS sensors. Figure 6This is a reliability comparison table for high-precision map sensors.
[0118] What needs to be known is that Figure 5 , Figure 6 The values in this application are merely one possible implementation and do not limit the specific range of values for reliability.
[0119] It should also be noted that when the obtained membership degree falls within the range threshold in the reliability lookup table, the membership degree can be assigned to any one of the ranges corresponding to the range threshold. For example: Figure 5 For example, if the membership degree is 0.6, then the range corresponding to this membership degree can be determined to be reliable or somewhat reliable.
[0120] Furthermore, to ensure reliability, in practical implementation, the range with lower reliability corresponding to the critical value can be selected as the range corresponding to the membership degree. For example: Figure 6 As shown, a membership degree of 0.7 indicates that the range corresponding to this membership degree is somewhat reliable.
[0121] In step 402: Randomly select values within the range to obtain the trust level of the sensor.
[0122] For example, if the sensor is a GPS sensor and the membership degree of the GPS sensor is 0.8, then the range of the GPS sensor is 0.6-1. Randomly selecting a value from 0.6-1, the confidence degree of the GPS sensor is 0.9.
[0123] If the sensor is a high-precision map sensor, and the membership degree corresponding to the high-precision map sensor is 0.6, then the range corresponding to the high-precision map sensor is 0-0.7. Randomly selecting a value within the range of 0-0.7 yields a confidence level of 0.6 for the high-precision map sensor. At this point, it can be determined that the sensor data corresponding to the GPS sensor is reliable, and the sensor data corresponding to the high-precision map sensor is somewhat reliable.
[0124] In some possible embodiments, after obtaining the membership degree and trust degree corresponding to each sensor, the weight corresponding to the sensor is obtained based on the membership degree and trust degree. Specifically, this can be implemented as follows: Figure 7 The steps shown are as follows:
[0125] In step 701: Determine the product of membership degree and trust degree.
[0126] In step 702: the product value is used as the weight corresponding to the sensor.
[0127] For example, if a GPS sensor has a trust score of 0.9 and a membership score of 0.8, then the weight of the GPS sensor is 0.9 * 0.8 = 0.72. If a high-precision map sensor has a membership score of 0.6 and a trust score of 0.6, then the weight of the high-precision map sensor is 0.6 * 0.6 = 0.36.
[0128] In some possible embodiments, in order to further improve the accuracy of data processing, the weights corresponding to each sensor can be normalized after the weights are obtained to obtain the normalized weights of each sensor.
[0129] For example, if the weight corresponding to the GPS sensor is 0.72 and the weight corresponding to the high-precision map sensor is 0.36, then the weight corresponding to the GPS sensor is normalized to 0.72 / (0.72+0.36) = 0.67; and the weight corresponding to the high-precision map sensor is normalized to 0.36 / (0.72+0.36) = 0.33.
[0130] In step 203: fusion processing is performed based on the weights corresponding to each sensor and the sensor data corresponding to each sensor to obtain fused data.
[0131] In some possible embodiments, after obtaining the weight corresponding to each sensor, the sensor data corresponding to each sensor can be multiplied by the weight corresponding to each sensor and then summed to obtain fused data.
[0132] For example, if the location coordinates obtained by the GPS sensor are (10, 15) and the location coordinates obtained by the high-precision map sensor are (1114), then the fused data x = 0.67*10 + 0.33*11 = 10.33, y = 0.67*15 + 0.33*14 = 14.67, and the fused data is (10.33, 14.67).
[0133] In this application, considering the inherent errors of the sensors themselves and the inherent ambiguity caused by changes in applicable conditions, fuzzy processing logic is adopted to fuse sensor data from different sensors. By determining the membership degree and confidence degree of each sensor, the exact weight of each sensor can be obtained, thereby ensuring the accuracy of the fused data.
[0134] Based on the same inventive concept, embodiments of this application also provide a data processing apparatus 800, such as... Figure 8 As shown, the device includes:
[0135] The data acquisition module 8001 is used to acquire sensor data corresponding to each sensor.
[0136] The data processing module 8002 is configured to, for each sensor,: determine the membership function corresponding to the sensor based on the sensor data corresponding to the sensor; obtain the membership degree of the sensor based on the sensor data and the membership function; determine the trust degree of the sensor based on the membership degree; and obtain the weight of the sensor based on the membership degree and the trust degree.
[0137] The data fusion module 8003 is used to perform fusion processing based on the weights corresponding to each sensor and the sensor data corresponding to each sensor to obtain fused data.
[0138] In some possible embodiments, the data processing module 8002 is specifically used for:
[0139] Obtain the set of membership functions corresponding to the sensor data;
[0140] If the first information value in the sensor data is greater than the first preset value, then the membership function corresponding to the sensor is the first membership function in the membership function set;
[0141] If the first information value in the sensor data is greater than or equal to the second preset value and less than or equal to the first preset value, then the membership function corresponding to the sensor is the second membership function in the membership function set;
[0142] If the first information value in the sensor data is less than the second preset value, then the membership function corresponding to the sensor is the third membership function in the membership function set.
[0143] In some possible embodiments, if the sensor data is Global Positioning System (GPS) data, the first information value is the GPS signal strength; if the sensor data is high-precision map data, the first information value is the update time of the high-precision map.
[0144] In some possible embodiments, the data processing module 8002 is specifically used for:
[0145] The first information value in the sensor data corresponding to the sensor is substituted into the second membership function to obtain the membership degree of the sensor.
[0146] In some possible embodiments, the data processing module 8002 is specifically used for:
[0147] Determine the range of the membership degree in a preset reliability lookup table;
[0148] The trust level of the sensor is obtained by randomly selecting a value within the range.
[0149] In some possible embodiments, the data processing module 8002 is specifically used for:
[0150] Determine the product of the membership degree and the trust degree;
[0151] The product value is used as the weight corresponding to the sensor.
[0152] In some possible embodiments, the data processing module 8002 is further configured to:
[0153] The weights corresponding to each sensor are normalized to obtain the normalized weights of each sensor.
[0154] Corresponding to the above embodiments, this application also provides an electronic device. Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 900 may include a processor 901, a memory 902, and a communication unit 903. These components communicate through one or more buses. Those skilled in the art will understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiment of the present invention. It may be a bus-shaped structure or a star-shaped structure, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0155] The communication unit 903 is used to establish a communication channel, enabling the electronic device to communicate with other devices. It receives user data from other devices or sends user data to other devices.
[0156] The processor 901 serves as the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs and / or modules stored in the memory 902, and calls data stored in the memory to perform various functions and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 901 may consist only of a central processing unit (CPU). In this embodiment, the CPU may have a single processing core or include multiple processing cores.
[0157] The memory 902 is used to store the execution instructions of the processor 901. The memory 902 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0158] When the execution instructions in memory 902 are executed by processor 901, the electronic device 900 is able to perform operations. Figure 7 Some or all of the steps in the illustrated embodiments.
[0159] In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps of the calling method provided by the present invention. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0160] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present invention.
[0161] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments and terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.
Claims
1. A data processing method, characterized by, The method comprises: obtaining sensor data corresponding to each sensor; for each sensor, determining a membership function corresponding to the sensor based on the sensor data corresponding to the sensor, obtaining a membership degree of the sensor based on the sensor data and the membership function, determining a trust degree corresponding to the sensor based on the membership degree, and obtaining a weight corresponding to the sensor based on the membership degree and the trust degree; performing fusion processing on the sensor data corresponding to each sensor based on the weight corresponding to each sensor to obtain fusion data.
2. The method of claim 1, wherein, The determination of the membership function corresponding to the sensor based on the sensor data corresponding to the sensor comprises: obtaining a set of membership functions corresponding to the sensor data; if a first information value in the sensor data is greater than a first preset value, the membership function corresponding to the sensor is a first membership function in the set of membership functions; if the first information value in the sensor data is greater than or equal to a second preset value and less than or equal to the first preset value, the membership function corresponding to the sensor is a second membership function in the set of membership functions; if the first information value in the sensor data is less than the second preset value, the membership function corresponding to the sensor is a third membership function in the set of membership functions.
3. The method of claim 2, wherein, If the sensor data is global positioning system (GPS) data, the first information value is the signal strength of the GPS; if the sensor data is high-precision map data, the first information value is the update time of the high-precision map.
4. The method of claim 2, wherein, If the membership function is the second membership function, the obtaining of the membership degree of the sensor based on the sensor data and the membership function comprises: inputting the first information value in the sensor data corresponding to the sensor into the second membership function to obtain the membership degree of the sensor.
5. The method of claim 1, wherein, The determination of the trust degree corresponding to the sensor based on the membership degree comprises: determining a range corresponding to the membership degree in a preset reliability reference table; randomly selecting a value in the range to obtain the trust degree corresponding to the sensor.
6. The method of claim 1, wherein, The obtaining of the weight corresponding to the sensor based on the membership degree and the trust degree comprises: determining a product value of the membership degree and the trust degree; and taking the product value as the weight corresponding to the sensor.
7. The method of claim 1, wherein, Before the fusion processing based on the weight corresponding to each sensor and the sensor data corresponding to each sensor, the method further comprises: normalizing the weight corresponding to each sensor to obtain a normalized weight of each sensor.
8. A data processing apparatus, characterized by, The device comprises: a data acquisition module configured to obtain sensor data corresponding to each sensor; a data processing module configured to, for each sensor, determine a membership function corresponding to the sensor based on the sensor data corresponding to the sensor, obtain a membership degree of the sensor based on the sensor data and the membership function, determine a trust degree corresponding to the sensor based on the membership degree, and obtain a weight corresponding to the sensor based on the membership degree and the trust degree. A data fusion module is configured to fuse the sensor data of each sensor based on the corresponding weight of each sensor to obtain fused data.
9. An electronic device, comprising: An electronic device comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1-7.