Batch processing strategy determination method, device, equipment, medium and program product

Abstract

The disclosure provides a method, device, equipment, medium and program product for determining a batch processing strategy, relates to the technical field of data processing, and particularly relates to the technical field of maps. A specific implementation solution is as follows: a first batch processing strategy to be processed is determined, the first batch processing strategy being used for batch processing of map data; a plurality of historical tasks are determined, the historical tasks including initial map data and target map data, the target map data being map data processed from the initial map data; a plurality of sample data are determined from the plurality of historical tasks according to the batch processing strategy, the sample data including sample initial map data and sample target map data, the sample target map data being map data processed from the sample initial map data; and the first batch processing strategy is verified and updated according to the plurality of sample data, so as to obtain a target batch processing strategy corresponding to the first batch processing strategy. Through the above process, the correctness of the batch processing strategy is ensured.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of map in data processing, and particularly relates to a batch processing strategy determination method and device, equipment, medium and program product. BACKGROUND

[0002] Map data updating refers to updating initial map data by using an update package to obtain target map data. Batch processing strategy refers to batch updating processing of initial map data based on an update package to obtain target map data.

[0003] In order to ensure the correctness of the target map data, the batch processing strategy needs to be verified first. SUMMARY

[0004] The present disclosure provides a batch processing strategy determination method, device, equipment, medium and program product.

[0005] According to a first aspect of the present disclosure, a batch processing strategy determination method is provided, comprising:

[0006] determining a first batch processing strategy to be processed, the first batch processing strategy being used for batch processing of map data;

[0007] determining a plurality of historical tasks, the historical tasks including initial map data and target map data, the target map data being map data processed from the initial map data;

[0008] determining a plurality of sample data from the plurality of historical tasks according to the first batch processing strategy, the sample data including sample initial map data and sample target map data, the sample target map data being map data processed from the sample initial map data;

[0009] performing verification processing and update processing on the first batch processing strategy according to the plurality of sample data to obtain a target batch processing strategy corresponding to the first batch processing strategy.

[0010] According to a second aspect of the present disclosure, a batch processing strategy determination device is provided, comprising:

[0011] a first determination module configured to determine a first batch processing strategy to be processed, the first batch processing strategy being used for batch processing of map data;

[0012] a second determination module configured to determine a plurality of historical tasks, the historical tasks including initial map data and target map data, the target map data being map data processed from the initial map data;

[0013] A third determining module is configured to determine, according to the first batch processing strategy, a plurality of sample data from the plurality of historical tasks, wherein the sample data comprises sample initial map data and sample target map data, and the sample target map data is map data processed from the sample initial map data.

[0014] A verification updating module is configured to perform verification processing and updating processing on the first batch processing strategy according to the plurality of sample data, to obtain a target batch processing strategy corresponding to the first batch processing strategy.

[0015] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory connected with the at least one processor in communication; wherein

[0018] The memory stores instructions executable 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 perform the method of any one of the first aspect.

[0019] According to a fourth 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 the computer to perform the method of any one of the first aspect.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program stored in a readable storage medium, and at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the electronic device to perform the method of the first aspect.

[0021] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0023] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of a batch processing strategy determination method provided by an embodiment of the present disclosure Figure 1 ;

[0025] Figure 3 A flowchart of a method for determining a batch processing strategy provided by an embodiment of the present disclosure Figure 2 ;

[0026] Figure 4 A flowchart of a method for determining a target historical task provided by an embodiment of the present disclosure

[0027] Figure 5 A flowchart of a method for determining a batch processing strategy provided by an embodiment of the present disclosure Figure 3 ;

[0028] Figure 6 A structural diagram of a device for determining a batch processing strategy provided by an embodiment of the present disclosure

[0029] Figure 7 A block diagram of an electronic device for implementing a method for determining a batch processing strategy provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Thus, those skilled in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0031] In order to facilitate understanding of the technical solutions of the present disclosure, first, the application scenario of the present disclosure is described in conjunction with Figure 1 The application scenario of the present disclosure is described in conjunction with

[0032] Figure 1 A structural diagram of an application scenario provided by an embodiment of the present disclosure. As shown in Figure 1 , the application scenario illustrates three stages, which are a batch processing strategy verification stage, a batch processing strategy pre-online stage, and a batch processing strategy publishing stage.

[0033] In the batch processing strategy verification stage, the test samples are selected from historical tasks. The historical tasks can be tasks after the online tasks are processed by batch processing, or tasks after the online tasks are processed by manual processing. Batch processing strategy verification refers to using the batch processing strategy to process the test samples by batch processing, and determining whether the batch processing strategy is correct according to the results after batch processing.

[0034] In the batch processing strategy pre-online stage, the batch processing strategy processes the online tasks by batch processing, and the results of batch processing need to be manually verified for correctness. The batch processing strategy used in the pre-online stage is the correct batch processing strategy determined by verification in the batch processing strategy verification stage.

[0035] In the batch release stage, the batch strategy is used to batch the tasks on line, and the batch result is directly returned to the database without inspection. The batch strategy used in the release stage is the batch strategy that has no problem in the batch strategy pre-online stage.

[0036] However, the test sample used in the existing batch strategy verification stage is artificially designed, and the artificially designed test sample is difficult to fully cover the real road scene, resulting in low correctness of the batch strategy verified in the existing batch strategy verification stage.

[0037] At the same time, the existing batch strategy verification stage is to verify the batch result manually, resulting in low efficiency of batch strategy verification.

[0038] On the other hand, since the artificially designed test sample cannot guarantee the correctness of the batch strategy, the existing batch strategy pre-online stage needs a long observation time, resulting in a long batch strategy observation period.

[0039] In view of the problems in the prior art, the present disclosure proposes the following technical concept: the batch strategy is verified by selecting test samples in historical tasks. Since the historical tasks cover all real road scenes, using historical tasks as test samples can guarantee the correctness of the batch strategy verified in the verification stage. Moreover, the historical tasks include the results after processing the test samples, which can directly compare the original results in the historical tasks with the results after processing by the batch strategy, improving the efficiency of batch strategy verification. On the other hand, since the correctness of the batch strategy obtained in the batch strategy verification stage is high, the observation time can be shortened in the batch strategy pre-online stage, and the batch strategy observation period is shortened.

[0040] On the basis of the above introduction, the determination method of the batch strategy provided by the present disclosure will be introduced in combination with specific embodiments. It should be pointed out that the execution subject of each embodiment in the present disclosure can be a server, or can also be a processor, a microprocessor or other devices with data processing function. The present embodiment does not limit the specific execution subject, as long as it is a device with data processing function.

[0041] Figure 2 Flowchart of a batch strategy determination method provided by an embodiment of the present disclosure Figure 1 As shown in FIG. 1, the method of the present embodiment comprises the following steps. Figure 2

[0042] S201, determine a first batch strategy to be processed, the first batch strategy is used for batch processing of map data.

[0043] ​The map data can be road network data, and data of traffic signs, speed limit conditions, electronic eyes, etc. The traffic signs can be traffic lights, left-turn signs, right-turn signs, straight-through signs, and U-turn signs, etc.

[0044] For example, the map data can be data of distribution of roads in a region, categories of roads, traffic signs of roads, speed limit conditions, and whether there are electronic eyes, etc.

[0045] In a possible implementation, for example, there are three roads in a region A, which are road 1, road 2, and road 3. The map data of the region A can include data of distribution of the three roads, number of lanes of the three roads, traffic signs of the three roads, speed limit conditions, and electronic eyes.

[0046] S202, a plurality of historical tasks are determined, the historical tasks including initial map data and target map data, the target map data being map data processed from the initial map data.

[0047] The historical task refers to a processed task.

[0048] For example, the historical task can be a batch-processed task, or a manually processed task.

[0049] Determining the plurality of historical tasks can be determining a plurality of processed tasks.

[0050] For example, assuming that there are 100 tasks, 50 of which have been batch-processed, and 10 of which have been manually processed, then 60 historical tasks can be determined from the 100 tasks.

[0051] In this embodiment, the tasks can be stored in different databases according to whether the tasks are processed.

[0052] For example, assuming that there are 100 unprocessed tasks and 100 historical tasks, the 100 unprocessed tasks are stored in a database 1, and the 100 historical tasks are stored in a database 2. After being processed, the unprocessed tasks in the database 1 can be moved to the database 2 for storage.

[0053] S203, a plurality of sample data are determined from the plurality of historical tasks according to a first batch processing strategy, the sample data including sample initial map data and sample target map data, the sample target map data being map data processed from the sample initial map data.

[0054] Different batch processing strategies process different map data, and the same map data can be processed by multiple batch processing strategies.

[0055] For example, it is assumed that there are two batch processing strategies, batch processing strategy A and batch processing strategy B, and five historical tasks, task 1, task 2, task 3, task 4 and task 5. Batch processing strategy A processes traffic sign data, and batch processing B processes electronic eye data. The map data in task 1 is electronic eye data, the map data in task 2 is map distribution data, the map data in task 3 is traffic sign data and electronic eye data, the data in task 4 is traffic sign data, and the map data in task 5 is speed limit data. According to batch processing strategy A, tasks 3 and 4 in the five historical tasks can be determined as sample data. According to batch processing strategy B, tasks 1 and 3 in the five historical tasks can be determined as sample data.

[0056] S204, verifying and updating the first batch processing strategy according to the plurality of sample data, to obtain a target batch processing strategy corresponding to the first batch processing strategy.

[0057] The first batch processing strategy is a batch processing strategy to be verified and determined to be correct.

[0058] The target batch processing strategy is a batch processing strategy that has been verified and is correct.

[0059] The verification process refers to verifying the batch processing result of the first batch processing strategy.

[0060] In one possible implementation, the verification process can compare the batch processing result of the first batch processing strategy with the sample target map data to determine whether the batch processing strategy is correct.

[0061] In another possible implementation, the verification process can compare the batch processing result of the first batch processing strategy with the result of manual processing to determine whether the batch processing strategy is correct.

[0062] The updating process refers to correcting the incorrect batch processing strategy.

[0063] In the embodiments of the present disclosure, the first batch processing strategy and the plurality of historical tasks are first determined, then the plurality of sample data are determined from the plurality of historical tasks according to the first batch processing strategy, and finally the first batch processing strategy is verified and updated according to the plurality of sample data, to obtain a target batch processing strategy corresponding to the first batch processing strategy. Based on the historical tasks, the batch processing strategy is verified and updated, which can improve the correctness of the batch processing strategy obtained in the verification stage. In addition, the batch processing strategy determination method provided in the embodiments can automatically determine sample data by a processor or the like, and automatically verify the first batch processing strategy, without the need for manual design of test samples and verification processing, thereby improving the efficiency of batch processing strategy verification.

[0064] To help readers gain a deeper understanding of the implementation principles of this disclosure, the following will be discussed in conjunction with... Figures 3 to 5 right Figure 2 The illustrated embodiments are further refined.

[0065] Figure 3 Flowchart of the batch processing strategy determination method provided in the embodiments of this disclosure Figure 2 .like Figure 3 As shown, the method in this embodiment includes:

[0066] S301. Determine the first batch of processing strategies to be processed. The first batch of processing strategies is used to process map data in batches.

[0067] The execution process of S301 can be found in the execution process of S201, and will not be repeated here.

[0068] S302. Identify multiple historical tasks, including initial map data and target map data. The target map data is the map data after processing the initial map data.

[0069] The execution process of S302 can be found in the execution process of S202, and will not be repeated here.

[0070] S303. Determine the map data category corresponding to the first batch processing strategy. The first batch processing strategy is used to process the map data corresponding to the map data category in batches.

[0071] Map data categories can be categories that reflect road information, such as road distribution, traffic signs, speed limits, and speed cameras.

[0072] The map data category corresponding to the batch processing strategy can be any map data category that the batch processing strategy can process.

[0073] S304. Based on the map data category, determine the target historical task among multiple historical tasks. The category of map data included in the target historical task is the map data category.

[0074] To facilitate understanding, the following will be combined with... Figure 4 The process of identifying the target historical task among multiple historical tasks is explained.

[0075] Figure 4 This is a schematic diagram illustrating the historical task of determining a target, as provided in an embodiment of this disclosure. Figure 4 As shown, suppose there are currently 5 historical tasks in the historical tasks list, namely... Figure 4 The historical tasks shown are 1, 2, 3, 4, and 5. (As shown...) Figure 4As shown, in the historical tasks, the category of the map data in historical task 1, historical task 3 and historical task 5 is A, and the category of the map data in historical task 2 and historical task 4 is B. Based on Figure 4 As shown in the historical tasks and the category of the map data in the historical tasks, it can be determined that the target historical tasks when the category of the map data corresponding to the first batch processing strategy is A are historical task 1, historical task 3 and historical task 5.

[0076] S305, determining a plurality of sample data according to the target historical task.

[0077] The historical task includes initial map data and target map data. For any target historical task, the initial map data in the target historical task is determined as sample initial map data in the sample data, and the target map data in the target historical task is determined as sample target map data.

[0078] For example, the target historical task 1 includes the initial map data 1 and the target map data 1, and the initial map data 1 can be determined as the sample initial map data 1, and the target map data 1 can be determined as the sample target map data 1.

[0079] In a possible implementation, the target historical task can include an update package, the target map data is obtained by updating the initial map data through the update package; the sample data includes a sample update package, and the sample target map data is obtained by updating the sample initial map data through the sample update package.

[0080] The update package can be update information of the initial map data. The update information can be an update of road distribution, an update of traffic signs, or an update of electronic eyes, speed limits, etc.

[0081] For example, it is assumed that the initial map data includes speed limit data of 3 roads, i.e., the speed limit of the first section of road 1 is 40 kilometers per hour, the speed limit of the second section of road 1 is 30 kilometers per hour, the speed limit of road 2 is 60 kilometers per hour, and the speed limit of road 3 is 80 kilometers per hour. The data in the update package can be that the speed limit of the first section of road 1 is adjusted to 30 kilometers per hour. Then, the target map data updated according to the update package is that the speed limit of road 1 is 30 kilometers per hour, the speed limit of road 2 is 60 kilometers per hour, and the speed limit of road 3 is 80 kilometers per hour.

[0082] S306, initializing i to 1.

[0083] i is a positive integer.

[0084] S307, performing batch processing on the sample initial map data in the i th sample data through the first batch processing strategy to obtain verification map data.

[0085] The sample initial map data includes a plurality of road data, and the batch processing is processing all the road data.

[0086] For example, assuming that the sample initial map data includes data of 100 roads, the batch processing refers to processing the data of the 100 roads simultaneously according to a first batch processing strategy to obtain the verification map data.

[0087] S308, obtaining difference information between the sample target map data in the i th sample data and the verification map data.

[0088] The difference information can be a field-level difference.

[0089] In a possible implementation, the sample target map data is "Road 1 speed limit 30 kilometers per hour", the verification map data is "Road 1 first segment speed limit 30 kilometers per hour, Road 1 second segment speed limit 30 kilometers per hour", and the difference between the two is "first segment speed limit 30 kilometers per hour, Road 1 second segment".

[0090] In another possible implementation, the sample target map data is "Road 1 meets Road 2 at longitude 100°10′10″ and latitude 100°10′10″", and the verification map data is "Road 1 meets Road 2 at longitude 100°10′12″ and latitude 100°10′10″", and the difference between the two is "longitude difference 1″".

[0091] S309, judging whether the difference information indicates that the sample target map data and the verification map data are the same.

[0092] If yes, it is determined that the i th verification result is verification success, and S312 is performed.

[0093] If no, S310 is performed.

[0094] When the difference information is meaningless, it can be considered that the sample target map data and the verification map data are the same.

[0095] For example, when the difference information of the sample target map data and the verification map data is a particle such as "liao", it is considered that the sample target map data and the verification map data are the same. If the difference information of the sample target map data and the verification map data is a real difference such as distance deviation, it is considered that the sample target map data and the verification map data are different.

[0096] S310, obtaining a difference category of the difference information, and judging whether the difference category is a preset category.

[0097] If yes, it is determined that the i th verification result is verification success, and S312 is performed.

[0098] If no, it is determined that the i-th verification result is a verification failure, and S311 is performed.

[0099] The category of the difference can be a small distance difference category, a large distance difference category, an electronic eye difference category, a traffic sign difference category, etc. The small distance difference category refers to a difference within a distance deviation range, which can be a preset category.

[0100] For example, assuming that the preset category is a category in which the road length difference is less than 1%, if the sample target map data is “road 1 is 100 meters long”, and the verification map data is “road 1 is 99.5 meters long”, the difference information of the two is “the length of road 1 differs by 0.5 meters”, it can be determined that the difference information of the two is the preset category, that is, the difference between the sample target map data and the verification map data is within the deviation range, and can be regarded as no difference.

[0101] S311, update the first batch processing strategy, set i to 1, and perform S307.

[0102] The update processing refers to the correction of the first batch processing strategy.

[0103] S312, i=i+1.

[0104] S313, determine whether i is greater than M.

[0105] M is the number of multiple sample data, and M is an integer greater than 1.

[0106] If yes, S314 is performed.

[0107] If no, S307 is performed.

[0108] S314, the first batch processing strategy is determined as the target batch processing strategy.

[0109] In the embodiment of the present disclosure, the first batch processing strategy and the plurality of historical tasks are determined; the target historical task is determined from the plurality of historical tasks according to the map data category corresponding to the first batch processing strategy; the plurality of sample data are determined according to the target historical task; the sample initial map data in the i th sample data is batch processed through the first batch processing strategy to obtain verification map data; the difference information between the sample target map data and the verification map data in the i th sample data is obtained; it is determined whether the difference information indicates that the sample target map data and the verification map data are the same, if yes, it is determined that the i th verification result is verification success; if not, the difference category of the difference information is obtained, when the difference category is a preset category, it is determined that the i th verification result is verification success, when the difference category is not the preset category, it is determined that the i th verification result is verification failure; if the i th verification result is verification success, i is increased by 1, and the verification step is executed until i is M, the first batch processing strategy is determined as the target batch processing strategy; if the i th verification result is verification failure, the first batch processing strategy is updated, i is set to 1, and the verification step is executed. The differences between the batch processing results and the historical processing results can be automatically compared by the comparator and the like, and at the same time, part of the differences can be automatically filtered by the filter and the like, without manual comparison and difference filtering, the correctness of the batch processing strategy can be quickly judged, and the efficiency of the batch processing strategy verification stage is improved.

[0110] Figures 2-4 The embodiment shown illustrates the determination method of the batch processing strategy in the batch processing strategy verification stage. Figures 2-4 On the basis of the embodiment shown in the embodiment, the determination method of the batch processing strategy in the batch processing strategy pre-online stage is described in detail. Figure 5 The embodiment shown illustrates the determination method of the batch processing strategy in the batch processing strategy pre-online stage.

[0111] Figure 5 The flowchart of the determination method of the batch processing strategy provided by the embodiment of the present disclosure is shown in Figure 3 . Please refer to Figure 5 , the embodiment method comprises:

[0112] S501, a plurality of online tasks are obtained in an online task database, and the online tasks comprise to-be-processed map data.

[0113] After the online task is processed, it becomes a historical task.

[0114] S502, the to-be-processed map data in the plurality of online tasks is batch processed through the target batch processing strategy to obtain a plurality of online target map data.

[0115] The online task can comprise to-be-processed map data and an update package.

[0116] In a possible implementation, the online task batch processing refers to batch processing, based on an update package, of to-be-processed map data in a plurality of online tasks by a target batch processing strategy to obtain a plurality of online target map data.

[0117] S503, obtaining a plurality of artificial annotation results corresponding to the plurality of online target map data in a preset period.

[0118] The artificial annotation result indicates whether the online target map data is correct. That is, after the batch processing ends, whether the target map data is correct is manually verified, and the online target map data is manually annotated. If it is wrong, the online target map data is modified to be correct.

[0119] The preset period can be adjusted according to actual conditions.

[0120] In a possible implementation, the preset period can be adjusted according to the number of people participating in manual verification. If the number of people participating in manual verification is large, the preset period can be set to be short. If the number of people participating in manual verification is small, the preset period can be set to be long.

[0121] For example, the preset period can be 7 days or 30 days.

[0122] S504, if the plurality of artificial annotation results in the preset period all indicate that the online target map data is correct, it is determined that the verification result of the target batch processing strategy is that the target batch processing strategy is verified successfully.

[0123] The target batch processing strategy that is verified successfully can be directly released.

[0124] S505, if there is an artificial annotation result indicating that the online target map data is incorrect in the plurality of artificial annotation results in the preset period, it is determined that the verification result of the target batch processing strategy is that the target batch processing strategy is verified unsuccessfully.

[0125] For example, there are 1000 artificial annotation results in the preset period, and one artificial annotation result indicates that the online map data is incorrect. It is determined that the verification result of the target batch processing strategy is that the target batch processing strategy is verified unsuccessfully.

[0126] For the target batch processing strategy that is verified unsuccessfully, the target batch processing strategy needs to be updated and processed, and the updated batch processing strategy is returned to the batch processing strategy verification stage for re-verification.

[0127] In the embodiment of the present disclosure, a plurality of online tasks are obtained in an online task database, and the online tasks include to-be-processed map data; the to-be-processed map data in the plurality of online tasks is processed in batches through a target batch processing strategy to obtain a plurality of online target map data; a plurality of artificial labeling results corresponding to the plurality of online target map data in a preset period are obtained, and if the plurality of artificial labeling results in the preset period all indicate that the online target map data is correct, it is determined that the verification result of the target batch processing strategy is that the target batch processing strategy is verified successfully; if there is an artificial labeling result in the plurality of artificial labeling results in the preset period indicating that the online target map data is incorrect, it is determined that the verification result of the target batch processing strategy is that the target batch processing strategy is verified unsuccessfully. Since the batch processing strategy verification result can guarantee the correctness of the batch processing strategy, the observation time can be shortened in the batch processing strategy pre-online stage. On the other hand, the artificial inspection of the batch processing result can be increased in the batch processing strategy pre-online stage, and compared with the artificial sampling inspection of the batch processing result, the embodiment can guarantee the correctness of the batch processing strategy.

[0128] Figure 6 A structure diagram of a batch processing strategy determination apparatus provided by the embodiment of the present disclosure is shown in FIG. 6. As shown in FIG. 6, the batch processing strategy determination apparatus 600 of the embodiment includes a first determination module 601, a second determination module 602, a third determination module 603, and a verification and update module 604. Among them, Figure 6 The first determination module 601 is configured to determine a to-be-processed first batch processing strategy, and the first batch processing strategy is used for batch processing of map data.

[0129] The second determination module 602 is configured to determine a plurality of historical tasks, and the historical tasks include initial map data and target map data, and the target map data is map data processed from the initial map data.

[0130] The third determination module 603 is configured to determine a plurality of sample data in the plurality of historical tasks according to the first batch processing strategy, and the sample data includes sample initial map data and sample target map data, and the sample target map data is map data processed from the sample initial map data.

[0131] The verification and update module 604 is configured to perform verification processing and update processing on the first batch processing strategy according to the plurality of sample data to obtain a target batch processing strategy corresponding to the first batch processing strategy.

[0132] In a possible implementation manner, the third determination module 603 includes:

[0133]

[0134] ​The first determining unit is configured to determine a map data category corresponding to the first batch processing strategy, and the first batch processing strategy is used to batch process map data corresponding to the map data category.

[0135] The second determining unit is configured to determine the plurality of sample data according to the map data category and the plurality of historical tasks.

[0136] In a possible implementation, the second determining unit includes:

[0137] The first determining sub-unit is configured to determine a target historical task according to the map data category and the plurality of historical tasks, and the target historical task includes map data of the map data category;

[0138] The second determining sub-unit is configured to determine the plurality of sample data according to the target historical task.

[0139] In a possible implementation, the second determining sub-unit is specifically configured to:

[0140] For any target historical task, initial map data in the target historical task is determined as sample initial map data in the sample data, and

[0141] Target map data in the target historical task is determined as sample target map data.

[0142] In a possible implementation, the second determining sub-unit is specifically configured to:

[0143] The target historical task includes an update package, and the target map data is obtained by updating the initial map data by using the update package;

[0144] The sample data includes sample update package, and the sample target map data is obtained by updating the sample initial map data by using the sample update package.

[0145] In a possible implementation, the verification updating module 604 is specifically configured to:

[0146] The first batch processing strategy is verified by using the plurality of sample data to obtain a verification result; when the verification result is a verification failure, the first batch processing strategy is updated until a verification result of an updated first batch processing strategy is a verification success, and the updated first batch processing strategy is determined as the target batch processing strategy.

[0147] In a possible implementation, the verification updating module 604 includes:

[0148] a verification unit, configured to perform verification processing on the first batch processing strategy by using the i th sample data, to obtain an i th verification result, and initially, the i is 1; if the i th verification result is verification success, the i is increased by 1, and the verification step is performed until the i is greater than M, the first batch processing strategy is determined as the target batch processing strategy, the M is the number of the plurality of sample data, the M is an integer greater than 1, and the i is a positive integer;

[0149] an updating unit, configured to perform updating processing on the first batch processing strategy if the i th verification result is verification failure, set the i to 1, and return to the verification unit.

[0150] In a possible implementation, the verification unit comprises:

[0151] a batch processing sub-unit, configured to perform batch processing on sample initial map data in the i th sample data by using the first batch processing strategy, to obtain verification map data;

[0152] an obtaining sub-unit, configured to obtain difference information between sample target map data in the i th sample data and the verification map data;

[0153] a determining sub-unit, configured to determine the i th verification result according to the difference information.

[0154] In a possible implementation, the determining sub-unit is specifically configured to:

[0155] determine whether the difference information indicates that the sample target map data and the verification map data are the same;

[0156] if yes, determine that the i th verification result is verification success;

[0157] if no, obtain a difference category of the difference information, when the difference category is a preset category, determine that the i th verification result is verification success, and when the difference category is not the preset category, determine that the i th verification result is verification failure.

[0158] In a possible implementation, the verification updating module 604 further comprises:

[0159] an obtaining module, configured to obtain a plurality of online tasks in an online task database, and the online tasks comprise to-be-processed map data;

[0160] a batch processing module, configured to perform batch processing on the to-be-processed map data in the plurality of online tasks by using a target batch processing strategy, to obtain a plurality of online target map data;

[0161] The fourth determination module is configured to obtain a plurality of artificial labeling results corresponding to the plurality of online target map data, and determine a verification result of the target batch processing strategy according to the plurality of artificial labeling results.

[0162] In a possible implementation, the fourth determination module comprises:

[0163] The first determination unit is configured to determine that the verification result of the target batch processing strategy is that the target batch processing strategy is verified successful, if the plurality of artificial labeling results all indicate that the online target map data is correct.

[0164] The second determination unit is configured to determine that the verification result of the target batch processing strategy is that the target batch processing strategy is verified failed, if there is an artificial labeling result in the plurality of artificial labeling results indicating that the online target map data is incorrect.

[0165] The determination apparatus for a batch processing strategy provided in this embodiment can execute the processing method of a three-dimensional model in a map provided in any of the method embodiments, and has similar implementation principles and technical effects, which will not be described here in detail.

[0166] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0167] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0168] According to the embodiments of the present disclosure, the present disclosure further provides a computer program product, which comprises a computer program stored in a readable storage medium, and at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to make the electronic device execute the scheme provided in any of the embodiments.

[0169] Figure 7 A schematic block diagram of an example electronic device 700 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 laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0170] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0171] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0172] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 701 performs the various methods and processes described above, such as the batch processing strategy determination method. For example, in some embodiments, the batch processing strategy determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on device 700 via ROM 802 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the batch processing strategy determination method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the batch processing strategy determination method by any other suitable means (e.g., by means of firmware).

[0173] This disclosure provides a method, apparatus, device, medium, and program product for determining batch processing strategies, which are applied in the field of map technology in data processing to ensure the correctness of batch processing strategies.

[0174] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0175] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0176] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The 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, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical conductors, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0177] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0178] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, 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), and the Internet.

[0179] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, or VPS for short) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0180] It should be understood that various forms of flow shown above can be used with reordering, additions, or removals of steps. For example, steps recited in the present disclosure can be executed in parallel, in serial, or in different orders, as long as the desired results of the technology disclosed in the present disclosure are achieved, which are not limited herein.

[0181] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A method for determining a batch processing strategy, comprising: Determine the first batch of processing strategies to be processed, which are used for batch processing of map data; Multiple historical tasks are identified, including initial map data and target map data, wherein the target map data is map data processed from the initial map data; According to the first batch of processing strategies, multiple sample data are determined in the multiple historical tasks. The sample data includes initial sample map data and target sample map data. The target sample map data is the map data after processing the initial sample map data. The first batch processing strategy is verified and updated based on the multiple sample data to obtain the target batch processing strategy corresponding to the first batch processing strategy.

2. The method according to claim 1, wherein, Based on the first batch of processing strategies, multiple sample data are identified from the multiple historical tasks, including: The map data category corresponding to the first batch of processing strategies is determined, and the first batch of processing strategies is used to perform batch processing on the map data corresponding to the map data category. Based on the map data category, the plurality of sample data are determined from the plurality of historical tasks.

3. The method according to claim 2, wherein, Based on the map data category, the plurality of sample data are determined from the plurality of historical tasks, including: Based on the map data category, a target historical task is determined among the plurality of historical tasks, wherein the category of map data included in the target historical task is the map data category; The multiple sample data are determined based on the target historical task.

4. The method according to claim 3, wherein, The multiple sample data determined based on the target historical task include: For any given target historical task, the initial map data in the target historical task is determined as the sample initial map data in the sample data, and, The target map data in the target historical task is determined as the sample target map data.

5. The method according to claim 4, wherein, The target historical task includes an update package, and the target map data is obtained by updating the initial map data through the update package. The sample data includes a sample update package, and the sample target map data is obtained by updating the initial sample map data through the sample update package.

6. The method according to any one of claims 1-5, wherein, The first batch processing strategy is validated and updated based on the multiple sample data to obtain the target batch processing strategy corresponding to the first batch processing strategy, including: The first batch processing strategy is verified using the multiple sample data to obtain a verification result; if the verification result is a verification failure, the first batch processing strategy is updated until the verification result of the updated first batch processing strategy is a verification success, at which point the updated first batch processing strategy is determined as the target batch processing strategy.

7. The method according to claim 6, wherein, The first batch processing strategy is validated using the multiple sample data to obtain a validation result; if the validation result is a validation failure, the first batch processing strategy is updated until the validation result of the updated first batch processing strategy is a validation success, at which point the updated first batch processing strategy is determined as the target batch processing strategy, including: The verification step includes: verifying the first batch of processing strategies using the i-th sample data to obtain the i-th verification result, where i is initially 1; If the i-th verification result is successful, then i is incremented by 1, and the verification step is executed until i is greater than M. Then, the first batch processing strategy is determined as the target batch processing strategy, where M is the number of the multiple sample data, M is an integer greater than 1, and i is a positive integer. If the i-th verification result is a verification failure, then the first batch processing strategy is updated by setting i to 1 and executing the verification step.

8. The method according to claim 7, wherein, The first batch of processing strategies is verified using the i-th map data to obtain the i-th verification result, including: Using the first batch processing strategy, the initial map data of the sample in the i-th sample data is processed in batches to obtain the verification map data. Obtain the sample target map data in the i-th sample data and the difference information between it and the verification map data; Based on the difference information, the i-th verification result is determined.

9. The method according to claim 8, wherein, Based on the difference information, the i-th verification result is determined, including: Determine whether the difference information indicates that the sample target map data and the verification map data are the same; If so, then the i-th verification result is determined to be a successful verification; If not, the difference category of the difference information is obtained. If the difference category is a preset category, the i-th verification result is determined to be a successful verification. If the difference category is not the preset category, the i-th verification result is determined to be a failed verification.

10. The method according to any one of claims 1-5 and 7-9, wherein, After verifying and updating the first batch processing strategy based on the multiple sample data to obtain the target batch processing strategy corresponding to the first batch processing strategy, the process further includes: Retrieve multiple online tasks from the online task database, the online tasks including map data to be processed; The target batch processing strategy is used to process the map data to be processed in the multiple online tasks in batches to obtain multiple online target map data. Obtain multiple manual annotation results corresponding to the multiple online target map data within a preset period, and determine the verification result of the target batch processing strategy based on the multiple manual annotation results.

11. The method according to claim 10, wherein, Based on the multiple manually labeled results, the verification results of the target batch processing strategy are determined, including: If all the manual annotation results within the preset period indicate that the online target map data is correct, then the verification result of the target batch processing strategy is determined to be: the target batch processing strategy has been successfully verified. If, within a preset period, one of the multiple manually labeled results indicates an error in the online target map data, then the verification result of the target batch processing strategy is determined to be: the verification of the target batch processing strategy fails.

12. A batch processing strategy determination apparatus, comprising: The first determining module is used to determine the first batch of processing strategies to be processed, wherein the first batch of processing strategies is used for batch processing of map data; The second determining module is used to determine multiple historical tasks, the historical tasks including initial map data and target map data, the target map data being map data processed from the initial map data; The third determining module is used to determine multiple sample data in the multiple historical tasks according to the first batch processing strategy. The sample data includes sample initial map data and sample target map data. The sample target map data is map data after processing the sample initial map data. The verification and update module is used to verify and update the first batch processing strategy based on the multiple sample data to obtain the target batch processing strategy corresponding to the first batch processing strategy.

13. The apparatus according to claim 12, wherein, The third determining module includes: The first determining unit is used to determine the map data category corresponding to the first batch processing strategy, wherein the first batch processing strategy is used to perform batch processing on the map data corresponding to the map data category. The second determining unit determines the plurality of sample data from the plurality of historical tasks based on the map data category.

14. The apparatus according to claim 13, wherein, The second determining unit includes: The first determining subunit is used to determine a target historical task among the plurality of historical tasks according to the map data category, wherein the category of map data included in the target historical task is the map data category; The second determining subunit is used to determine the plurality of sample data based on the target historical task.

15. The apparatus according to claim 14, wherein, The second determining subunit is specifically used for: For any given target historical task, the initial map data in the target historical task is determined as the sample initial map data in the sample data, and, The target map data in the target historical task is determined as the sample target map data.

16. The apparatus according to claim 15, wherein, The second determining subunit is specifically used for: The target historical task includes an update package, and the target map data is obtained by updating the initial map data through the update package. The sample data includes a sample update package, and the sample target map data is obtained by updating the initial sample map data through the sample update package.

17. The apparatus according to any one of claims 12-16, wherein, The verification update module is specifically used for: The first batch processing strategy is verified using the multiple sample data to obtain a verification result; if the verification result is a verification failure, the first batch processing strategy is updated until the verification result of the updated first batch processing strategy is a verification success, at which point the updated first batch processing strategy is determined as the target batch processing strategy.

18. The apparatus according to claim 17, wherein, The verification update module includes: A verification unit is used to execute verification steps, which include: verifying the first batch processing strategy using the i-th sample data to obtain the i-th verification result, where i is initially 1; if the i-th verification result is successful, then incrementing i by 1 and executing the verification steps until i is greater than M, at which point the first batch processing strategy is determined as the target batch processing strategy, where M is the number of the plurality of sample data, M is an integer greater than 1, and i is a positive integer; An update unit is used to update the first batch processing strategy if the i-th verification result is a verification failure, setting i to 1 and returning to the verification unit.

19. The apparatus according to claim 18, wherein, The verification unit includes: The batch processing subunit is used to perform batch processing on the initial map data of the i-th sample data using the first batch processing strategy to obtain the verification map data. The acquisition subunit is used to acquire the sample target map data in the i-th sample data and the difference information between it and the verification map data; A subunit is defined to determine the i-th verification result based on the difference information.

20. The apparatus according to claim 19, wherein, The determining subunit is specifically used for: Determine whether the difference information indicates that the sample target map data and the verification map data are the same; If so, then the i-th verification result is determined to be a successful verification; If not, the difference category of the difference information is obtained. If the difference category is a preset category, the i-th verification result is determined to be a successful verification. If the difference category is not the preset category, the i-th verification result is determined to be a failed verification.

21. The apparatus according to any one of claims 12-16, 18-20, wherein, Following the verification update module, the system also includes: The acquisition module is used to acquire multiple online tasks from an online task database, including map data to be processed. The batch processing module is used to process the map data to be processed in the multiple online tasks in batches according to the target batch processing strategy, so as to obtain multiple online target map data. The fourth determining module is used to obtain multiple manual annotation results corresponding to the multiple online target map data within a preset period, and determine the verification result of the target batch processing strategy based on the multiple manual annotation results.

22. The apparatus according to claim 21, wherein, The fourth determining module includes: The first determining unit is configured to determine the verification result of the target batch processing strategy as follows: the target batch processing strategy is successfully verified if all of the multiple manual annotation results within a preset period indicate that the online target map data is correct. The second determining unit determines the target batch processing strategy verification result as follows: verification of the target batch processing strategy fails if, within a preset period, one of the multiple manual annotation results indicates that the online target map data is incorrect.

23. 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 to enable the at least one processor to perform the method of any one of claims 1-11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

25. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-11.

Images