Methods, devices, equipment and media for quality inspection of identification points in map elements

Abstract

The present disclosure provides a method, device, equipment, medium and product for quality inspection of identification points in map elements, which relates to the field of the Internet, and in particular to the field of intelligent transportation technology. The specific implementation scheme is as follows: in response to the current identification point being a valid identification point, the valid identification point is verified for passability rationality in combination with the map base map data; in response to the current identification point being an invalid identification point, the invalid identification point is recalled based on the number of original identification points with the same identification content as the invalid identification point in the original identification point database. The technical solution disclosed in the present disclosure can improve the accuracy of identification point quality inspection.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, in particular to intelligent transportation technology, and specifically to a method, device, equipment, medium and product for quality inspection of identification points in map elements. Background Art

[0002] Navigation has become an integral part of people's lives. The accuracy of electronic map data directly impacts navigation effectiveness. Electronic map data is generated based on numerous map elements. The verification process for these map elements consists of three main steps: image verification, point mark verification, and internal production.

[0003] However, the verification effect of marks in map elements still cannot meet the current demand for map data accuracy, and the verification accuracy of mark data is still not high. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, device, medium and product for quality inspection of identification points in map elements.

[0005] According to one aspect of the present disclosure, a method for quality inspection of marker points in map elements is provided, comprising:

[0006] In response to the current identification point being a valid identification point, performing a passability rationality check on the valid identification point in combination with the map base map data;

[0007] In response to the current identification point being an invalid identification point, the invalid identification point is recalled according to the number of original identification points in the original identification point database that have the same identification content as the invalid identification point.

[0008] According to another aspect of the present disclosure, a device for quality inspection of identification points in map elements is provided, comprising:

[0009] A valid identification point verification module is used to verify the passability rationality of the valid identification point in response to the current identification point being a valid identification point in combination with the map base map data;

[0010] The invalid identification point recall module is used to recall the invalid identification point in response to the current identification point being an invalid identification point according to the number of original identification points in the original identification point database that have the same identification content as the invalid identification point.

[0011] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for quality inspection of identification points in map elements described in any embodiment of the present disclosure.

[0015] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method for quality inspection of identification points in map elements described in any embodiment of the present disclosure.

[0016] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for quality inspection of identification points in map elements described in any embodiment of the present disclosure.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0019] Figure 1 is a schematic diagram of a method for quality inspection of identification points in map elements according to an embodiment of the present disclosure;

[0020] Figure 2a is a schematic diagram of a method for quality inspection of identification points in map elements according to an embodiment of the present disclosure;

[0021] Figure 2b This is a schematic diagram of traffic rationality judgment according to an embodiment of the present disclosure;

[0022] Figure 2c is another schematic diagram of traffic rationality judgment according to an embodiment of the present disclosure;

[0023] Figure 2d is a schematic diagram of recalling invalid identification points according to an embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram of a method for quality inspection of identification points in map elements according to an embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram of a method for quality inspection of identification points in map elements according to an embodiment of the present disclosure;

[0026] Figure 5is a schematic diagram of a device for quality inspection of identification points in map elements according to an embodiment of the present disclosure;

[0027] Figure 6 It is a block diagram of an electronic device used to implement the method for quality inspection of identification points in map elements in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0029] Figure 1 This is a flow chart of a method for quality inspection of identification points in map elements according to an embodiment of the present disclosure. This embodiment is applicable to the case of quality inspection of identification points in map elements. The method can be executed by a device for quality inspection of identification points in map elements, which is implemented in software and / or hardware and is preferably configured in an electronic device, such as a client device or a server device. The client device is, for example, a mobile phone, a tablet computer, a vehicle-mounted terminal, a desktop computer, etc. Figure 1 As shown, the method specifically includes the following:

[0030] S101. In response to the current identification point being a valid identification point, a traffic rationality check is performed on the valid identification point in combination with map base map data.

[0031] Map base map data refers to the generated electronic map data, which contains relevant information about the city's basic road network. Electronic map data is generated based on many map elements. Marker points, as one of the map elements, require regular information collection and quality inspection to update the electronic map data. Usually, environmental image information is collected by cameras pre-deployed at the location to be collected or by map collection vehicles, and valid information is extracted from the environmental image information. This valid information is the marker point. For example, the marker point can include guide marks on the road, traffic lights or signs around the road, or a bridge, a gas station or a river, etc.

[0032] In order to determine the validity of the current identification point, a preliminary validity judgment can be performed on the current identification point. For example, the map base map data can be used to perform differential deduplication on the current identification point, and then the current identification point that passes the differential deduplication is determined as a valid identification point, while the current identification point that fails the differential deduplication is determined as an invalid identification point. Of course, in addition to differential deduplication, other forms of validity judgment can also be performed on the current identification point according to actual conditions, such as data logical rationality judgment, to determine whether the current identification point is a valid identification point.

[0033] In the disclosed embodiment, after a preliminary validity determination confirms that the current marker is a valid marker, to further improve the accuracy of the marker quality inspection, the valid marker is not directly added to the base map data. Instead, the valid marker is further subjected to a traffic rationality check. Specifically, traffic rationality check refers to an inspection of the marker based on a preset traffic rationality judgment principle in combination with the base map data. The purpose is to determine whether the marker is valid from the perspective of traffic rationality, thereby further improving the accuracy of the marker quality inspection.

[0034] When it is determined that the valid identification points meet the requirements for reasonable passage, they can be used to generate map base map data. Otherwise, the valid identification points can be further corrected or directly abandoned and re-collected to ensure the correctness of the identification points and map base map data.

[0035] In a specific example, the current identification point is, for example, a no right turn sign, and has been identified as a valid identification point. In the embodiment of the present disclosure, a traffic rationality judgment principle associated with the no right turn sign is further obtained in the preset traffic rationality judgment principle. For example, the judgment principle is to judge whether there is a right turn lane in the road opposite to the no right turn sign. At this time, the lane type of the road opposite to the no right turn sign can be obtained from the map base map data. If there is a right turn lane, it is determined that the no right turn sign (i.e., the valid identification point) has not passed the traffic rationality check; otherwise, it is determined that the no right turn sign has passed the traffic rationality check.

[0036] S102: In response to the current identification point being an invalid identification point, the invalid identification point is recalled according to the number of original identification points in the original identification point database that have the same identification content as the invalid identification point.

[0037] In the disclosed embodiment, after a preliminary validity check determines that a current marker is invalid, if the invalid marker is discarded directly, a valid marker may be missed due to misjudgment. Therefore, to further improve the accuracy of marker quality inspection, invalid markers are not discarded directly. Instead, invalid markers are recalled based on the number of original markers in the original marker database that have the same identification content as the invalid marker. The identification content may include the object identified by the marker and the location where the marker was obtained.

[0038] Specifically, the identification content of the invalid identification point can be obtained first, and then the original identification point with the same identification content as the invalid identification point can be identified in the original identification point database. If the number of original identification points with the same identification content as the invalid identification point reaches the set number threshold, it indicates that there are a large number of identification points in the original identification point database that are the same as the current invalid identification point, and the probability of their true values ​​is very high. Therefore, the current invalid identification point can be recalled, thereby avoiding the loss of valid identification points caused by initial judgment errors.

[0039] Among them, after the invalid identification points are recalled, they can be used to generate map base map data, and the recalled invalid identification points can also be further checked for traffic rationality, thereby avoiding map base map data errors caused by invalid identification points not meeting traffic rationality.

[0040] In a specific example, if the current identification point A is determined to be an invalid identification point, the original identification point database can be searched for an original identification point that identifies the same object as the current identification point A (for example, both identify a road sign) and is close to the acquisition location of the current identification point A (for example, the straight-line distance between the two acquisition locations is less than 5 meters). If the number of original identification points that meet the above conditions exceeds a set threshold, the invalid identification point is recalled.

[0041] The technical solution of the embodiment of the present disclosure is that, in response to the current identification point being a valid identification point, the valid identification point is checked for pass rationality in combination with the map base map data, and in response to the current identification point being an invalid identification point, the invalid identification point is recalled based on the number of original identification points in the original identification point database that have the same identification content as the invalid identification point. The valid identification point can be further checked for pass rationality and the invalid identification point can be recalled, thereby improving the accuracy of identification point quality inspection and avoiding omission of valid identification points due to misjudgment.

[0042] Figure 2aThis is a flow chart of the method for quality inspection of identification points in map elements according to the embodiment of the present disclosure. This embodiment is further optimized on the basis of the above embodiment. It provides specific steps for checking the passability rationality of the current identification point in combination with the map base map data, as well as specific steps for recalling invalid identification points based on the number of original identification points with the same identification content as the invalid identification points in the original identification point database. Figure 2a As shown, the method specifically includes the following:

[0043] S201. In response to the current identification point being a valid identification point, the valid identification point is compared with the map base map data, and the valid identification point is checked for pass rationality according to a pre-set pass rationality check principle.

[0044] In the embodiment of the present disclosure, after the current identification point is determined as a valid identification point in the initial verification, the valid identification point is compared with the map base map data, and the valid identification point is verified for traffic rationality according to the pre-set traffic rationality verification principle. Specifically, the identification points within the set range around the valid identification point can be obtained in the map base map data, and then the traffic rationality verification can be performed on the valid identification point based on the pre-set traffic rationality verification principle and the identification points within the obtained set range. It is also possible to obtain the verification principle associated with the valid identification point from the pre-set multiple traffic rationality verification principles, and then obtain the judgment data required for the current rationality verification principle in the map base map data. Finally, based on the judgment data and the traffic rationality judgment principle, it is determined whether the valid identification point has traffic rationality.

[0045] In a specific example, Figure 2b As shown, the current landmark is the left-turn guide line in the image and has been identified as a valid landmark. The lane where the left-turn guide line is located can be determined in the basemap data, and other guide lines within a set distance from the left-turn guide line can be obtained in the lane where the left-turn guide line is located. For example, a straight-ahead guide line within a set distance from the left-turn guide line can be obtained in the lane where the left-turn guide line is located. At this point, it can be determined that the valid landmark conflicts with a landmark already in the basemap data, and the valid landmark is determined to not meet traffic rationality requirements.

[0046] In another specific example, Figure 2cAs shown, the current identification point is a no right turn sign and has been identified as a valid identification point. The traffic rationality judgment principle associated with the no right turn sign can be obtained in the preset traffic rationality judgment principle. For example, the judgment principle is to judge whether there is a right turn lane in the road opposite to the no right turn sign. At this time, the lane type of the road opposite to the no right turn sign can be obtained from the map base map data. If there is a right turn lane, it is determined that the no right turn sign (i.e., the valid identification point) has not passed the traffic rationality check; otherwise, it is determined that the no right turn sign has passed the traffic rationality check.

[0047] S202. If the traffic rationality check passes, the valid identification point is put into the valid identification point database.

[0048] In the disclosed embodiment, if a valid identification point passes the pass rationality check, it can be directly stored in a valid identification point database. The valid identification point database includes multiple valid identification points that have passed quality inspection, and the valid identification points in the valid identification point database are used for internal work, adding more detailed map element information to the base map data, or correcting existing map element information to improve map accuracy.

[0049] S203. If the passage rationality check fails, the valid identification point is corrected and put into the valid identification point database.

[0050] If a valid identification point fails to pass the pass rationality check, it means that the current valid identification point may have a logical error. In this case, the valid identification point can be corrected and then placed in the valid identification point database. For example, the current valid identification point can be corrected based on other identification points in the map base map data. For example, the left turn guide line (i.e., the current valid identification point) that conflicts with the straight guide line originally existing in the map base map data can be corrected to a straight guide line. By further quality inspection of the valid identification points initially determined, the pass rationality of the valid identification points can be guaranteed, and the accuracy of the map data can be further improved.

[0051] In addition, if the traffic plausibility check fails, a quality inspection item is generated. This quality inspection item includes at least one factor that caused the current valid landmark to fail the traffic plausibility check. During actual processing, the quality inspection item can be identified using the landmark quality inspection manual to determine its validity. If the quality inspection item is invalid, it is determined to be redundant. If the quality inspection item is valid, the valid landmark can be corrected based on the quality inspection item. If the correction cannot be completed, intelligence push collection can be performed to re-acquire the data for the landmark. For example, if the quality inspection item is "The sequence of vehicle signal arrows is irregular, verify and supplement the U-turn vehicle signal." The business principle for this quality inspection item is: if the vehicle signal from the left is "straight, straight left", there is no U-turn arrow, and there is no car-prohibited intersection limit, verify whether to derive the U-turn vehicle signal. The quality inspection item is then verified and corrected according to the provisions of the quality inspection manual. For example, the existence of the actual vehicle information can be verified based on the latest track photo, and if not, it can be deleted; or the actual vehicle information can be verified based on the latest track photo to see if it has changed. If so, the vehicle information is re-entered and displayed, and the corresponding guidance vehicle information is derived (confirming whether the criteria for additional U-turns are met, and if so, guiding the additional U-turn; otherwise, not adding the U-turn). The specific operation of revising the quality inspection items in conjunction with the quality inspection manual is not limited in the present embodiment, and can be implemented according to any existing technology.

[0052] S204. If the number of original identification points in the original identification point database that have the same identification content as the invalid identification point meets the preset conditions, the invalid identification point is recalled, wherein the same identification content means that the identified objects are the same, and the coordinate position of the original identification point is within the set range around the invalid identification point.

[0053] In the embodiment of the present disclosure, when it is preliminarily determined that the current identification point is an invalid identification point, if the invalid identification point is directly abandoned, the valid identification point may be lost due to misjudgment. Therefore, the original identification point with the same identification content as the invalid identification point can be searched in the original identification point database, wherein the same identification content means that the identified objects are the same, and the coordinate position of the original identification point is within the set range around the invalid identification point. For example, the identified objects are all lane guide lines, and the original identification point is within the set range of the invalid identification point. Further, it is determined whether the number of original identification points obtained meets the preset conditions. If so, it means that the probability that the current invalid identification point is actually valid is relatively high, and the invalid identification point is recalled to avoid the loss of valid identification points.

[0054] In a specific example, Figure 2dAs shown, if marker point A is determined to be invalid, the original marker point data can be searched for original marker points that have the same object as marker point A and are within a set distance. For example, if five original marker points are found, and the number of original marker points found is greater than a threshold of 3, the invalid marker point A is recalled.

[0055] Optionally, recall invalid identification points, including:

[0056] Combined with the map base map data, the invalid identification points are checked for passability rationality;

[0057] If the pass rationality check passes, the invalid identification point is placed in the valid identification point database and the invalid identification point is changed to a valid identification point;

[0058] If the passage rationality check fails, the invalid identification point will be corrected and placed in the valid identification point database, and the corrected invalid identification point will be changed to a valid identification point.

[0059] In this optional embodiment, a specific method for recalling invalid identification points is provided: first, the invalid identification points are checked for traffic rationality in combination with the map base map data. If the traffic rationality check passes, it indicates that the recalled invalid identification points meet the traffic rationality, and the invalid identification points are placed in the valid identification point database for standby use, and the invalid identification points are changed to valid identification points; if the traffic rationality check fails, the invalid identification points are corrected and placed in the valid identification point database, and the corrected invalid identification points are changed to valid identification points, so as to ensure that the identification points entering the valid identification point database are correct and valid, thereby providing a guarantee for the accuracy of the map data.

[0060] Among them, the method of checking the rationality of passage for invalid identification points is the same as the above-mentioned method of checking the rationality of passage for valid identification points. Both are checked according to the pre-set rationality check principles for passage, which will not be repeated here.

[0061] S205. Storing the valid identification points in the valid identification point database and the correlation between the internal work results obtained based on the valid identification points in the valid identification point database.

[0062] Among them, the results of internal work can be map elements in map data generated based on valid identification points in the valid identification point database. For example, based on the road signs stored in the valid identification point database, the map data is further improved, that is, the road signs are added to the map data. The road signs added to the map data are the results of internal work.

[0063] In the disclosed embodiment, after valid identification points that have undergone quality inspection are added to the valid identification point database, internal work results generated based on the valid identification points in the valid identification point database can be obtained, and the association between the internal work results and the corresponding valid identification points can be stored. If problems are later discovered in the internal work results, the valid identification points that generated the internal work results can be promptly located based on the aforementioned associations, and further quality inspection or error correction operations can be performed on the valid identification points.

[0064] The technical solution of the embodiment of the present disclosure compares the valid identification points with the map base data, and performs a pass rationality check on the valid identification points according to the pre-set pass rationality check principle. If it passes, it is placed in the valid identification point database; otherwise, it is corrected and placed in the valid identification point database. For invalid identification points, if the number of original identification points with the same identification content as the invalid identification point in the original identification point database meets the preset conditions, the invalid identification point is recalled. On the one hand, the valid identification points that are initially determined can be further quality-checked to improve the accuracy of the quality inspection. On the other hand, the invalid identification points that are initially determined can be recalled to avoid the loss of valid identification points due to misjudgment.

[0065] Figure 3 This is a flow chart of the method for quality inspection of identification points in map elements according to the embodiment of the present disclosure. This embodiment is further optimized on the basis of the above embodiment. It provides specific steps before the validity rationality check of the valid identification points in combination with the map base map data. Figure 3 As shown, the method specifically includes the following:

[0066] S301. Use the map base map data to perform differential deduplication on the current identification point.

[0067] In the disclosed embodiment, a marker point is first extracted from the original marker database as the current marker point, and the current marker point is differentially deduplicated using the map base data to determine whether the current marker point is a valid marker point. Specifically, the differential comparison is to perform a buffered comparison between the current marker point and marker points in the map base data that are within a set range of the current marker point's location to determine whether the current marker point is valid data; deduplication is to determine that if the same marker point is collected at the same location within multiple collection cycles, it is considered necessary to dedupe the current marker point to avoid adding duplicate marker points to the map data.

[0068] S302: If the differential deduplication fails, the current identification point is determined to be an invalid identification point.

[0069] If the current marker point fails the above-mentioned differential deduplication process, the current marker point is determined to be an invalid marker point. Through the differential deduplication process, it is possible to preliminarily determine whether the current marker point is a valid marker point, providing a basis for the subsequent quality inspection of the marker points and improving the efficiency of the marker point quality inspection. For example, if the current marker point is determined to be a duplicate of an existing marker point in the map base map data through deduplication, the current marker point can be determined to be an invalid marker point.

[0070] Optionally, if differential deduplication is performed, determining that the current marker is a valid marker includes:

[0071] If the differential elimination is successful, the current identification point is determined to be a temporary valid identification point, and the data logic rationality verification of the temporary valid identification point is performed according to the pre-set data logic rationality verification principle;

[0072] If the data logic rationality check passes, the current identification point is determined to be a valid identification point;

[0073] If the data logic rationality check fails, the current identification point is determined to be an invalid identification point.

[0074] In this optional embodiment, a specific method is provided for determining that the current identification point is a valid identification point by differential deduplication: if the current identification point passes differential deduplication, the current identification point is determined to be a temporary valid identification point. Furthermore, in order to improve the quality of the quality inspection of the identification point, the temporary valid identification point is further subjected to a data logic rationality check based on a pre-set data logic rationality check principle. If the data logic rationality check passes, the current identification point is determined to be a valid identification point; if the data logic rationality check fails, the current identification point is determined to be an invalid identification point. By adding the data logic rationality check, the accuracy of the identification point quality inspection is further improved.

[0075] For example, the principle of data logic rationality verification refers to the constraints of the specification value range. That is, for each temporary valid identification point, the corresponding specification value range requirements are pre-agreed. If the temporary valid identification point is determined to meet the specification value range requirements, the temporary valid identification point can be determined as a valid identification point; otherwise, it is determined to be an invalid identification point.

[0076] S303: If duplicate removal is performed by differential analysis, the current identification point is determined to be a valid identification point.

[0077] S304: In response to the current identification point being a valid identification point, confirm the type of the valid identification point.

[0078] In the embodiment of the present disclosure, after determining that the current identification point is a valid identification point, before performing a pass rationality check on the valid identification point, the type of the valid identification point can be determined. Exemplarily, the type of the valid identification point can be addition, modification, or deletion.

[0079] S305. If the type of the valid identification point is to increase, the valid identification point is checked for passability rationality in combination with the map base map data.

[0080] In the embodiment of the present disclosure, if the type of the valid identification point is addition, indicating that the valid identification point is used to further improve and supplement the map data, the valid identification point can be directly combined with the map base map data to perform a pass rationality check.

[0081] S306. If the type of the valid identification point is deletion or modification, then in response to the data acquisition time of the valid identification point, which is later than the generation time of the map element corresponding to the valid identification point in the map base map, the valid identification point is checked for passability rationality in combination with the map base map data.

[0082] In the embodiment of the present disclosure, if the type of the valid identification point is deletion or modification, it indicates that the valid identification point is used to modify or delete the map data. At this time, the valid identification point needs to be constrained in the time dimension. Specifically, the data acquisition time of the valid identification point and the generation time of the map element corresponding to the valid identification point in the map base data are judged. If the acquisition time is later than the generation time, it indicates that the data acquisition time corresponding to the valid identification point is later than the map element generation time, and it belongs to new data. Then, the valid identification point can be checked for pass rationality in combination with the map base data. If the acquisition time is earlier than the generation time, it indicates that the data acquisition time corresponding to the valid identification point is earlier than the map element generation time, and it belongs to old data. Then, an intelligence push collection request is sent to the data collection terminal to obtain new collection data. By constraining the valid identification point in the time dimension, it is possible to avoid old data replacing new data, ensure the timeliness of the valid identification point, and improve the accuracy of the identification point quality inspection.

[0083] S307: In response to the current identification point being an invalid identification point, the invalid identification point is recalled according to the number of original identification points in the original identification point database that have the same identification content as the invalid identification point.

[0084] The technical solution of the embodiment of the present disclosure utilizes map base map data to perform differential deduplication on the current identification point to determine whether the current identification point is valid data. When the current identification point is determined to be a valid identification point, in response to the current identification point being a valid identification point, the type of the valid identification point is confirmed. If the type of the valid identification point is increase, the valid identification point is checked for passability rationality in combination with the map base map data. Otherwise, the valid identification point needs to be constrained in the time dimension, which can avoid the operation of replacing old data with new data, ensure the timeliness of the identification point, and improve the accuracy of the identification point quality inspection.

[0085] Figure 4 This is a flow chart of the method for quality inspection of identification points in map elements according to an embodiment of the present disclosure. This embodiment is further optimized based on the above embodiment. Figure 4 As shown, the method specifically includes the following:

[0086] 1. Extract the current identification point from the original identification point database, and use the map base map data to perform differential deduplication on the current identification point. If the differential deduplication is valid, execute step 2 (data logic rationality check); if the differential deduplication is invalid, it is determined that the current identification point is an invalid identification point, and execute step 3 (recall judgment).

[0087] 2. Data logic rationality check. According to the pre-set data logic rationality check principle, perform data logic rationality check on the current identification point where the differential rearrangement is valid. If the data logic rationality check fails, the current identification point is determined to be an invalid identification point, and the process goes to step 3. If the data logic rationality check passes, the current identification point is determined to be a valid identification point, and the process goes to step 4 (pass rationality check). If the data logic rationality check result cannot be verified, step 5 (intelligence push collection) is executed.

[0088] 3. Recall judgment is based on the recall service implementation of invalid identification points. Specifically, whether to recall invalid identification points is determined based on the number of original identification points with the same identification content as the invalid identification points in the original identification point database. Furthermore, the recalled invalid identification points are subjected to a pass rationality check. If the pass rationality check passes, the current invalid identification point is added to the correct whitelist (at the same time, the invalid identification point is changed to a valid identification point), and the current invalid identification point is added to the valid identification point database; if the pass rationality check fails, the current invalid identification point is added to the recalled identification point database, and after the current invalid identification point is corrected, it is added to the valid identification point database.

[0089] 4. Pass rationality check is implemented based on the identification point guarantee service. Specifically, the valid identification points are checked for pass rationality according to the pre-set pass rationality check principles. If the pass rationality check passes, the current valid identification point is added to the correct whitelist and the current valid identification point is added to the valid identification point database; if the pass rationality check fails, the current invalid identification point is added to the difference identification point database, and the current valid identification point is corrected and added to the valid identification point database.

[0090] 5. Intelligence push collection, that is, re-obtaining the information of the identification point.

[0091] 6. Conduct internal work judgments on the valid identification points in the valid identification point database, and generate internal work results based on the internal business work judgment results.

[0092] The technical solution of the embodiment of the present disclosure is to perform a pass rationality check on the valid identification points in combination with the map base map data, and to recall the invalid identification points based on the number of original identification points with the same identification content as the invalid identification points in the original identification point database. The valid identification points can be further checked for pass rationality and the invalid identification points can be recalled, thereby improving the accuracy of quality inspection and avoiding the omission of valid identification points due to misjudgment.

[0093] Figure 5 This is a schematic diagram of the structure of the device for quality inspection of identification points in map elements according to an embodiment of the present disclosure. This embodiment is applicable to the case of quality inspection of identification points in map elements. The device can implement the method for quality inspection of identification points in map elements described in any embodiment of the present disclosure. Figure 5 As shown, the device 500 specifically includes:

[0094] The valid identification point verification module 501 is used to verify the passability rationality of the valid identification point in response to the current identification point being a valid identification point in combination with the map base map data;

[0095] The invalid identification point recall module 502 is used to recall the invalid identification point in response to the current identification point being an invalid identification point based on the number of original identification points in the original identification point database that have the same identification content as the invalid identification point.

[0096] Furthermore, the valid identification point verification module 501 is specifically configured to:

[0097] Confirm the type of the valid identification point;

[0098] If the type of the valid identification point is to increase, the valid identification point is checked for passability rationality in combination with the map base map data;

[0099] If the type of the valid identification point is deletion or modification, then in response to the data acquisition time of the valid identification point, which is later than the generation time of the map element corresponding to the valid identification point in the map base map, the valid identification point is checked for pass rationality in combination with the map base map data.

[0100] Furthermore, the valid identification point verification module 501 is specifically configured to:

[0101] Comparing the valid identification point with the map base map data, and performing a pass rationality check on the valid identification point according to a pre-set pass rationality check principle;

[0102] If the pass rationality check passes, the valid identification point is placed in the valid identification point database;

[0103] If the passage rationality check fails, the valid identification point is corrected and placed in the valid identification point database.

[0104] Furthermore, the invalid identification point recall module 502 is specifically configured to:

[0105] If the number of original identification points in the original identification point database that have the same identification content as the invalid identification point meets the preset conditions, the invalid identification point will be recalled, wherein the same identification content means that the identified objects are the same, and the coordinate position of the original identification point is within the set range around the invalid identification point.

[0106] Furthermore, the invalid identification point recall module 502 is further specifically configured to:

[0107] Performing a pass rationality check on the invalid identification point in combination with the map base map data;

[0108] If the pass rationality check passes, the invalid identification point is placed in the valid identification point database and the invalid identification point is changed to a valid identification point;

[0109] If the passage rationality check fails, the invalid identification point is corrected and put into the valid identification point database, and the corrected invalid identification point is changed to a valid identification point.

[0110] Furthermore, the device 500 for inspecting quality of landmarks in map elements further includes:

[0111] A differential deduplication module, configured to perform differential deduplication on the current identification point using the base map data;

[0112] an invalid identification point determining module, configured to determine that the current identification point is the invalid identification point if the current identification point fails the differential duplication elimination;

[0113] The effective identification point determination module is used to determine that the current identification point is the effective identification point if the differential deduplication is passed.

[0114] Furthermore, the effective identification point determination module is specifically used to:

[0115] If the differential deduplication is passed, the current identification point is determined to be a temporary valid identification point, and a data logic rationality check is performed on the temporary valid identification point according to a preset data logic rationality check principle;

[0116] If the data logic rationality check passes, determining the current identification point as the valid identification point;

[0117] If the data logic rationality check fails, the current identification point is determined to be the invalid identification point.

[0118] Furthermore, the device 500 for inspecting quality of landmarks in map elements further includes:

[0119] The successful operation association module is used to store the association relationship between the valid identification points in the valid identification point database and the internal operation results obtained based on the valid identification points in the valid identification point database.

[0120] The above-mentioned product can execute the identification point quality inspection method in the map elements provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0122] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0123] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0124] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0125] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0126] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for quality inspection of landmarks in map elements. For example, in some embodiments, the method for quality inspection of landmarks in map elements can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for quality inspection of landmarks in map elements described above can be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the method for quality inspection of landmarks in map elements in any other appropriate manner (eg, by means of firmware).

[0127] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0132] A computer system may include a client and a server. The client and server are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0133] Artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily encompass computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graphs.

[0134] Cloud computing refers to a technology system that provides network access to elastically scalable shared pools of physical or virtual resources. These resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on-demand in a self-service manner. Cloud computing technology provides efficient and powerful data processing capabilities for the application of technologies such as artificial intelligence and blockchain, as well as for model training.

[0135] In addition, according to an embodiment of the present disclosure, the present disclosure also provides another electronic device, another readable storage medium and another computer program product for executing one or more steps of the artificial intelligence method described in any embodiment of the present disclosure. The specific structure and program code thereof can be found in Figure 6 The description of the contents of the embodiment shown will not be repeated here.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved. This is not limited herein.

[0137] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for quality inspection of identification points in map elements, comprising: In response to the current identification point being a valid identification point, performing a passability rationality check on the valid identification point in combination with the map base map data; In response to the current identification point being an invalid identification point, if the number of original identification points in the original identification point database that have the same identification content as the invalid identification point meets a preset condition, the invalid identification point is recalled, wherein the same identification content means that the identified objects are the same and the coordinate position of the original identification point is within a set range around the invalid identification point; The process of checking the validity of the valid identification points in combination with the base map data includes: Confirm the type of the valid identification point; If the type of the valid identification point is to increase, the valid identification point is checked for passability rationality in combination with the map base map data; If the type of the valid identification point is deletion or modification, then in response to the data acquisition time of the valid identification point, which is later than the generation time of the map element corresponding to the valid identification point in the map base map, the valid identification point is checked for pass rationality in combination with the map base map data.

2. The method according to claim 1, wherein The method of checking the passability rationality of the valid identification points in combination with the map base map data includes: Comparing the valid identification point with the map base map data, and performing a pass rationality check on the valid identification point according to a pre-set pass rationality check principle; If the pass rationality check passes, the valid identification point is placed in the valid identification point database; If the passage rationality check fails, the valid identification point is corrected and placed in the valid identification point database.

3. The method according to claim 1, wherein The recalling of the invalid identification point includes: Performing a pass rationality check on the invalid identification point in combination with the map base map data; If the pass rationality check passes, the invalid identification point is placed in the valid identification point database and the invalid identification point is changed to a valid identification point; If the passage rationality check fails, the invalid identification point is corrected and put into the valid identification point database, and the corrected invalid identification point is changed to a valid identification point.

4. The method according to claim 1, further comprising: Using the map base map data to perform differential deduplication on the current identification point; If the differential duplication elimination fails, determining the current identification point as the invalid identification point; If the differential deduplication is passed, the current identification point is determined to be the valid identification point.

5. The method according to claim 4, wherein If the differential duplicate removal is successful, determining the current identification point as the valid identification point includes: If the differential deduplication is passed, the current identification point is determined to be a temporary valid identification point, and a data logic rationality check is performed on the temporary valid identification point according to a preset data logic rationality check principle; If the data logic rationality check passes, determining the current identification point as the valid identification point; If the data logic rationality check fails, the current identification point is determined to be the invalid identification point.

6. The method according to claim 2 or 3, further comprising: The effective identification points in the effective identification point database are stored, and the association relationship between the internal work results obtained based on the effective identification points in the effective identification point database is stored.

7. A device for quality inspection of identification points in map elements, comprising: A valid identification point verification module, configured to, in response to a current identification point being a valid identification point, confirm the type of the valid identification point; If the type of the valid identification point is addition, the valid identification point is checked for passability rationality in combination with the map base map data; if the type of the valid identification point is deletion or modification, the valid identification point is checked for passability rationality in combination with the map base map data in response to a data acquisition time of the valid identification point that is later than a generation time of a map element corresponding to the valid identification point in the map base map; An invalid identification point recall module is used to respond to the current identification point being an invalid identification point. If the number of original identification points in the original identification point database with the same identification content as the invalid identification point meets a preset condition, the invalid identification point will be recalled, wherein the same identification content means that the identified objects are the same, and the coordinate position of the original identification point is within a set range around the invalid identification point.

8. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for quality inspection of identification points in map elements according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method for quality inspection of identification points in map elements according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for quality inspection of marker points in map elements according to any one of claims 1 to 6.

Images