High-precision map updating method, device, equipment, medium and product

Abstract

The embodiment of the invention discloses a high-precision map updating method and device, equipment, a medium and a product, and the scheme can comprise the steps: obtaining historical traffic road data collected in a first time period, and determining abnormal data in the historical traffic road data through known traffic road data in known high-precision map data; determining a frequent item set of the abnormal data based on the data features of the abnormal data; based on the frequent item set, screening the traffic road data collected in a second time period to obtain a screening result; and updating the known high-precision map data by using the screening result. According to the embodiment of the invention, the frequent item set can be determined based on the abnormal data in the historical traffic road data, and the abnormal data in the traffic road data collected in the second time period can be screened out by using the frequent item set, so that the known high-precision map data can be accurately updated according to the screening result.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method, apparatus, device, medium, and product for updating a high-precision map. Background Art

[0002] A high-definition map (HD Map), also known as a high-precision electronic map, is different from a traditional navigation map. In addition to providing road-level navigation information, it can also provide lane-level navigation information. In terms of both the richness and accuracy of information, the high-definition map is much higher than the traditional navigation map, so it is widely used in scenarios such as vehicle navigation and autonomous driving.

[0003] In practical applications, roads may change due to factors such as construction and route diversion. In order to maintain the real-time nature of the map, that is, the so-called "freshness" in the industry, it is necessary to continuously update the high-precision map. Currently, it is generally to use a crowdsourcing collection vehicle equipped with collection equipment to collect traffic road data to update the map. However, when the crowdsourcing collection vehicle collects traffic road data, it is easily affected by the collection environment or the collection object itself, resulting in poor accuracy of the collected traffic road data, so that the high-precision map cannot be updated accurately. Summary of the Invention

[0004] Embodiments of this specification provide a method, apparatus, device, medium, and product for updating a high-precision map to update the high-precision map more accurately.

[0005] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0006] A method for updating a high-precision map provided by an embodiment of this specification includes:

[0007] Obtain historical traffic road data collected within a first time period, and use the known traffic road data in the known high-precision map data to determine the abnormal data in the historical traffic road data;

[0008] Based on the data characteristics of the abnormal data, determine the frequent item sets of the abnormal data; the frequent item sets represent the data characteristics and / or data characteristic sets in the abnormal data whose occurrence frequency is greater than or equal to a preset frequency threshold;

[0009] Based on the frequent item sets, screen the traffic road data collected within a second time period to obtain a screening result;

[0010] Use the screening result to update the known high-precision map data.

[0011] An apparatus for updating a high-precision map provided by an embodiment of this specification includes:

[0012] An abnormal data determination module, configured to obtain historical traffic road data collected within a first time period, and determine abnormal data in the historical traffic road data by using known traffic road data in known high-precision map data;

[0013] A frequent item set determination module, configured to determine a frequent item set of the abnormal data based on data characteristics of the abnormal data; the frequent item set represents data characteristics and / or data characteristic sets in the abnormal data that appear with a frequency greater than or equal to a preset frequency threshold;

[0014] A data screening module, configured to screen traffic road data collected within a second time period based on the frequent item set to obtain a screening result;

[0015] A data update module, configured to update the known high-precision map data by using the screening result.

[0016] A computer device provided by an embodiment of this specification includes a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method described above.

[0017] A computer-readable storage medium provided by an embodiment of this specification stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described above; and / or a computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method described above.

[0018] An embodiment of this specification achieves the following beneficial effects:

[0019] By using known traffic road data in known high-precision map data, an embodiment of this specification can relatively efficiently determine abnormal data in historical traffic road data; determine a frequent item set based on the abnormal data in the historical traffic road data, screen out abnormal data in the traffic road data collected within a second time period according to the frequent item set, and then can relatively accurately update the known high-precision map data according to the screening result. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a schematic flowchart of a high-precision map update method provided by an embodiment of this specification;

[0022] Figure 2 Schematic diagram when the acquisition vehicle in the embodiments of this specification acquires data of traffic signs;

[0023] Figure 3 Schematic diagram when data matching is performed in the embodiments of this specification;

[0024] Figure 4 Process schematic diagram of a high-precision map updating method provided by the embodiments of this specification;

[0025] Figure 5 Structural schematic diagram of a high-precision map updating device provided by the embodiments of this specification;

[0026] Figure 6 Corresponding to the embodiments of this specification Figure 1 Structural schematic diagram of a computer device. Detailed implementation manners

[0027] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope protected by one or more embodiments of this specification.

[0028] The following details the technical solutions provided by each embodiment of this specification in conjunction with the drawings.

[0029] To solve the defects in the prior art, the following embodiments are given in this solution:

[0030] Figure 1 Flow schematic diagram of a high-precision map updating method provided by the embodiments of this specification. From a program perspective, the execution entity of the process can be a high-precision map updating device, or an application server carried by the high-precision map updating device or a program in the cloud. As Figure 1 shown, the method may include the following steps:

[0031] Step 102: Obtain historical traffic road data collected within a first time period, and determine abnormal data in the historical traffic road data by using known traffic road data in known high-precision map data.

[0032] Among them, the first time period may be a certain time period before the high-precision map updating method of the embodiments of this specification is executed.

[0033] In the embodiments of this specification, the historical traffic road data may include data of ground feature elements. Among them, the ground feature elements may include at least one of traffic sign poles, traffic signs, traffic signal lights, curbs, guardrails, and road traffic markings; the data of the ground feature elements may include multiple data features, such as at least one of the type feature, color feature, shape feature, and size feature of the ground feature elements; in addition, the historical traffic road data may further include the acquisition condition data when acquiring the data of the ground feature elements; the acquisition condition data may also include multiple data features, such as at least one of the acquisition time feature, acquisition distance feature, acquisition angle feature, and acquisition environment feature.

[0034] In the embodiments of this specification, the historical traffic road data may be acquired by an acquisition device. Among them, the acquisition device may be a crowdsourcing vehicle deployed in a crowdsourcing map service.

[0035] Figure 2 The following is a schematic diagram when a collection vehicle provided by the embodiments of this specification collects data of traffic signs, as Figure 2 shown, the collection vehicle, that is, the crowdsourcing vehicle, can collect traffic signs on the traffic road, and then can obtain the data of the traffic signs.

[0036] It can be understood that the acquisition device in the embodiments of this specification may also be an acquisition device at a certain fixed installation position. For example, it may be a roadside computing unit (English name: Roadside Computing Unit, English abbreviation: RCU) installed beside the traffic road, or an image acquisition device installed on a traffic sign pole on the traffic road, etc.

[0037] Further, after the acquisition device acquires the historical traffic road data, it can send the historical traffic road data to the execution subject of the process, and then the execution subject of the process obtains the historical traffic road data; of course, the execution subject of the process can also actively obtain the historical traffic road data from the acquisition device regularly or irregularly, which is not limited here.

[0038] In the embodiments of this specification, the known high-precision map data may be the high-precision map data obtained before executing the high-precision map update method of the embodiments of this specification.

[0039] Among them, the known high-precision map data can be used as the ground truth, and the data of the ground feature elements in the known traffic road data are matched with the data of the ground feature elements in the historical traffic road data, so as to determine the abnormal data in the historical traffic road data.

[0040] In the embodiments of this specification, known high-precision map data is used as the ground truth to determine abnormal data in historical traffic road data. Compared with determining abnormal data based on manual experience, abnormal data can be determined more efficiently.

[0041] Step 104: Based on the data characteristics of the abnormal data, determine the frequent item sets of the abnormal data; the frequent item sets represent data characteristics and / or sets of data characteristics that appear in the abnormal data with a frequency greater than or equal to a preset frequency threshold.

[0042] In the embodiments of this specification, the frequent item sets of the abnormal data can be determined based on the data characteristics of the abnormal data.

[0043] Among them, frequent item sets (English name: frequent item sets) refer to data with a support exceeding the minimum support count threshold. In the embodiments of this specification, the frequent item sets can represent data characteristics or sets of data characteristics that appear in the abnormal data with a frequency greater than or equal to a preset frequency threshold.

[0044] For example, the frequent item sets in the embodiments of this specification can include data characteristics of one dimension, such as any one of the acquisition distance characteristics, acquisition environment characteristics, type characteristics of ground features, color characteristics of ground features, and shape characteristics of ground features; they can also include data characteristics of multiple dimensions, such as multiple of the acquisition distance characteristics, acquisition environment characteristics, type characteristics of ground features, color characteristics of ground features, and shape characteristics of ground features.

[0045] Furthermore, based on the data characteristics of the abnormal data, algorithms such as the FP-Tree (English full name: FrequentPattern Tree; Chinese full name: frequent pattern tree) algorithm or the Apriori algorithm can be used to determine the frequent item sets of the abnormal data.

[0046] Step 106: Based on the frequent item sets, screen the traffic road data collected in the second time period to obtain a screening result.

[0047] Among them, the second time period can include any time period after the first time period.

[0048] Since the frequent item sets can represent data characteristics or sets of data characteristics that appear in the abnormal data with a frequency greater than or equal to a preset frequency threshold, the frequent item sets can be data characteristics that cause abnormalities in the traffic road data, that is, affect the accuracy of traffic road data acquisition. Based on this, traffic data containing the frequent item sets can be screened out from the traffic road data collected in the second time period to obtain relatively accurate traffic road data.

[0049] Further, the second time period may also include the first time period. In the embodiments of this specification, the historical traffic road data collected within the first time period may also be filtered based on the frequent item sets of the abnormal data to obtain a filtering result.

[0050] Step 108: Update the known high-precision map data by using the filtering result.

[0051] In the embodiments of this specification, the known high-precision map data may be updated by using the traffic road data that does not contain frequent item sets in the traffic road data collected within the second time period.

[0052] It can be understood that if there is no traffic road data that does not contain frequent item sets in the traffic road data collected within the second time period, the known high-precision map data may not be updated by using the traffic road data collected within the second time period.

[0053] In the embodiments of this specification, the frequent item sets may be determined based on the abnormal data in the historical traffic road data, and the abnormal data in the traffic road data collected within the second time period may be screened out by using the frequent item sets. Furthermore, the known high-precision map data may be updated more accurately by using the traffic road data that does not contain frequent item sets.

[0054] It should be understood that the order of some steps of the method described in one or more embodiments of this specification may be interchanged according to actual needs, or some of the steps may also be omitted or deleted.

[0055] Based on Figure 1 the method, some specific implementation schemes of the method are further provided in the embodiments of this specification, which are described below.

[0056] In the embodiments of this specification, for the convenience of data processing, after the historical traffic road data is obtained, the historical traffic road data may also be preprocessed. Specifically, it may include:

[0057] Discretize the feature values corresponding to the data features of the historical traffic road data.

[0058] In the embodiments of this specification, the value range of the feature values corresponding to the data features may be divided into multiple intervals. Furthermore, the feature values of the data features may be mapped to the intervals corresponding to the feature values, so as to represent different feature values by using different discrete values for different intervals. For example, the feature value corresponding to the width feature in the size feature of the traffic sign is 2.2 meters. Assuming that the interval corresponding to the feature value of 2.2 meters is then 2 may be used to represent the interval The discrete value then represents the eigenvalue. That is, the eigenvalue corresponding to the width feature in the size feature of the traffic sign, which is 2.2 meters, becomes 2 meters after discretization, thus greatly facilitating the subsequent data processing process.

[0059] In the embodiments of this specification, the historical traffic road data may include data of multiple ground feature elements collected by the collection device. Assuming that there is a certain ground feature element in the high-precision map, but the collection device has not collected the data of this ground feature element, that is, it is known that the traffic road data includes the data of a certain ground feature element, but the historical traffic road data does not include the data of this ground feature element, then it can be considered that the historical traffic road data corresponding to the data of this ground feature element is abnormal data. The determining the abnormal data in the historical traffic road data by using the known traffic road data in the known high-precision map data may specifically include:

[0060] Matching the data of the ground feature elements in the known traffic road data with the data of the ground feature elements in the historical traffic road data;

[0061] Determining the historical traffic road data corresponding to the data of the ground feature elements with failed matching as the abnormal data in the historical traffic road data.

[0062] Specifically, based on the data characteristics of the first ground feature element in the known traffic road data and the data characteristics of the second ground feature element in the historical traffic road data, the data of the first ground feature element in the known traffic road data can be matched with the data of the second ground feature element in the historical traffic road data; if the difference between the eigenvalue corresponding to the data characteristics of the first ground feature element and the eigenvalue corresponding to the data characteristics of the second ground feature element is not within the first preset difference range, then the historical traffic road data corresponding to the data of the second ground feature element can be determined as the abnormal data in the historical traffic road data.

[0063] Furthermore, data matching can be performed based on data characteristics of the data of the ground feature elements, such as type characteristics, color characteristics, shape characteristics, or size characteristics, etc. If the type characteristics of the data of the ground feature elements in the known traffic road data are the same as, and / or the color characteristics are the same as, and / or the difference between the eigenvalues corresponding to the size characteristics is within the first preset difference range, then it can be determined that the data matching is successful, otherwise the data matching fails.

[0064] In the embodiments of this specification, the data of the ground feature elements in the historical traffic road data may further include location data. Data matching may also be performed based on the location data in the data of the ground feature elements. Among them, based on the location data of the first ground feature element in the known traffic road data and the location data of the second ground feature element in the historical traffic road data, the data of the first ground feature element in the known traffic road data may be matched with the data of the second ground feature element in the historical traffic road data; if the difference between the location value corresponding to the location data of the first ground feature element and the location value corresponding to the location data of the second ground feature element is not within the second preset difference range, the historical traffic road data corresponding to the data of the second ground feature element may be determined as the abnormal data in the historical traffic road data.

[0065] For example, the location data of the ground feature element can be represented by longitude and latitude. If the difference between the longitude and latitude of the ground feature element in the known traffic road data and the longitude and latitude of the ground feature element in the historical traffic road data is within the second preset difference range, it can be determined that the data matching is successful; otherwise, the data matching fails.

[0066] Figure 3 It is a schematic diagram during data matching provided by the embodiments of this specification. As Figure 3 shown in the figure, B1 in the figure may be the first road traffic marking in the known high-precision map, B2 may be the second road traffic marking in the known high-precision map, B3 may be the third road traffic marking in the known high-precision map, B4 may be the first traffic sign in the known high-precision map, and B5 may be the second traffic sign in the known high-precision map; R1 may be the fourth road traffic marking collected by the collection device, R2 may be the fifth road traffic marking collected by the collection device, R3 may be the sixth road traffic marking collected by the collection device, and R4 may be the third traffic sign collected by the collection device. The data matching result may be that the data of B1 is successfully matched with the data of R1, the data of B2 is successfully matched with the data of R2, the data of B3 is successfully matched with the data of R3, the data of B4 is successfully matched with the data of R4, and the data of B5 fails to match.

[0067] In the embodiments of this specification, the historical traffic road data corresponding to the data of the ground feature element with a failed match may be determined as the abnormal data in the historical traffic road data. As Figure 3 shown in the figure, assuming that the data of B5 fails to match, the historical traffic road data corresponding to the data of B5 may be determined as the abnormal data in the historical traffic road data.

[0068] The historical traffic road data corresponding to the data of B5 may include the acquisition condition data of the acquisition device at B5. In a specific embodiment, the historical traffic road data may further include the position data of the acquisition device when collecting the data of the ground feature elements. The one-to-one correspondence between the position data of the acquisition device and the acquisition condition data may be established in advance based on the acquisition time of the data of the ground feature elements. When determining the acquisition condition data of the acquisition device at B5, the position data of B5 may be matched with the position data of the acquisition device. For example, the position data of the acquisition device may be represented by longitude and latitude. If the difference between the longitude and latitude of B5 and the longitude and latitude of the acquisition device is within the range of the third preset difference, it may be determined that the data matching is successful. Furthermore, based on the position data of the acquisition device, the acquisition condition data of the acquisition device at B5 may be determined by using the one-to-one correspondence between the position data of the acquisition device and the acquisition condition data.

[0069] Furthermore, the abnormal data in the embodiments of the present specification may further include the data of B5, that is, the data of the ground feature elements that fail to match in the known traffic road data. Since the data of the ground feature elements that fail to match may be the data that the acquisition device fails to collect, the frequent item set may be determined based on the data characteristics of the data that the acquisition device fails to collect, and the data characteristics affecting the acquisition accuracy of the traffic road data may be obtained.

[0070] In the embodiments of the present specification, if the recall rate of the data of the ground feature elements is less than or equal to the first preset recall rate threshold, the historical traffic road data including the data of the ground feature elements may also be determined as abnormal data. The recall rate may also be understood as the acquisition rate. The high-precision map update method provided by the embodiments of the present specification may further include:

[0071] For any data of a ground feature element in the successfully matched historical traffic road data, calculate the recall rate of the data of the any ground feature element;

[0072] Judge whether the recall rate is less than or equal to the first preset recall rate threshold;

[0073] If the recall rate is less than or equal to the first preset recall rate threshold, the historical traffic road data including the data of the any ground feature element is determined as the abnormal data in the historical traffic road data.

[0074] It can be understood that the embodiments of the present specification may also directly calculate the recall rate of the data of any ground feature element in the historical traffic data obtained in step 102, and then determine the abnormal data.

[0075] The embodiments of the present specification use the known high-precision map data as the ground truth to determine the abnormal data in the historical traffic road data. Compared with determining the abnormal data according to manual experience, the abnormal data can be determined more efficiently.

[0076] In the embodiments of this specification, abnormal data can be clustered to obtain abnormal data of multiple categories. For the abnormal data of multiple categories, frequent itemsets can be determined in parallel, thereby greatly improving the data processing efficiency. Determining the frequent itemsets of the abnormal data based on the data characteristics of the abnormal data may specifically include:

[0077] Clustering the abnormal data to obtain abnormal data of multiple categories;

[0078] For any category of abnormal data, based on the data characteristics of the abnormal data of the category, determine the frequent itemsets of the abnormal data of the category.

[0079] Among them, the abnormal data can be clustered based on the data characteristics of the ground feature data, or the abnormal data can be clustered based on the data characteristics of the acquisition condition data. The clustering the abnormal data to obtain abnormal data of multiple categories may specifically include:

[0080] Clustering the abnormal data based on the data characteristics of the ground feature data in the abnormal data to obtain abnormal data of multiple categories; the ground features include at least one of traffic sign poles, traffic signs, traffic lights, curbs, guardrails, and road traffic markings; the data characteristics of the ground feature data include at least one of type characteristics, color characteristics, shape characteristics, and size characteristics;

[0081] And / or,

[0082] Clustering the abnormal data based on the data characteristics of the acquisition condition data in the abnormal data to obtain abnormal data of multiple categories; the acquisition condition data is the acquisition condition data when acquiring the data of the ground features; the data characteristics of the acquisition condition data include at least one of acquisition time characteristics, acquisition distance characteristics, acquisition angle characteristics, and acquisition environment characteristics. The acquisition environment characteristics may include illumination characteristics, acquisition scene characteristics, etc.

[0083] Furthermore, algorithms such as the k-means clustering algorithm (English full name: k-means clustering algorithm), Mean-shift (Chinese full name: mean shift algorithm), DBSCAN (English full name: Density-Based Spatial Clustering of Applications with Noise; Chinese full name: density-based clustering algorithm) can be used to cluster the abnormal data.

[0084] In the embodiments of this specification, after obtaining abnormal data of multiple categories, it is also possible to determine whether the abnormal data of multiple categories is valid abnormal data. For example, it can be determined based on the similarity between the abnormal data of multiple categories or the aggregation degree of the abnormal data of any category. Among them, determining whether the abnormal data of multiple categories is valid abnormal data may specifically include:

[0085] Using a preset algorithm to determine the similarity between the abnormal data of the multiple categories;

[0086] Determining the target category quantity of the abnormal data of the category whose similarity is less than or equal to a preset category similarity threshold;

[0087] Calculating a first proportion of the target category quantity in the category quantity of the abnormal data of the multiple categories;

[0088] If the first proportion is less than or equal to a preset first proportion threshold, it is determined that the abnormal data of the multiple categories is valid abnormal data;

[0089] And / or,

[0090] For the abnormal data of any category among the abnormal data of the multiple categories, using a preset algorithm to determine the aggregation degree of the abnormal data of the any category;

[0091] If the aggregation degree meets a preset aggregation degree condition, it is determined that the abnormal data of the any category is valid abnormal data.

[0092] Among them, the preset algorithm may be the FP-Tree (full English name: Frequent Pattern Tree; full Chinese name: frequent pattern tree) algorithm.

[0093] Furthermore, the preset category similarity threshold may be 0.4, 0.5, etc., and the first proportion threshold may be 0.3, 0.4, etc. Of course, in actual applications, the preset category similarity threshold and the first proportion threshold can be set according to actual needs, and no specific limitations are made here.

[0094] In the embodiments of this specification, the frequent item set of the abnormal data of any category can be determined based on the FP-Tree algorithm. If the determined frequent item set meets the following conditions, it can be determined that the aggregation degree of the abnormal data of any category meets the preset aggregation degree condition:

[0095] The min support (Chinese name: node minimum support) when using the FP-Tree algorithm to determine the frequent item set of the abnormal data of any category is greater than or equal to a preset support threshold;

[0096] And / or, when using the FP-Tree algorithm to determine the frequent item sets of abnormal data of any category, the max support decrease (Chinese name: the maximum amount of support decrease after node division) is greater than or equal to a preset decrease threshold;

[0097] And / or, when using the FP-Tree algorithm to determine the frequent item sets of abnormal data of any category, the min setnum (Chinese name: the minimum number of sets) is greater than or equal to a preset minimum number of sets threshold.

[0098] Among them, the preset support threshold can be 0.6, 0.5, etc., the preset decrease threshold can be 0.3, 0.3, etc., and the preset minimum number of sets threshold can be 3, 4, etc. Of course, in actual applications, the preset support threshold, the preset decrease threshold, and the preset minimum number of sets threshold can be set according to actual needs, and no specific limitations are made here.

[0099] In the embodiments of this specification, the frequent item sets can include multiple frequent item sets, such as the first frequent item set, the second frequent item set, etc. Among them, the dimensions of the data features of different frequent item sets can be different. For example, the first frequent item set can be the data feature of the first dimension, and the second frequent item set can be the data feature of the second dimension, etc. The data feature of the first dimension can be a data feature containing one dimension, such as any one of the data features including the acquisition distance feature, the acquisition environment feature, the type feature of ground objects, the color feature of ground objects, and the shape feature of ground objects; the data feature of the second dimension can be a data feature containing two dimensions, such as including two of the data features including the acquisition distance feature, the acquisition environment feature, the type feature of ground objects, the color feature of ground objects, and the shape feature of ground objects.

[0100] The traffic road data collected in the second time period can be screened in turn based on the first frequent item set, the second frequent item set, etc. For example, taking the frequent item sets including the first frequent item set and the second frequent item set as an example, the traffic road data can be screened based on the first frequent item set, and the traffic road data containing the first frequent item set can be determined as abnormal data, and the traffic road data not containing the first frequent item set can be screened again based on the second frequent item set. Since the traffic road data can be screened first using the frequent item sets with data features of fewer dimensions, the data screening workload is small, so the traffic road data can be screened relatively quickly. Based on this, in the embodiments of this specification, the screening of the traffic road data collected in the second time period based on the frequent item sets to obtain a screening result may specifically include:

[0101] Judge whether the traffic road data collected in the second time period contains the first frequent item set; the data feature of the first dimension contains a data feature of one dimension;

[0102] If the traffic road data collected within the second time period contains the first frequent item set, then the traffic road data collected within the second time period that contains the first frequent item set is screened out;

[0103] If the traffic road data collected within the second time period does not contain the first frequent item set, then it is determined whether the traffic road data collected within the second time period contains the second frequent item set; the second-dimensional data feature includes data features of two dimensions;

[0104] If the traffic road data collected within the second time period contains the second frequent item set, then the traffic road data collected within the second time period that contains the second frequent item set is screened out;

[0105] If the traffic road data collected within the second time period does not contain the second frequent item set, then the traffic road data collected within the second time period that does not contain the second frequent item set is determined as the screening result.

[0106] The embodiments of this specification also provide a specific process for determining a frequent item set. Based on the data features of the abnormal data, determining the frequent item set of the abnormal data may specifically include:

[0107] Based on the data features of the abnormal data, determining the first frequent item set of the abnormal data; the first frequent item set is the first-dimensional data feature;

[0108] Screening out the abnormal data that contains the first-dimensional data feature from the abnormal data to obtain first abnormal data;

[0109] Based on the data features of the first abnormal data, determining the second frequent item set of the first abnormal data; the second frequent item set is the second-dimensional data feature; the data dimension of the second-dimensional data feature is different from that of the first-dimensional data feature;

[0110] Determining the first frequent item set and the second frequent item set as the frequent item set of the abnormal data.

[0111] Among them, the first frequent item set can be determined by using the FP-Tree algorithm or the Apriori algorithm, and the second frequent item set can also be determined by using the FP-Tree algorithm or the Apriori algorithm.

[0112] Since the embodiments of this specification can first screen traffic road data based on the first frequent item set, and then screen the screened traffic road data based on the second frequent item set, and the screening result based on the first frequent item set will affect the subsequent screening results, the accuracy of the first frequent item set is crucial. Therefore, the first frequent item set can be determined from the abnormal data of the historical traffic road data determined in step 104, and then the second frequent item set can be determined from the abnormal data that does not include the first frequent item set.

[0113] In the embodiments of this specification, after determining the second frequent item set, the third frequent item set can also be determined, where the third frequent item set can be the data characteristics of the third dimension. The determination process of the third frequent item set and the second frequent item set is the same. The difference is that the third frequent item set can be determined based on the abnormal data that does not include the data characteristics of the second dimension in the first abnormal data. Further, the fourth frequent item set, the fifth frequent item set, etc. can also be determined according to actual needs.

[0114] It can be understood that, to improve the efficiency of determining the frequent item set, the second frequent item set, the third frequent item set, etc. can also be determined from the abnormal data of the historical traffic road data determined in step 104, that is, the first frequent item set, the second frequent item set, the third frequent item set, etc. are determined from the abnormal data respectively.

[0115] In the embodiments of this specification, it can also be determined whether the frequent item set is a credible frequent item set. If the frequent item set is a credible frequent item set, the traffic road data collected in the second time period is screened to improve the accuracy of data screening. Among them, it can be determined whether the frequent item set is a credible frequent item set based on the confidence level of the frequent item set, the lift, or the data strength of the historical traffic road data including the frequent item set. The determination of whether the frequent item set is a credible frequent item set may specifically include at least one of the following:

[0116] Based on the proportion of the data volume of the historical traffic road data including the frequent item set in the data volume of the historical traffic road data, and the data volume of the abnormal data including the frequent item set, determine the confidence level of the frequent item set; if the confidence level is greater than or equal to the preset confidence threshold, determine that the frequent item set is a credible frequent item set;

[0117] Based on the proportion of the data volume of the historical traffic road data including the frequent item set in the data volume of the historical traffic road data, the data volume of the abnormal data including the frequent item set, and the data volume of the abnormal data, determine the lift of the frequent item set; if the lift is greater than or equal to the preset lift threshold, determine that the frequent item set is a credible frequent item set;

[0118] Determine the data intensity of the historical traffic road data containing the frequent item set based on the data volume of the historical traffic road data containing the frequent item set; if the data intensity is greater than or equal to the preset data intensity threshold, determine the frequent item set as a credible frequent item set.

[0119] Further, the determination formula of confidence can be as follows:

[0120]

[0121] Among them, P(AB) is the data volume of the abnormal data containing the frequent item set, and P(B) is the proportion of the data volume of the historical traffic road data containing the frequent item set in the data volume of the historical traffic road data.

[0122] The determination formula of lift can be as follows:

[0123]

[0124] Among them, P(A) is the data volume of the abnormal data.

[0125] In the embodiments of this specification, the data intensity of the historical traffic road data containing the frequent item set can be determined by constructing a sigmoid shock function, and the specific formula can be as follows:

[0126]

[0127] Among them, e is the natural constant, ω is a preset scaling parameter, and n is the data volume of the historical traffic road data containing the frequent item set.

[0128] In the embodiments of this specification, the data of the ground object elements in the successfully matched historical traffic road data can be divided based on a first preset recall rate threshold and a second preset recall rate threshold, where the first preset recall rate threshold can be less than the second preset recall rate threshold. The historical traffic road data containing the data of the ground object elements less than or equal to the first preset recall rate threshold can be determined as target abnormal data, the historical traffic road data containing the data of the ground object elements greater than the first preset recall rate threshold and less than or equal to the second preset recall rate threshold can be determined as pending abnormal data, and the historical traffic road data containing the data of the ground object elements greater than the second preset recall rate threshold can be determined as normal data. The target abnormal data can be verified through the pending abnormal data and the normal data, and then it can be determined whether the frequent item set is a credible frequent item set. Among them, the frequent item set in the embodiments of this specification can include a target frequent item set determined based on the target abnormal data; determining whether the frequent item set is a credible frequent item set can further include at least one of the following:

[0129] Determine the purity of the target abnormal data based on the data volume of the target abnormal data and the data volume of the normal data; if the purity is greater than or equal to a preset purity threshold, determine that the target frequent item set is a credible frequent item set;

[0130] Determine the clarity of the target abnormal data based on the data volume of the target abnormal data and the data volume of the to-be-determined abnormal data; if the clarity is greater than or equal to a preset clarity threshold, determine that the target frequent item set is a credible frequent item set.

[0131] Further, the formula for determining purity can be as follows:

[0132]

[0133] where n(x) is the data volume of the target abnormal data, and n(z) is the data volume of the normal data.

[0134] The formula for determining clarity can be as follows:

[0135]

[0136] where n(y) is the data volume of the to-be-determined abnormal data.

[0137] In the embodiments of this specification, the first preset recall rate threshold and the second preset recall rate threshold can be determined by using a Gaussian mixture model based on the recall rate of the data of the ground object elements. This is because whether the data of the ground object elements are collected by the acquisition device follows a binomial distribution that is independent of each other. Therefore, the recall rate of the data of the ground object elements can follow a Gaussian mixture model (abbreviation in English: GMM; full English name: Gaussian Mixture Module) generated by superimposing multiple Gaussian distributions. Therefore, in the embodiments of this specification, the first preset recall rate threshold and the second preset recall rate threshold can be determined more accurately by using a Gaussian mixture model based on the recall rate of the data of the ground object elements, and then it can be determined more accurately whether the target frequent item set is a credible frequent item set.

[0138] Figure 4 is a process schematic diagram of a high-precision map update method provided by the embodiments of this specification, as Figure 4As shown, the method may include step 402: obtaining historical traffic road data collected within a first time period; step 404: determining abnormal data. Among them, the abnormal data in the historical traffic road data can be determined by using the known traffic road data in the known high-precision map data; step 406: determining the frequent item sets of the abnormal data; step 408: determining that the frequent item sets obtained in step 406 are credible frequent item sets; step 410: judging whether there are the frequent item sets obtained in step 406 in the database. If not, store the frequent item sets obtained in step 406 in the database and execute step 402 or step 404 or step 406 again. If so, execute step 412; step 412: using the frequent item sets in the database to filter the traffic road data collected within a second time period, and then updating the known high-precision map data according to the filtering result.

[0139] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 5 For the embodiments of this specification, corresponding to Figure 1 is a schematic structural diagram of a computer device. As Figure 5 shown, the device may include:

[0140] An abnormal data determination module 502, configured to obtain historical traffic road data collected within a first time period, and use the known traffic road data in the known high-precision map data to determine the abnormal data in the historical traffic road data;

[0141] A frequent item set determination module 504, configured to determine the frequent item sets of the abnormal data based on the data characteristics of the abnormal data; the frequent item sets represent data characteristics and / or data characteristic sets in the abnormal data whose occurrence frequencies are greater than or equal to a preset frequency threshold;

[0142] A data screening module 506, configured to screen the traffic road data collected within a second time period based on the frequent item sets to obtain a screening result;

[0143] A data update module 508, configured to update the known high-precision map data by using the screening result.

[0144] In the embodiments of this specification, the abnormal data determination module 502 may specifically include:

[0145] A first matching unit, configured to match the data of the first feature element in the known traffic road data with the data of the second feature element in the historical traffic road data based on the data features of the first feature element in the known traffic road data and the data features of the second feature element in the historical traffic road data; if the difference between the feature value corresponding to the data feature of the first feature element and the feature value corresponding to the data feature of the second feature element is not within the first preset difference range, then determine the historical traffic road data corresponding to the data of the second feature element as the abnormal data in the historical traffic road data;

[0146] And / or, a second matching unit, configured to match the data of the first feature element in the known traffic road data with the data of the second feature element in the historical traffic road data based on the position data of the first feature element in the known traffic road data and the position data of the second feature element in the historical traffic road data; if the difference between the position value corresponding to the position data of the first feature element and the position value corresponding to the position data of the second feature element is not within the second preset difference range, then determine the historical traffic road data corresponding to the data of the second feature element as the abnormal data in the historical traffic road data.

[0147] In the embodiments of the present specification, the frequent item set determination module 504 may specifically include:

[0148] A first frequent item set determination unit, configured to determine a first frequent item set of the abnormal data based on the data features of the abnormal data; the first frequent item set is a first-dimensional data feature;

[0149] A screening unit, configured to screen out the abnormal data containing the first-dimensional data feature from the abnormal data to obtain first abnormal data;

[0150] A second frequent item set determination unit, configured to determine a second frequent item set of the first abnormal data based on the data features of the first abnormal data; the second frequent item set is a second-dimensional data feature; the data dimension of the second-dimensional data feature is different from that of the first-dimensional data feature;

[0151] A frequent item set determination unit, configured to determine the first frequent item set and the second frequent item set as the frequent item set of the abnormal data.

[0152] Further, the high-precision map updating device may further include:

[0153] A credible frequent item set determination module, configured to determine whether the frequent item set is a credible frequent item set.

[0154] In the embodiments of this specification, the credible frequent item set determination module may specifically include at least one of the following:

[0155] The first credible frequent item set determination unit is configured to determine the confidence of the frequent item set based on the proportion of the data volume of the historical traffic road data containing the frequent item set in the data volume of the historical traffic road data and the data volume of the abnormal data containing the frequent item set; if the confidence is greater than or equal to the preset confidence threshold, determine that the frequent item set is a credible frequent item set;

[0156] The second credible frequent item set determination unit is configured to determine the lift of the frequent item set based on the proportion of the data volume of the historical traffic road data containing the frequent item set in the data volume of the historical traffic road data, the data volume of the abnormal data containing the frequent item set, and the data volume of the abnormal data; if the lift is greater than or equal to the preset lift threshold, determine that the frequent item set is a credible frequent item set;

[0157] The third credible frequent item set determination unit is configured to determine the data strength of the historical traffic road data containing the frequent item set based on the data volume of the historical traffic road data containing the frequent item set; if the data strength is greater than or equal to the preset data strength threshold, determine that the frequent item set is a credible frequent item set.

[0158] Further, the data screening module 506 may specifically include:

[0159] The first judgment unit is configured to judge whether the traffic road data collected in the second time period contains the first frequent item set; the first-dimensional data feature includes the data feature of one dimension;

[0160] The first screening unit is configured to screen the traffic road data collected in the second time period containing the first frequent item set when the traffic road data collected in the second time period contains the first frequent item set;

[0161] The second judgment unit is configured to judge whether the traffic road data collected in the second time period contains the second frequent item set when the traffic road data collected in the second time period does not contain the first frequent item set; the second-dimensional data feature includes the data features of two dimensions;

[0162] The second screening unit is configured to screen the traffic road data collected in the second time period containing the second frequent item set when the traffic road data collected in the second time period contains the second frequent item set;

[0163] A screening result determination unit, when the traffic road data collected within the second time period does not contain the second frequent item set, determines the traffic road data collected within the second time period that does not contain the second frequent item set as the screening result.

[0164] In the embodiments of this specification, the historical traffic road data includes data of ground features, and the ground features include at least one of traffic sign poles, traffic signs, traffic lights, curbs, guardrails, and road traffic markings; the data features of the data of the ground features include at least one of type features, color features, shape features, and size features.

[0165] And / or, the historical traffic road data includes acquisition condition data when acquiring data of ground features, and the data features of the acquisition condition data include at least one of acquisition time features, acquisition distance features, acquisition angle features, and acquisition environment features.

[0166] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.

[0167] Figure 6 For the Figure 1 corresponding to the embodiments of this specification Figure 6 is a schematic structural diagram of a computer device. As

[0168] shown, the device 600 may include: a memory 610, a processor 620, and a computer program 630 stored on the memory 610. The processor 620 executes the computer program 630 to implement the steps of the above method for identifying traffic elements.

[0169] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for Figure 6 the computer device shown, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0170] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one type of HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0171] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0172] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0173] For the convenience of description, the above devices are described by dividing them into various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0174] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0175] The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block of the flowchart illustrations and / or block diagrams, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processors of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing apparatus create means for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0178] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0179] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0180] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0181] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0182] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0183] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0184] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A high-precision map update method, characterized in that, Including: Obtain historical traffic road data collected within a first time period, and use the known traffic road data in the known high-precision map data to determine the abnormal data in the historical traffic road data; Based on the data characteristics of the abnormal data, determine the frequent item sets of the abnormal data; the frequent item sets represent data characteristics and / or data characteristic sets in the abnormal data that appear with a frequency greater than or equal to a preset frequency threshold; Based on the frequent item sets, screen the traffic road data collected within a second time period to obtain a screening result; Use the screening result to update the known high-precision map data.

2. The method according to claim 1, characterized in that, The step of using the known traffic road data in the known high-precision map data to determine the abnormal data in the historical traffic road data specifically includes: Based on the data characteristics of the first ground feature element in the known traffic road data and the data characteristics of the second ground feature element in the historical traffic road data, match the data of the first ground feature element in the known traffic road data with the data of the second ground feature element in the historical traffic road data; if the difference between the characteristic value corresponding to the data characteristics of the first ground feature element and the characteristic value corresponding to the data characteristics of the second ground feature element is not within the first preset difference range, then determine the historical traffic road data corresponding to the data of the second ground feature element as the abnormal data in the historical traffic road data; And / or, based on the position data of the first ground feature element in the known traffic road data and the position data of the second ground feature element in the historical traffic road data, match the data of the first ground feature element in the known traffic road data with the data of the second ground feature element in the historical traffic road data; if the difference between the position value corresponding to the position data of the first ground feature element and the position value corresponding to the position data of the second ground feature element is not within the second preset difference range, then determine the historical traffic road data corresponding to the data of the second ground feature element as the abnormal data in the historical traffic road data.

3. The method according to claim 1, wherein The step of determining the frequent item sets of the abnormal data based on the data characteristics of the abnormal data specifically includes: Based on the data characteristics of the abnormal data, determine the first frequent item sets of the abnormal data; the first frequent item sets are data characteristics in the first dimension; Screen out the abnormal data containing the data characteristics in the first dimension from the abnormal data to obtain the first abnormal data; Based on the data characteristics of the first abnormal data, determine the second frequent item sets of the first abnormal data; the second frequent item sets are data characteristics in the second dimension; the data dimensions of the second frequent item sets are different from those of the first frequent item sets; Determine the first frequent item sets and the second frequent item sets as the frequent item sets of the abnormal data.

4. The method according to claim 1, characterized in that, After the step of determining the frequent item sets of the abnormal data based on the data characteristics of the abnormal data, it further includes: determining whether the frequent item sets are credible frequent item sets.

5. The method according to claim 4, characterized in that The step of determining whether the frequent item sets are credible frequent item sets specifically includes at least one of the following: Determine the confidence of the frequent item set based on the proportion of the data volume of the historical traffic road data containing the frequent item set in the data volume of the historical traffic road data and the data volume of the abnormal data containing the frequent item set; if the confidence is greater than or equal to the preset confidence threshold, determine that the frequent item set is a credible frequent item set; Determine the lift of the frequent item set based on the proportion of the data volume of the historical traffic road data containing the frequent item set in the data volume of the historical traffic road data, the data volume of the abnormal data containing the frequent item set, and the data volume of the abnormal data; If the lift is greater than or equal to the preset lift threshold, determine that the frequent item set is a credible frequent item set; Determine the data intensity of the historical traffic road data containing the frequent item set based on the data volume of the historical traffic road data containing the frequent item set; If the data intensity is greater than or equal to the preset data intensity threshold, determine that the frequent item set is a credible frequent item set.

6. The method according to claim 3, characterized in that The screening of the traffic road data collected in the second time period based on the frequent item set to obtain a screening result specifically includes: Judge whether the traffic road data collected in the second time period contains the first frequent item set; the first-dimensional data feature includes the data feature of one dimension; If the traffic road data collected in the second time period contains the first frequent item set, screen out the traffic road data collected in the second time period that contains the first frequent item set; If the traffic road data collected in the second time period does not contain the first frequent item set, judge whether the traffic road data collected in the second time period contains the second frequent item set; the second-dimensional data feature includes the data features of two dimensions; If the traffic road data collected in the second time period contains the second frequent item set, screen out the traffic road data collected in the second time period that contains the second frequent item set; If the traffic road data collected in the second time period does not contain the second frequent item set, determine the traffic road data collected in the second time period that does not contain the second frequent item set as the screening result.

7. The method according to claim 1, characterized in that, The historical traffic road data includes data of ground features, and the ground features include at least one of traffic sign poles, traffic signs, traffic signal lights, curbs, guardrails, and road traffic markings; the data features of the data of the ground features include at least one of type features, color features, shape features, and size features; And / or, the historical traffic road data includes the acquisition condition data when acquiring the data of the ground features, and the data features of the acquisition condition data include at least one of acquisition time features, acquisition distance features, acquisition angle features, and acquisition environment features.

8. A high-precision map update device, characterized in that, Include: An abnormal data determination module, configured to obtain the historical traffic road data collected in the first time period, and determine the abnormal data in the historical traffic road data by using the known traffic road data in the known high-precision map data; The frequent item set determination module is used to determine the frequent item sets of the abnormal data based on the data characteristics of the abnormal data; the frequent item sets represent the data characteristics and / or data characteristic sets that appear in the abnormal data with a frequency greater than or equal to a preset frequency threshold; The data screening module is used to screen the traffic road data collected in the second time period based on the frequent item sets to obtain a screening result; The data update module is used to update the known high-precision map data with the screening result.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor; and / or a computer program product, including a computer program, which implements the method according to any one of claims 1 to 7 when executed by a processor.

Images