Positioning quality data processing method and apparatus, device, and medium
By using pre-defined rules of thumb and support vector machine models to score and sample the positioning quality data of autonomous vehicles, the problem of reduced server cluster performance was solved, and more efficient data storage and analysis were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UISEE SHANGHAI AUTOMOTIVE TECH LTD
- Filing Date
- 2023-06-28
- Publication Date
- 2026-06-12
Smart Images
Figure CN116860731B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of data processing technology, and in particular to a method, apparatus, device and medium for processing positioning quality data. Background Technology
[0002] With the rapid development of autonomous driving technology, autonomous vehicles are being used in more and more environments. Location is a key factor affecting the driving quality of autonomous vehicles. Many problems can be identified from the location data generated during autonomous vehicle operation, and the vehicle's operating status can be displayed on electronic maps using visualization tools and location data.
[0003] Autonomous vehicles generate real-time driving data during operation. Current technologies store this data by receiving it all at once from server clusters. Users can analyze this data to determine the causes of vehicle malfunctions, thus requiring high performance and capacity from the server cluster. However, as the number of projects and vehicles increases, the volume of driving data grows, leading to a decrease in server cluster performance and impacting its storage capacity. Furthermore, improper storage of vehicle driving data by the server cluster can result in discontinuous data over time, affecting the analysis results. Summary of the Invention
[0004] To address or at least partially address the aforementioned technical problems, this disclosure provides a method, apparatus, device, and medium for processing positioning quality data, thereby reducing the storage pressure on server clusters, decreasing the computational load on server clusters, improving the accuracy of positioning quality data processing, and enhancing user experience.
[0005] In a first aspect, embodiments of this disclosure provide a method for processing positioning quality data, including:
[0006] Acquire multiple location quality data for the vehicle;
[0007] For each location quality data point, the location quality data is scored using a preset rule of thumb and a pre-trained support vector machine model to obtain the target score result for the location quality data.
[0008] Based on the target scoring result, the positioning quality data is sampled and processed to obtain target positioning quality data.
[0009] Secondly, embodiments of this disclosure provide a method for querying and visualizing location quality data, including:
[0010] In response to a user query, the system listens for and collects target positioning quality data generated by the query, the target positioning quality data being obtained by the positioning quality data processing method as described in the first aspect.
[0011] The target positioning quality data with the same characteristics are associated to construct multiple target positioning quality data sets;
[0012] The multiple target positioning quality data sets are populated into a common target positioning quality data set to determine the results of multiple dimensions of the target positioning quality data.
[0013] The results of the target positioning quality data from multiple dimensions are presented in the visualization system.
[0014] Thirdly, embodiments of this disclosure provide a positioning quality data processing apparatus, comprising:
[0015] The acquisition module is used to acquire multiple positioning quality data of the vehicle;
[0016] The scoring module is used to score each location quality data point using preset empirical rules and a pre-trained support vector machine model, and obtain the target score result of the location quality data.
[0017] The processing module is used to sample and process the positioning quality data according to the target scoring result to obtain target positioning quality data.
[0018] Fourthly, embodiments of this disclosure provide a visualization device for querying location quality data, comprising:
[0019] A collection module is used to respond to a user query, listen to and collect target positioning quality data generated by the query, wherein the target positioning quality data is obtained by processing the positioning quality data processing method as described in the first aspect;
[0020] The association module is used to associate the target positioning quality data with the same characteristics to construct multiple target positioning quality data sets;
[0021] The filling module is used to fill the multiple target positioning quality data sets into a common target positioning quality data set, thereby determining the results of multiple dimensions of the target positioning quality data.
[0022] The presentation module is used to present the results of the target positioning quality data from multiple dimensions in the visualization system.
[0023] Fifthly, embodiments of this disclosure provide an electronic device, including:
[0024] Memory;
[0025] Processor; and
[0026] Computer programs;
[0027] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first or second aspect.
[0028] In a sixth aspect, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first or second aspect.
[0029] In a seventh aspect, embodiments of this disclosure also provide a computer program product comprising a computer program or instructions that, when executed by a processor, implement the method described in the first or second aspect.
[0030] The positioning quality data processing method, apparatus, device, and medium provided in this disclosure acquire multiple positioning quality data of a vehicle; for each positioning quality data, a target score result is obtained by scoring the positioning quality data using preset empirical rules and a pre-trained support vector machine model; based on the target score result, the positioning quality data is sampled to obtain target positioning quality data. This reduces the storage pressure on the server cluster, lowers the computational load of the server cluster, improves the accuracy of positioning quality data processing, and enhances the user experience. Attached Figure Description
[0031] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0032] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0033] Figure 1 A flowchart of a positioning quality data processing method provided in this embodiment of the disclosure;
[0034] Figure 2 A flowchart of a positioning quality data processing method provided in this embodiment of the disclosure;
[0035] Figure 3 A flowchart of a method for providing a first scoring result of positioning quality data in an embodiment of this disclosure;
[0036] Figure 4 A flowchart illustrating the method for obtaining target scoring results for positioning quality data provided in this embodiment of the disclosure;
[0037] Figure 5 Flowchart of the method for querying and visualizing positioning quality data provided in this embodiment of the disclosure;
[0038] Figure 6 Flowchart of the method for querying and visualizing positioning quality data provided in this embodiment of the disclosure;
[0039] Figure 7 A schematic diagram of the positioning quality data processing device provided in this embodiment of the present disclosure;
[0040] Figure 8 A schematic diagram of the structure of the location quality data query visualization device provided in the embodiments of this disclosure;
[0041] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation
[0042] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.
[0043] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.
[0044] With the rapid development of autonomous driving technology, autonomous vehicles are being used in more and more environments. Location is a key factor affecting the driving quality of autonomous vehicles. Many problems can be identified from the location data generated during autonomous vehicle operation, and the vehicle's operating status can be displayed on electronic maps using visualization tools and location data.
[0045] Autonomous vehicles generate real-time driving data during operation. In existing technologies, server clusters store this data by receiving it all at once. Users can analyze vehicle malfunctions and other issues based on this data, thus requiring high performance and capacity from the server cluster. However, as the number of projects and vehicles increases, the amount of driving data grows, leading to a decrease in server cluster performance and impacting its storage capacity. Furthermore, improper storage of vehicle driving data by the server cluster can result in discontinuous data over time, affecting the analysis results. To address this issue, this disclosure provides a method for processing positioning quality data, which will be described below with reference to specific embodiments.
[0046] Figure 1 This is a flowchart illustrating a positioning quality data processing method provided in an embodiment of this disclosure. The method can be executed by a positioning quality data processing device, which can be implemented in software and / or hardware. This device can be configured in an electronic device, such as a server or terminal. Specifically, the terminal includes electric vehicles, gasoline vehicles, hybrid vehicles, etc. For example, the positioning quality data processing device can be a vehicle infotainment system in a vehicle. Furthermore, this method can be applied to various positioning quality data processing scenarios. It is understood that the positioning quality data processing method provided in this embodiment can also be applied to other scenarios.
[0047] The following is about Figure 1 The positioning quality data processing method shown is described below, and the specific steps of this method are as follows:
[0048] S101. Obtain multiple positioning quality data of the vehicle.
[0049] The vehicle's logs are packaged into a log package, which can be structured or unstructured data. The log package is then uploaded to a cloud server. The vehicle listens to the cloud server, and when the log upload event is triggered, the vehicle downloads the log package, parses the original logs, and obtains multiple location quality data points from the original logs. Each location quality data point has multiple dimensions of indicators.
[0050] Optionally, the plurality of positioning quality data includes basic indicator data and advanced indicator data, wherein the basic indicator data is obtained from the source data and the advanced indicator data is calculated and generated based on the basic indicator data;
[0051] Specifically, the multiple positioning quality data include basic indicator data and advanced indicator data. The basic indicator data is obtained from the source data, that is, the indicator data is directly obtained from the original vehicle logs. The advanced indicator data is calculated and generated based on the basic indicator data, that is, the advanced indicator data is generated based on the basic indicator data by aggregating and calculating the basic indicator data.
[0052] Optionally, the basic index data includes at least: the deviation between the measurement source and the fusion positioning, the fusion result of the measurement source, the data result of the measurement source, the missing result of the measurement source, the confidence of the measurement source, and the confidence of the fusion positioning;
[0053] Specifically, the positioning in the deviation between the measurement source and the fused positioning refers to the parameters of geographic coordinates, such as longitude, latitude, and latitude / longitude confidence. The parameters of the measurement source can be obtained through sensors, while the parameters of the fused positioning are the values fed back after the algorithm comprehensively calculates the parameters of the measurement source. For example, if the measurement source is the Global Positioning System (GPS), and the parameters of the fused positioning are longitude 1000, latitude 1000, and latitude / longitude confidence of 0.8, while the parameters of the GPS measurement source are longitude 999, latitude 999, and latitude / longitude confidence of 0.79, then the deviation between the GPS measurement source and the fused positioning is: longitude (999-1000) = -1, latitude (999-1000) = -1, and latitude / longitude confidence (0.79-0.8) = -0.01. When there are multiple measurement sources, such as GPS measurement sources, Vision Simultaneous Localization and Mapping (VSMART) sources, etc., the fused positioning will not be affected by these deviations. Mapping (VSLAM) measurement sources, etc., calculate the deviation between each measurement source and the fused positioning, thus obtaining the deviation results of multiple measurement sources and the fused positioning. Specifically, this multiple deviation result can be the average of the deviations of multiple measurement sources and the fused positioning. The result of measurement source fusion refers to the value obtained by fusing the parameters of a measurement source based on a fusion algorithm when a single measurement source has data. For example, if the measurement source is a Global Positioning System (GPS), and the GPS measurement source has data with parameters of longitude 999, latitude 999, and latitude / longitude confidence 0.79, and the longitude of the GPS measurement source can be fused, but the latitude and latitude / longitude confidence cannot be fused, then the GPS measurement source fusion rate is 1 / 3. When there are multiple measurement sources, such as GPS measurement sources, VSLAM measurement sources, etc., the result of fusion for each measurement source is calculated, thus obtaining the result of multiple measurement source fusion. Specifically, this multiple measurement source fusion result can be the average of the multiple measurement source fusion results. The data result of the measurement source refers to the data acquired by a single measurement source from the sensor. The effective parameter is the ratio of all parameters acquired by a single measurement source from the sensor. An invalid parameter specifically refers to a parameter that is 0. For example, if the longitude, latitude, and latitude / longitude confidence level acquired by the GPS measurement source are 0, then the parameters generated by the GPS measurement source are invalid. For instance, when the measurement sources are a GPS measurement source and a VSLAM measurement source, and the positioning quality data is 100 frames, the GPS measurement source has 20 frames of positioning quality data, and the VSLAM measurement source has 50 frames of positioning quality data. In this case, the data result of the GPS measurement source is 0.2, and the data result of the VSLAM measurement source is 0.5. Therefore, the data result of the measurement source is (0.2 + 0.5) / 2 = 0.35; Missing measurement source results refer to a situation where a single measurement source cannot acquire data from the sensor, resulting in a null value. For example, this could be due to sensor malfunction causing a single measurement source to be unable to acquire data. The specific calculation results are similar to the data results from the aforementioned measurement sources, and will not be elaborated upon in this embodiment.
[0054] Confidence level refers to the confidence interval of a probability sample, which is an interval estimate of a population parameter for that sample. The confidence interval shows the degree to which the true value of this parameter has a certain probability of falling within the range of the measured result. The confidence interval gives the range of confidence regarding the measured value of the measured parameter, that is, the aforementioned certain probability; this probability is called the confidence level.
[0055] Optionally, the advanced index data includes at least: the coverage rate of the number of positioning sources being greater than a preset value, the first driving distance under a single positioning source, the second driving distance under the pure motion estimation state of positioning, the third driving distance during the positioning error recovery process, the frequency of recoverable positioning anomalies, and the frequency of unrecoverable positioning anomalies.
[0056] Specifically, the coverage rate of the number of localization sources exceeding a preset value refers to the ratio of the number of frames with a localization source exceeding a preset value to the total number of frames. The preset value can be manually set; for example, it can be 2. For instance, if the total number of frames is 100 and the number of frames with a localization source exceeding 2 is 60, then the coverage rate of the number of localization sources exceeding the preset value is 0.6. The first driving distance under a single localization source refers to the vehicle's driving distance when there is only one localization source. The second driving distance under pure motion estimation state refers to the vehicle's driving distance when the number of measurement sources entering fusion is zero. Zero includes no measurement source or measurement source not being fused; the third driving distance in the positioning error recovery process refers to the driving distance of the vehicle during the positioning error recovery process; the frequency of recoverable positioning anomalies refers to the ratio of recoverable positioning anomalies to total positioning anomalies. For example, if there are 10 total positioning anomalies and 8 recoverable positioning anomalies, the frequency of recoverable positioning anomalies is 0.8; the frequency of unrecoverable positioning anomalies is the ratio of unrecoverable positioning anomalies to total positioning anomalies. For example, if there are 10 total positioning anomalies and 2 unrecoverable positioning anomalies, the frequency of unrecoverable positioning anomalies is 0.2.
[0057] S102. For each of the positioning quality data, the positioning quality data is scored using a preset empirical rule and a pre-trained support vector machine model to obtain the target score result of the positioning quality data.
[0058] Support Vector Machines (SVMs) are a type of generalized linear classifier that performs binary classification of data using supervised learning. Their decision boundary is the maximum-margin hyperplane obtained by solving for the training samples. SVMs use a hinge loss function to calculate empirical risk and incorporate a regularization term into the solution system to optimize structural risk, making them sparsity- and robust classifiers. SVMs can perform non-linear classification using kernel methods, making them one of the common kernel learning methods.
[0059] Preset rules of thumb are used to manually label positioning quality data during the collection process, based on the user's understanding of a large amount of positioning quality data and combined with the actual driving conditions of the vehicle. In some embodiments, the preset rules of thumb are shown in Table 1:
[0060] Table 1
[0061]
[0062]
[0063] For each location quality data point, a target score is obtained by scoring the location quality data using preset empirical rules and a pre-trained support vector machine model.
[0064] S103. Based on the target scoring result, the positioning quality data is sampled and processed to obtain target positioning quality data.
[0065] Based on the target scoring results above, the positioning quality data is sampled and processed to obtain the target positioning quality data.
[0066] Specifically, based on the target score of each frame of positioning quality data, the positioning quality data is sorted in ascending order according to the target score and the time of its generation, resulting in a positioning quality data queue. For example, if the target score includes three levels (Level 1, Level 2, and Level 3), the positioning quality data for Level 1, Level 2, and Level 3 in the positioning quality data queue are labeled separately. Sampling processing is then performed on the positioning quality data, specifically, the positioning quality data for Level 1, Level 2, and Level 3 in the positioning quality data queue. This sampling process includes downsampling and full sampling, thereby obtaining the target positioning quality data and the target positioning quality data queue.
[0067] This embodiment of the disclosure acquires multiple positioning quality data points of a vehicle; for each positioning quality data point, a target score is obtained by scoring the positioning quality data using a preset empirical rule and a pre-trained support vector machine model; based on the target score, the positioning quality data is sampled to obtain target positioning quality data. This reduces the amount of positioning quality data acquired, and while ensuring that the positioning quality data can identify the vehicle's positioning status, it reduces the storage pressure on the server cluster, reduces the computational load of the server cluster, improves the accuracy of positioning quality data processing, and enhances the user experience.
[0068] Figure 2 A flowchart of the positioning quality data processing method provided in the embodiments of this disclosure is shown below. Figure 2 As shown, the specific steps included in this method are as follows:
[0069] S201. Obtain multiple positioning quality data of the vehicle.
[0070] Specifically, the implementation process and principle of S201 and S101 are the same, and will not be repeated here.
[0071] S202. For each of the positioning quality data, the positioning quality data is scored using a preset rule of thumb to obtain a first score result for the positioning quality data.
[0072] For each location quality data point, a score is calculated using preset rules of thumb to obtain the first score result for that location quality data point.
[0073] Optionally, the first rating result includes: a first level, a second level, and a third level, wherein the first level is higher than the second level, and the second level is higher than the third level.
[0074] S203. The positioning quality data is scored using a pre-trained support vector machine model to obtain a second score result for the positioning quality data.
[0075] The location quality data is scored using a pre-trained SVM model, resulting in a second score. The pre-trained SVM model can identify location quality data features that are not observable by human experience, thus accurately labeling the location quality data.
[0076] Optionally, the training process of the support vector machine model includes: calibrating the sample localization quality data by using a preset empirical rule to obtain calibrated sample localization quality data; inputting the calibrated sample localization quality data into the support vector machine model to be trained, training the support vector machine model to be trained, and obtaining the pre-trained support vector machine model.
[0077] Specifically, the process involves acquiring sample positioning quality data; calibrating the sample positioning quality data using pre-defined empirical rules, resulting in calibrated sample positioning quality data, which includes first-level, second-level, and third-level positioning quality data; inputting the calibrated sample positioning quality data into the support vector machine model to be trained, thereby training the SVM model to obtain a pre-trained SVM model, which can directly output the second score result of the positioning quality data after inputting the positioning quality data into the pre-trained SVM model.
[0078] Optionally, the second rating result includes: a first level, a second level, and a third level, wherein the first level is higher than the second level, and the second level is higher than the third level.
[0079] S204. Based on the first scoring result and the second scoring result, obtain the target scoring result of the positioning quality data.
[0080] Based on the first and second scores of each location quality data point, the target score for that location quality data is obtained.
[0081] S205. Based on the target scoring result, the positioning quality data is sampled and processed to obtain target positioning quality data.
[0082] Specifically, the implementation process and principle of S205 and S103 are the same, and will not be repeated here.
[0083] This embodiment of the disclosure scores the positioning quality data using preset empirical rules to obtain a first score result; it then scores the positioning quality data using a pre-trained support vector machine model to obtain a second score result; based on the first and second score results, it obtains a target score result for the positioning quality data. By combining preset empirical rules summarized from human observation with an SVM model to mine features of positioning quality data that cannot be observed through human experience, the origin of the target score result for the positioning quality data is clarified. This provides a data foundation for subsequent sampling and processing of the positioning quality data, comprehensively judging the positioning quality of the data, and is more suitable for multi-dimensional positioning quality data.
[0084] Specifically, S202 can be achieved through, for example... Figure 3 The method shown is implemented as follows: Figure 3 As shown, the specific steps included in S202 are as follows:
[0085] S301. Based on the preset empirical rules, score the multiple basic index data and multiple advanced index data of the positioning quality data respectively to obtain multiple first sub-scores of the positioning quality data.
[0086] Based on the aforementioned pre-set rules of thumb, multiple basic and advanced indicators for each location quality data are scored to obtain multiple first sub-scores for that location quality data.
[0087] For example, based on preset empirical rules, multiple basic and advanced index data of each positioning quality data in multiple positioning quality data are scored. When multiple is N, that is, the number of positioning quality data is N, an N*12 dimensional positioning quality data set can be obtained. Here, 12 represents the index data of the deviation between the measurement source and the fused positioning, the result of the measurement source entering the fusion, the data result of the measurement source, the missing result of the measurement source, the confidence of the measurement source, the confidence of the fused positioning, the coverage rate of the number of positioning sources greater than a preset value, the first driving distance under a single positioning source, the second driving distance under the pure motion estimation state of positioning, the third driving distance of the positioning error recovery process, the frequency of the occurrence of positioning recoverable anomalies, and the frequency of the occurrence of positioning unrecoverable anomalies. For example, the first sub-score of the deviation between the measurement source and the fused positioning of the positioning quality data is high, the first sub-score of the result of the measurement source entering the fusion of the positioning quality data is medium, and the positioning quality data... The first sub-score of the measurement source data result is low; the first sub-score of the missing measurement source result of the positioning quality data is high; the first sub-score of the measurement source confidence of the positioning quality data is high; the first sub-score of the fused positioning confidence of the positioning quality data is low; the first sub-score of the number of positioning sources of the positioning quality data is medium; the first sub-score of the first driving distance under a single positioning source of the positioning quality data is medium; the first sub-score of the second driving distance of the positioning pure motion estimation state of the positioning quality data is high; the first sub-score of the third driving distance of the positioning error recovery process of the positioning quality data is low; the first sub-score of the frequency of the positioning recoverable anomaly of the positioning quality data is low; and the first sub-score of the index data of the frequency of the positioning unrecoverable anomaly of the positioning quality data is medium. Then, the multiple first sub-scores can be [high, medium, low, high, high, low, medium, medium, high, low, low, medium].
[0088] S302. Calculate the sum of multiple first sub-scores of the positioning quality data.
[0089] Calculate the sum of multiple first sub-scores of the above positioning quality data. For example, assign a value of 10 to the high score of the first sub-score, 5 to the medium score, and 0 to the low score. It can be understood that high, medium, and low scores can also be assigned other values, where the high score assignment > medium score assignment > low score assignment. Calculate the sum of the multiple first sub-scores [high, medium, low, high, high, low, medium, medium, high, low, low, medium], which is 10+5+0+10+10+0+5+5+10+0+0+5=60 points.
[0090] S303. Sort the multiple positioning quality data according to the sum of their values to obtain the sorting result of the multiple positioning quality data.
[0091] The data is sorted according to the sum of multiple location quality data. Specifically, the sum of multiple location quality data can be sorted in descending or ascending order. This embodiment uses descending order as an example to illustrate the sorting result of the multiple location quality data. If the number of location quality data is N, then the result of the descending order of the sum of N location quality data is obtained.
[0092] S304. The sorting results of the multiple positioning quality data are divided into grades to obtain the first score result of the positioning quality data.
[0093] The ranking results of multiple location quality data are divided into levels to obtain a first score for each location quality data. Specifically, the ranking results of multiple location quality data are divided into levels. For example, in the descending order of the location quality data, the ranking [0, 30%) is the first level, the ranking [30%, 60%) is the second level, and the ranking [60%, 1] is the third level, thus obtaining the first score for each location quality data. The first level is higher than the second level, and the second level is higher than the third level, i.e., first level > second level > third level. It is understood that the above level division of [0, 30%) as the first level, [30%, 60%) as the second level, and [60%, 1] as the third level is only an example. In other embodiments, the proportions of the level division can be adaptively adjusted according to the actual situation.
[0094] It is understandable that after obtaining multiple first sub-ratings and first rating results of the location quality data, the location quality data can be used as sample location quality data to train the SVM model to be trained.
[0095] This embodiment of the disclosure scores multiple basic and advanced indicators of positioning quality data according to preset empirical rules, obtaining multiple first sub-scores for the positioning quality data; calculates the sum of the multiple first sub-scores of the positioning quality data; sorts the multiple positioning quality data according to the sum of the multiple sums, obtaining a sorting result of the multiple positioning quality data; and classifies the sorting result of the multiple positioning quality data into levels, obtaining a first score result of the positioning quality data. This realizes the classification of each positioning quality data according to preset empirical rules, which facilitates the use of the first score result to train the SVM model and improves the accuracy of the SVM model in recognizing positioning quality data.
[0096] Specifically, S204 can be achieved through, for example... Figure 4 The method shown is implemented as follows: Figure 4 As shown, the specific steps included in S204 are as follows:
[0097] S401. When both the first rating result and the second rating result are at the first level, the target rating result of the positioning quality data is at the first level.
[0098] If both the first and second rating results are at the first level, then the target rating result for the location quality data is at the first level.
[0099] S402. When both the first rating result and the second rating result are at the second level, the target rating result of the positioning quality data is at the second level.
[0100] If both the first and second rating results are at the second level, then the target rating result for the location quality data is at the second level.
[0101] S403. When both the first rating result and the second rating result are at the third level, the target rating result of the positioning quality data is at the third level.
[0102] If both the first and second rating results are at the third level, then the target rating result for the location quality data is at the third level.
[0103] S404. When one of the first rating result and the second rating result is at the first level and the other rating result is at the second level, the target rating result of the positioning quality data is at the first level.
[0104] If the first rating result is Level 1 and the second rating result is Level 2, then the target rating result for the location quality data is Level 1.
[0105] If the first rating result is level two and the second rating result is level one, then the target rating result for the location quality data is level one.
[0106] S405. When one of the first rating result and the second rating result is at the first level and the other rating result is at the third level, the target rating result of the positioning quality data is at the second level.
[0107] If the first rating result is Level 1 and the second rating result is Level 3, then the target rating result for the location quality data is Level 2.
[0108] If the first rating result is level three and the second rating result is level one, then the target rating result for the location quality data is level two.
[0109] S406. When one of the first rating result and the second rating result is at the second level and the other rating result is at the third level, then the target rating result of the positioning quality data is at the third level.
[0110] If the first rating result is level two and the second rating result is level three, then the target rating result for the location quality data is level three.
[0111] If the first rating result is level three and the second rating result is level two, then the target rating result for the location quality data is level three.
[0112] Understandably, the determination of the target score results in S204 can also be as shown in Table 2:
[0113] Table 2
[0114] First rating result Second rating result Target scoring results First level First level First level First level Second level First level Second level First level First level First level Level 3 Second level Second level Second level Second level Level 3 First level Second level Level 3 Second level Level 3 Second level Level 3 Level 3 Level 3 Level 3 Level 3
[0115] This disclosure describes in detail how the target score result of the positioning quality data is obtained based on the first score result and the second score result, which makes the target score result more accurate and improves the accuracy of positioning quality data processing.
[0116] In some embodiments, the target rating result includes: a first level, a second level, and a third level;
[0117] Specifically, based on the target rating result, the positioning quality data is sampled and processed to obtain target positioning quality data, including: when the target rating result is at the first level, the positioning quality data of the first level is stored at a period of a first preset number of frames to obtain target positioning quality data of the first level; when the target rating result is at the second level, the positioning quality data of the second level is stored at a period of a second preset number of frames to obtain target positioning quality data of the second level; when the target rating result is at the third level, all the positioning quality data of the third level is stored to obtain target positioning quality data of the third level.
[0118] The positioning quality data is sorted in ascending order according to the time of its generation. For positioning quality data with a target score of Level 1, the data is stored at a period of a first preset number of frames to obtain Level 1 target positioning quality data. For positioning quality data with a target score of Level 2, the data is stored at a period of a second preset number of frames to obtain Level 2 target positioning quality data, where the first preset number of frames > the second preset number of frames. For positioning quality data with a target score of Level 3, all Level 3 positioning quality data is stored to obtain Level 3 target positioning quality data.
[0119] For example, the positioning quality data is sorted in ascending order according to the time of its generation. When the first preset number of frames is 10 and the second preset number of frames is 5, positioning quality data with a target score of level 1 is stored at a cycle of 10 frames to obtain level 1 target positioning quality data. Positioning quality data with a target score of level 2 is stored at a cycle of 5 frames to obtain level 2 target positioning quality data. Positioning quality data with a target score of level 3 is stored in its entirety to obtain level 3 target positioning quality data. In other words, when analyzing vehicle positioning quality data, more attention is paid to level 3 positioning quality data because it is the decisive factor affecting vehicle positioning quality. Level 1 and level 2 target positioning quality data are generally considered to indicate normal vehicle operation and are not considered a focus. Level 3 positioning quality data primarily affects vehicle operating status and performance, reflecting hardware and software malfunctions, and therefore requires special attention. The main purpose of the above sampling process is to intelligently downsample the first-level positioning quality data and the second-level target positioning quality data, thereby saving resources, reducing the storage pressure on the server cluster, and reducing the computational load of the server cluster while ensuring the identification of problems caused by vehicles.
[0120] Figure 5 A flowchart of the method for querying and visualizing location quality data provided in this embodiment of the disclosure is shown below. Figure 5 As shown, the specific steps included in this method are as follows:
[0121] S501. In response to a user query, listen to and collect the target positioning quality data generated by the query.
[0122] When a user accesses the data visualization platform, the user enters the vehicle name and time, clicks the query button, and the system listens to the vehicle name and time entered by the user. Based on the listened vehicle name and time, the system collects the target positioning quality data generated by the user's query. It can be understood that this target positioning quality data is obtained by the positioning quality data processing method of the above embodiment.
[0123] Specifically, when a user performs a query on any chart on the data visualization platform, the triggering algorithm acquires the parameters used in the query at that moment, as well as the parameters of the query return value. The system collects and saves the parameter data used in the query and the parameter data of the query return value, i.e., the target location quality data generated by the user's query. For example, if a user queries fault data of a target vehicle that occurred between June 10, 2023 and June 20, 2023, then the user's selected query start time and query end time, as well as the name of the target vehicle, can be collected from the user's behavior; the geographic coordinates of the target vehicle's fault and fault code information can be obtained from the query return value. The system collects and saves the aforementioned query start time, query end time, target vehicle name, geographic coordinates of the target vehicle's fault, and fault code information.
[0124] S502. Associate the target positioning quality data with the same characteristics to construct multiple target positioning quality data sets.
[0125] The target positioning quality data with the same characteristics are associated, such as query start time, query end time, target vehicle name, geographical coordinates of the target vehicle malfunction, fault code information, etc., to construct multiple target positioning quality data sets.
[0126] S503. Fill the multiple target positioning quality data sets into a common target positioning quality data set to determine the results of multiple dimensions of the target positioning quality data.
[0127] By populating a common target positioning quality data set with multiple related target positioning quality data sets, the results of multiple dimensions of the target positioning quality data are determined. Specifically, target positioning quality data under specified conditions is retrieved from the database and sent to the common target positioning quality data set so that the system can access all charts.
[0128] Optionally, the changes in target positioning quality data in the public target positioning quality data set are monitored, and when the public target positioning quality data set is filled, the public target positioning quality data set is filled according to the query return value of the target positioning quality data.
[0129] Specifically, the system monitors changes in target positioning quality data in the common target positioning quality data set. When the common target positioning quality data set is filled, the system fills the common target positioning quality data set according to the query return value of the target positioning quality data, thereby achieving synchronous query.
[0130] S504. Present the results of the target positioning quality data in multiple dimensions in the visualization system.
[0131] The results of the target positioning quality data from multiple dimensions are presented on the data visualization platform of the visualization system, so that when users input data for one-click query, multiple charts can be viewed simultaneously.
[0132] This embodiment of the disclosure collects target location quality data generated by a user's query when the user enters query conditions to query a chart once during a single access to the data visualization platform. This target location quality data is then used to simultaneously query and visualize multiple charts, which not only reduces the process of repetitive operations for the user, but also intelligently presents the target location quality data that the user wants to see, thereby improving the efficiency of the visualization tool.
[0133] Figure 6 A flowchart of the method for querying and visualizing location quality data provided in this embodiment of the disclosure is shown below. Figure 6 As shown, when a user (Actor) accesses the data visualization platform, the system monitors the user's behavior. This behavior can be a time node selected by the user, such as the query start time and query end time mentioned above, or it can be a vehicle name, vehicle status, etc. In response to the user clicking to query, the system obtains the first query result of a single chart corresponding to the user's behavior (i.e., the target positioning quality data mentioned above). Based on the monitored user behavior, the system saves the user behavior and the first query result. It then constructs a set of associations for multiple charts based on the user behavior and the first query result. The system queries the database using the user behavior and / or the first query result, returning the second query result of multiple charts based on the user behavior and the first query result. The second query result is then populated into a common data set (i.e., the common target positioning quality data set mentioned above). Finally, the common data set is populated into the visualization tool, allowing users to query and view multiple charts at once on the data visualization platform through the visualization tool. This reduces repetitive user operations and improves the user experience.
[0134] Figure 7 This is a schematic diagram of the structure of a positioning quality data processing device provided in an embodiment of this disclosure. The positioning quality data processing device may be a terminal as described in the above embodiment, or it may be a component or assembly within the terminal. The positioning quality data processing device provided in this embodiment of the disclosure can execute the processing flow provided in the embodiments of the positioning quality data processing method, such as... Figure 7As shown, the positioning quality data processing device 70 includes: an acquisition module 71, a scoring module 72, and a processing module 73; wherein, the acquisition module 71 is used to acquire multiple positioning quality data of the vehicle; the scoring module 72 is used to score each positioning quality data using a preset empirical rule and a pre-trained support vector machine model to obtain a target score result for the positioning quality data; the processing module 73 is used to sample and process the positioning quality data according to the target score result to obtain target positioning quality data.
[0135] Optionally, the scoring module 72 is further configured to score the positioning quality data using preset empirical rules to obtain a first scoring result of the positioning quality data; score the positioning quality data using a pre-trained support vector machine model to obtain a second scoring result of the positioning quality data; and obtain a target scoring result of the positioning quality data based on the first scoring result and the second scoring result.
[0136] Optionally, the positioning quality data processing device 70 further includes: a training module 74, used to calibrate the sample positioning quality data using preset empirical rules to obtain calibrated sample positioning quality data; input the calibrated sample positioning quality data into the support vector machine model to be trained, train the support vector machine model to be trained, and obtain the pre-trained support vector machine model.
[0137] Optionally, the plurality of positioning quality data includes basic indicator data and advanced indicator data. The basic indicator data is obtained from the source data, and the advanced indicator data is calculated and generated based on the basic indicator data. The basic indicator data includes at least: the deviation between the measurement source and the fused positioning, the result of the measurement source entering the fusion, the data result of the measurement source, the missing result of the measurement source, the confidence of the measurement source, and the confidence of the fused positioning. The advanced indicator data includes at least: the coverage rate of the number of positioning sources exceeding a preset value, the first driving distance under a single positioning source, the second driving distance under the pure motion estimation state of positioning, the third driving distance during the positioning error recovery process, the frequency of recoverable positioning anomalies, and the frequency of unrecoverable positioning anomalies.
[0138] Optionally, the scoring module 72 is further configured to score multiple basic indicator data and multiple advanced indicator data of the positioning quality data according to the preset empirical rules, thereby obtaining multiple first sub-scores of the positioning quality data; calculate the sum of the multiple first sub-scores of the positioning quality data; sort the multiple positioning quality data according to the size of the sum of the multiple positioning quality data, thereby obtaining the sorting result of the multiple positioning quality data; and classify the sorting result of the multiple positioning quality data into levels, thereby obtaining the first score result of the positioning quality data.
[0139] Optionally, the first rating result includes: a first level, a second level, and a third level; the second rating result includes: a first level, a second level, and a third level, wherein the first level is higher than the second level, and the second level is higher than the third level; wherein, the rating module 72 is further configured to: when both the first rating result and the second rating result are at the first level, then the target rating result of the positioning quality data is at the first level; when both the first rating result and the second rating result are at the second level, then the target rating result of the positioning quality data is at the second level; when both the first rating result and the second rating result are at the third level, then the target rating result of the positioning quality data is at the third level; when one of the first rating result and the second rating result is at the first level and the other rating result is at the second level, then the target rating result of the positioning quality data is at the first level; when one of the first rating result and the second rating result is at the first level and the other rating result is at the third level, then the target rating result of the positioning quality data is at the second level; when one of the first rating result and the second rating result is at the second level and the other rating result is at the third level, then the target rating result of the positioning quality data is at the third level.
[0140] Optionally, the target scoring result includes: a first level, a second level, and a third level; wherein, the processing module 73 is further configured to: when the target scoring result is the first level, store the positioning quality data of the first level at a period of a first preset number of frames to obtain target positioning quality data of the first level; when the target scoring result is the second level, store the positioning quality data of the second level at a period of a second preset number of frames to obtain target positioning quality data of the second level; when the target scoring result is the third level, store all the positioning quality data of the third level to obtain target positioning quality data of the third level.
[0141] Figure 7 The positioning quality data processing device of the illustrated embodiment can be used to execute the technical solution of the above-described positioning quality data processing method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.
[0142] Figure 8 This is a schematic diagram of the structure of a location quality data query and visualization device provided in an embodiment of this disclosure. The location quality data query and visualization device can be the system described in the above embodiment, or it can be a component or part of that system. The location quality data query and visualization device provided in this embodiment of the disclosure can execute the processing flow provided in the location quality data query and visualization method embodiment, such as... Figure 8As shown, the location quality data query visualization device 80 includes: a collection module 81, an association module 82, a filling module 83, and a presentation module 84; wherein, the collection module 81 is used to respond to user queries, listen to and collect target location quality data generated by the query, the target location quality data being processed by the location quality data processing method in the above embodiments; the association module 82 is used to associate the target location quality data with the same characteristics to construct multiple target location quality data sets; the filling module 83 is used to fill the multiple target location quality data sets into a common target location quality data set, thereby determining the results of multiple dimensions of the target location quality data; the presentation module 84 is used to present the results of multiple dimensions of the target location quality data in the visualization system.
[0143] Figure 8 The location quality data query and visualization device shown in the embodiment can be used to execute the technical solution of the above-described location quality data query and visualization method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.
[0144] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device may be a terminal or system as described in the above embodiments. The electronic device provided in this disclosure can execute the processing flow provided in the embodiments of the positioning quality data processing method or the positioning quality data query and visualization method, such as… Figure 9 As shown, the electronic device 90 includes: a memory 91, a processor 92, a computer program, and a communication interface 93; wherein, the computer program is stored in the memory 91 and is configured to be executed by the processor 92 as described above, using the positioning quality data processing method or the positioning quality data query and visualization method.
[0145] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the positioning quality data processing method described in the above embodiments.
[0146] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the positioning quality data processing method described above.
[0147] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
[0148] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.
[0149] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.
[0150] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:
[0151] Acquire multiple location quality data for the vehicle;
[0152] For each location quality data point, the location quality data is scored using a preset rule of thumb and a pre-trained support vector machine model to obtain the target score result for the location quality data.
[0153] Based on the target scoring result, the positioning quality data is sampled and processed to obtain target positioning quality data.
[0154] In addition, the electronic device can also perform other steps in the positioning quality data processing method described above.
[0155] Computer program code for performing the operations of this disclosure can be written in one or more programming languages or a combination thereof, including but not limited to object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0157] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.
[0158] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.
[0159] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0160] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0161] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for processing positioning quality data, characterized in that, The method includes: Acquire multiple location quality data for the vehicle; For each location quality data point, the location quality data is scored using a preset rule of thumb and a pre-trained support vector machine model to obtain the target score result for the location quality data. Based on the target scoring result, the positioning quality data is sampled and processed to obtain target positioning quality data; The target scoring results include: first level, second level, and third level; The step of sampling and processing the positioning quality data based on the target scoring result to obtain target positioning quality data includes: When the target score result is the first level, the positioning quality data of the first level is stored at a period of a first preset number of frames to obtain the target positioning quality data of the first level. When the target score result is the second level, the positioning quality data of the second level is stored at a period of the second preset number of frames to obtain the target positioning quality data of the second level. When the target score result is level three, store all the positioning quality data of level three to obtain the target positioning quality data of level three. The positioning quality data is scored using preset empirical rules and a pre-trained support vector machine model to obtain a target score result for the positioning quality data, including: The positioning quality data is scored using preset rules of thumb to obtain a first score result for the positioning quality data; The positioning quality data is scored by a pre-trained support vector machine model to obtain a second score result for the positioning quality data. Based on the first scoring result and the second scoring result, the target scoring result of the positioning quality data is obtained.
2. The method according to claim 1, characterized in that, The training process of the support vector machine model includes: The sample localization quality data is calibrated by using preset empirical rules to obtain calibrated sample localization quality data. The calibrated sample localization quality data is input into the support vector machine model to be trained, and the support vector machine model to be trained is trained to obtain the pre-trained support vector machine model.
3. The method according to claim 1, characterized in that, The multiple positioning quality data include basic indicator data and advanced indicator data. The basic indicator data is obtained from the source data, and the advanced indicator data is calculated and generated based on the basic indicator data. The basic indicator data includes at least: The deviation between the measurement source and the fusion positioning, the result of the measurement source entering the fusion, the data result of the measurement source, the missing result of the measurement source, the confidence of the measurement source, and the confidence of the fusion positioning, wherein the result of the measurement source entering the fusion refers to the value obtained by fusing the parameters of the measurement source based on the fusion algorithm when data is available from a single measurement source; The advanced indicator data includes at least: The following parameters are considered: coverage rate of more than a preset number of positioning sources, first driving distance under a single positioning source, second driving distance under pure motion estimation state of positioning, third driving distance during positioning error recovery process, frequency of recoverable positioning anomalies, and frequency of unrecoverable positioning anomalies. The second driving distance under pure motion estimation state of positioning refers to the driving distance of the vehicle when the number of measurement sources fused is zero.
4. The method according to claim 3, characterized in that, The positioning quality data is scored using preset empirical rules to obtain a first score result for the positioning quality data, including: Based on the preset rule of thumb, the positioning quality data is scored on multiple basic indicators and multiple advanced indicators to obtain multiple first sub-scores of the positioning quality data. Calculate the sum of multiple first sub-scores of the positioning quality data; The multiple location quality data are sorted according to their sum values to obtain the sorting result of the multiple location quality data; The sorting results of the multiple positioning quality data are divided into grades to obtain the first score result of the positioning quality data.
5. The method according to claim 1, characterized in that, The first rating results include: Level 1, Level 2, and Level 3; The second rating result includes: a first level, a second level, and a third level, wherein the first level is higher than the second level, and the second level is higher than the third level; The target score result for the positioning quality data is obtained based on the first score result and the second score result, including: When both the first rating result and the second rating result are at the first level, the target rating result of the positioning quality data is at the first level. When both the first rating result and the second rating result are at the second level, the target rating result of the positioning quality data is at the second level. When both the first rating result and the second rating result are at the third level, the target rating result of the positioning quality data is at the third level. If one of the first rating result and the second rating result is at the first level and the other rating result is at the second level, then the target rating result of the positioning quality data is at the first level. If one of the first rating result and the second rating result is at the first level and the other rating result is at the third level, then the target rating result of the positioning quality data is at the second level. If one of the first rating result and the second rating result is at the second level and the other rating result is at the third level, then the target rating result of the positioning quality data is at the third level.
6. A method for querying and visualizing location quality data, characterized in that, The method includes: In response to a user query, the system listens for and collects the target positioning quality data generated by the query, wherein the target positioning quality data is obtained by the positioning quality data processing method as described in any one of claims 1-5; The target positioning quality data with the same characteristics are associated to construct multiple target positioning quality data sets; The multiple target positioning quality data sets are populated into a common target positioning quality data set to determine the results of multiple dimensions of the target positioning quality data. The results of the target positioning quality data from multiple dimensions are presented in the visualization system.
7. A positioning quality data processing device, characterized in that, The device includes: The acquisition module is used to acquire multiple positioning quality data of the vehicle; The scoring module is used to score each location quality data point using preset empirical rules and a pre-trained support vector machine model, and obtain the target score result of the location quality data. The processing module is used to sample and process the positioning quality data according to the target scoring result to obtain target positioning quality data; The target scoring results include: first level, second level, and third level; The processing module is further configured to: when the target score result is at the first level, store the positioning quality data of the first level at a period of a first preset number of frames to obtain the target positioning quality data of the first level; when the target score result is at the second level, store the positioning quality data of the second level at a period of a second preset number of frames to obtain the target positioning quality data of the second level; and when the target score result is at the third level, store all the positioning quality data of the third level to obtain the target positioning quality data of the third level. The positioning quality data is scored using preset empirical rules and a pre-trained support vector machine model to obtain a target score result for the positioning quality data, including: The positioning quality data is scored using preset rules of thumb to obtain a first score result for the positioning quality data; The positioning quality data is scored by a pre-trained support vector machine model to obtain a second score result for the positioning quality data. Based on the first scoring result and the second scoring result, the target scoring result of the positioning quality data is obtained.
8. A device for querying and visualizing location quality data, characterized in that, The device includes: A collection module is used to respond to a user query, listen to and collect target positioning quality data generated by the query, wherein the target positioning quality data is obtained by the positioning quality data processing method as described in any one of claims 1-5; The association module is used to associate the target positioning quality data with the same characteristics to construct multiple target positioning quality data sets; The filling module is used to fill the multiple target positioning quality data sets into a common target positioning quality data set, thereby determining the results of multiple dimensions of the target positioning quality data. The presentation module is used to present the results of the target positioning quality data from multiple dimensions in the visualization system.
9. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.