Map data processing method, device, equipment and storage medium

Abstract

The present disclosure provides a map data operation method, device and equipment and a storage medium, relates to the technical field of data processing, in particular to the technical field of electronic map, automatic driving and the like. The map data operation method comprises: performing a screenshot operation on map data operated by an operator to obtain a screenshot picture of the map data; obtaining a detection result of the map data based on the screenshot picture, the detection result being used to indicate whether there is error data in the map data; performing correction processing on the error data until there is no error data in the map data; and taking the map data without error data as the map data operated by the operator. The present disclosure can improve the accuracy and production efficiency of map data.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, specifically to the fields of electronic maps, autonomous driving, etc., and particularly to a method, apparatus, device, and storage medium for processing map data. Background Technology

[0002] With the development of information technology, electronic maps have gradually become a frequently used tool. To ensure the accuracy of electronic maps, the quality of map data is particularly important.

[0003] The process of creating map data generally involves several stages: work by operators, inspection by quality control personnel, and acceptance by acceptance personnel. For unqualified map data, these stages will be repeated. Therefore, the entire production process often involves multiple "work-quality control-acceptance" stages. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for operating map data.

[0005] According to one aspect of this disclosure, a method for working with map data is provided, comprising: taking a screenshot of the map data being worked on by a worker to obtain a screenshot image of the map data; obtaining a detection result of the map data based on the screenshot image, the detection result being used to indicate whether there is erroneous data in the map data; correcting the erroneous data until there is no erroneous data in the map data; and using the map data without erroneous data as the map data completed by the worker.

[0006] According to another aspect of this disclosure, a map data processing apparatus is provided, comprising: a screenshot module for taking screenshots of map data processed by workers to obtain screenshot images of the map data; an acquisition module for acquiring detection results of the map data based on the screenshot images, the detection results indicating whether erroneous data exists in the map data; a correction module for correcting the erroneous data until no erroneous data exists in the map data; and a generation module for using the map data without erroneous data as the map data completed by the workers.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein the memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the method as described in any of the foregoing aspects.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to any of the preceding aspects.

[0009] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any of the preceding aspects.

[0010] According to the technical solution disclosed herein, the accuracy and production efficiency of map data can be improved.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0014] Figure 2 This is a comparative diagram of application scenarios and related technologies corresponding to the embodiments of this disclosure;

[0015] Figure 3 This is a schematic diagram according to the second embodiment of the present disclosure;

[0016] Figure 4 This is a schematic diagram according to the third embodiment of the present disclosure;

[0017] Figure 5 This is a schematic diagram of the data collection and training process according to an embodiment of this disclosure;

[0018] Figure 6 This is a schematic diagram of the training process of the detection model according to the embodiments of this disclosure;

[0019] Figure 7 This is a schematic diagram according to the fourth embodiment of the present disclosure.

[0020] Figure 8 This is a schematic diagram of an electronic device used to implement the map data operation method of the embodiments of this disclosure. Detailed Implementation

[0021] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0022] In related technologies, the process typically includes three stages: "operation-quality inspection-acceptance," with quality inspection and acceptance both performed manually. Because it is done manually, there are problems with efficiency, accuracy, and labor costs.

[0023] To improve the accuracy and efficiency of map data production, this disclosure provides the following embodiments.

[0024] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure, which provides a method for processing map data. For example... Figure 1 As shown, the map data processing method provided in this embodiment includes:

[0025] 101. Take a screenshot of the map data used by the workers to obtain a screenshot of the map data.

[0026] 102. Based on the screenshot, obtain the detection result of the map data, and the detection result is used to indicate whether there is erroneous data in the map data.

[0027] 103. Correct the erroneous data until there is no erroneous data in the map data.

[0028] 104. Use the map data that does not contain erroneous data as the map data for the completion of the operation by the operator.

[0029] Among them, operators can use operation tools to work on map data. These operation tools are generally specialized software tools for creating map base maps.

[0030] Accordingly, this embodiment can be specifically executed by a work tool.

[0031] In related technologies, after operators use tools to work on map data, they upload the completed map data to the map data creation server. Quality inspectors download or browse the map data processed by the operators from the map data creation server. If errors are found, the quality inspectors upload the error information to the map data creation server. After obtaining the error information from the map data creation server, the operators correct the erroneous map data based on the error information. The acceptance personnel follow a similar workflow to the quality inspectors.

[0032] As can be seen from the above process, the map data production process in related technologies includes three stages: "operation-quality inspection-acceptance". Both quality inspection and acceptance are done manually, which may result in problems such as poor accuracy and low efficiency.

[0033] In this embodiment, during the operation, erroneous data in the map data is corrected, and map data without errors is used as the map data completed by the operators. The entire process no longer includes the three stages of "operation-quality inspection-acceptance," but only the "operation" stage, thus saving steps and improving production efficiency. Furthermore, the operation stage allows for the inspection and correction of errors in the map data processed by the operators, improving the accuracy of the operation data.

[0034] To better understand the embodiments of this disclosure, the application scenarios of these embodiments are described. These embodiments can be applied to the process of creating map data for electronic maps.

[0035] like Figure 2 As shown above, the map creation process in related technologies generally includes three stages: "operation - quality inspection - acceptance." After operators use the tools to work on the map data, they upload the completed map data to the map data creation server. Quality inspectors download or browse the map data created by the operators from the map data creation server, and if errors are found, they upload the error information to the map data creation server. After receiving the error information from the map data creation server, the operators correct the erroneous map data based on the error information. The acceptance process is similar to that of the quality inspectors.

[0036] In this embodiment, such as Figure 2 As shown below, the map data creation process consists of only the "task" stage. After the operators work on the map data using the tools, the processed map data can be sent to the map data inspection server. The map data inspection server can inspect the map data and provide feedback to the operators. Based on the inspection results, the operators correct the erroneous data and repeat the above process until there is no erroneous data in the map data. The map data without erroneous data is then uploaded to the map data creation server.

[0037] like Figure 3 As shown, specifically, workers can use tools to perform tasks, which can specifically refer to drawing map elements. Map elements can also be called map features, production factors, etc. Map elements include, for example, road lines, speed limit signs, and traffic guidance signs (straight ahead signs, left turn signs, etc.).

[0038] The task management tool can take screenshots of the map data worked on by the workers to obtain screenshot images. Specifically, the tool can take screenshots based on pre-configured trigger events. These trigger events could be: the worker drawing a preset number of map elements (e.g., 10); or the worker completing all tasks (e.g., clicking a confirmation button or uploading the task after completion); or the worker actively initiating the trigger event (e.g., clicking a detection button on the tool).

[0039] When taking a screenshot using the assignment tool, you can capture an image of a set size, such as 100*100, which means both the height and width are 100 pixels.

[0040] After obtaining a screenshot of the map data, the task tool can read the pixel values ​​of each pixel in the screenshot and form a vector, which can be called a pixel value vector. For example, if the screenshot is 100*100 pixels, the pixel value vector has a dimension of 1*10000, and each element of the vector is the pixel value of each pixel in the screenshot. Pixel values ​​can be grayscale values. It's also understandable that pixel values ​​can use RGB values.

[0041] like Figure 3 As shown, the process of obtaining pixel value vectors from screenshot images can be called quantization. The quantized pixel value vectors can be sent to the map data detection server, specifically through an Application Programming Interface (API). Figure 3 In Chinese, this is represented by the intelligent detection API. The map data detection server can pre-train a detection model. The detection model is a deep learning model. The input of the detection model is a pixel value vector, and the output is the detection result. The detection result can be specifically the error confidence score, which is the probability value that the map data corresponding to the pixel value vector is erroneous data. The higher the error confidence score, the higher the probability that the corresponding map data is erroneous.

[0042] The map data detection server can send the detection results back to the operation tool via API. The operation tool can then display error messages on the operation interface, allowing operators to correct the errors based on these messages.

[0043] This process (job-correction) can be repeated multiple times until there are no erroneous data in the map data used by the operators. After that, the operators can upload the map data without erroneous data to the map data production server.

[0044] In conjunction with the above application scenarios, this disclosure also provides a method for creating electronic map data.

[0045] Figure 4 This is a schematic diagram based on the third embodiment of the present disclosure, which provides a method for processing map data.

[0046] like Figure 4 As shown, the map data processing method provided in this embodiment includes:

[0047] 401. Work tools: Take screenshots of the map data used by the workers to obtain screenshot images of the map data.

[0048] Among them, operators can use work tools to carry out their work. The map data used by operators can specifically refer to map elements drawn on the work interface. Map elements include, for example, road lines, speed limit signs, traffic guidance signs, etc.

[0049] Specifically, the center point of the map element can be used as the center point of the screenshot image, and a screenshot image of a preset size can be taken as the screenshot image of the map element.

[0050] This could involve the operator drawing a preset number of map elements and then taking a screenshot of each of those elements, or it could involve the operator drawing all the map elements and then taking a screenshot of each of them.

[0051] In this embodiment, by using the center point of the map element as the center point of the screenshot image and taking a screenshot image of a preset size, the standardization of the screenshot image can be achieved, thereby improving the reliability of error data detection.

[0052] 402. The task tool obtains the pixel value data corresponding to the screenshot image.

[0053] Specifically, it can read the pixel value of each pixel in the screenshot image. The pixel value can be a grayscale value, and the vector composed of these grayscale values ​​can be called pixel value data. For example, if the screenshot image size is 100*100 pixels, then the pixel value data can be a 1*10000 vector, where each element of the vector is the grayscale value of each pixel.

[0054] 403. The operation tool sends the pixel value data to the map data detection server.

[0055] The task tool can be pre-configured with an API for the map data detection server, through which pixel value data can be sent to the map data detection server.

[0056] 404. The map data detection server uses a pre-trained detection model to process the input pixel value data and output the error confidence score.

[0057] The detection model is a neural network model, whose input is the pixel value data corresponding to the map feature, and whose output is the confidence level that the map feature is incorrect.

[0058] The detection model can be obtained after training on training data, for example, such as Figure 5 As shown, training data can come from the work data of the operators. For example... Figure 5 As shown, the work tasks can be divided into multiple drawing tasks, and the operators draw the corresponding map features based on the drawing tasks. The work tools can collect work data and upload it to the server for annotation.

[0059] The task data can specifically consist of screenshots of map features drawn by the operators, along with their pixel values. Annotators can manually determine if the screenshots contain errors and assign corresponding labels. Errors may include incorrect categories (e.g., a speed limit sign was drawn as a traffic guidance sign), errors in the feature itself (e.g., a speed limit of 50 was drawn as a speed limit of 30), or errors in the symbol itself. If an error exists, the label data can be represented by 1; otherwise, it can be represented by 0. This allows the pixel values ​​(represented by x) and label data (represented by y) of the map features to be combined into a training dataset.<x,y> By accumulating data, a large amount of training data can be obtained, and the detection model can be trained using this large amount of training data.

[0060] The training process for the detection model can follow the usual model training process. For example, the model parameters are represented by W, and y = W. T *x, W T This represents the transpose operation of W. The final W can be determined through training and used in the detection process.

[0061] 405. The map data detection server feeds back the error confidence level to the operation tool.

[0062] Among them, the map data detection server can feed back the error confidence to the operation tool through API.

[0063] Specifically, the job tool can use a centralized request method or a synchronous request method to obtain the error confidence level from the server via API.

[0064] The centralized request method refers to sending the pixel values ​​of all map features to the map data inspection server after all map features have been drawn, and then obtaining the error confidence scores from the map data inspection server. This method can reduce the number of interactions between the job tool and the server, thus reducing resource consumption.

[0065] The synchronous request method refers to the process where, after a batch (preset number) of map features is processed, the operator sends the pixel values ​​of that batch of map features to the map data detection server and obtains the error confidence score from the server. This method can improve real-time performance, achieving near real-time, synchronous detection.

[0066] In addition, different types of map elements can be detected using different detection models. For example, speed limit signs are detected using the first detection model, while traffic guidance signs are detected using the second detection model. The first and second detection models are different.

[0067] Therefore, the data sent by the task tool to the map data detection server includes not only pixel value data, but also category identifiers. This allows the server to select the corresponding detection model based on the category identifiers to determine the error confidence of map features.

[0068] Furthermore, the detection of map features can be triggered explicitly or implicitly. For example, the work tool's interface may have a detection button. When an operator clicks this button, the detection of currently processed but undetected map features is triggered. Alternatively, the work interface may have an upload button for uploading work data to the map data creation server. When an operator clicks the upload button, the work tool can first check the map data through the map data detection server. Only if no errors are found will the upload operation be performed, uploading the error-free map data to the map data creation server. Alternatively, the work tool may automatically detect a preset number of map features drawn by the operator.

[0069] In addition, the task tool can also determine the detection frequency of map features based on historical task information. For example, if the error rate of a certain type of map feature is high in historical task information, the detection frequency of the map feature with the high error rate will be increased.

[0070] In addition, this embodiment takes server-side detection as an example. If the user terminal where the job tool is located has sufficient performance, the job tool can also integrate the detection model into the user terminal, so that the detection can be performed locally on the user terminal.

[0071] In this embodiment, the detection result is obtained based on the feedback result, which is obtained by the detection model after processing the input pixel value data. Therefore, the detection result can be obtained based on the detection model. Since the detection model is usually a deep learning model, its accuracy is high, thus improving the accuracy of the detection result.

[0072] 406. The work tool determines the detection result based on the error confidence level.

[0073] The error confidence score is a value between 0 and 1, used to indicate the probability that the map data is erroneous. A higher error confidence score indicates a higher error rate for the corresponding map data.

[0074] If the error confidence level is greater than or equal to a first preset value, the detection result indicates that there is erroneous data in the map data; or, if the error confidence level is less than a second preset value, the detection result indicates that there is no erroneous data in the map data; or, if the error confidence level is greater than or equal to the second preset value and less than the first preset value, the detection result is obtained based on manual verification; wherein, the first preset value is greater than the second preset value.

[0075] For example, if the confidence level is in the range of [0.9, 1], the error rate is considered extremely high, and the result is deemed unacceptable; if the confidence level is in the range of [0.7, 0.9), the error rate is considered moderate, and the result is marked and uploaded to the server for manual intervention by the labelers; if the confidence level is less than 0.7, the error rate is considered low, and the result can be passed directly.

[0076] In this embodiment, the detection result can be easily determined by comparing the error confidence level with the preset value. Furthermore, by setting the first preset value and the second preset value, multiple numerical ranges can be formed based on the first preset value and the second preset value, thereby improving the accuracy of the detection result.

[0077] 407. If the detection result indicates that there is erroneous data in the map data, the operation tool displays a prompt message to the operator, the prompt message being used to indicate that there is erroneous data in the map data.

[0078] Specifically, a prompt box may pop up on the work interface where the map data is located, and the prompt information may be displayed in the prompt box; or, the erroneous data may be displayed at the location of the erroneous data on the work interface in a preset display mode (such as highlighting); wherein, the preset display method is different from the display mode of the correct data.

[0079] In this embodiment, by using the aforementioned prompt box or different display methods, various interactive methods can be employed to display prompt information to the operators, thereby increasing the diversity of interactive methods.

[0080] Alternatively, if the detection results indicate that there is no erroneous data in the map data, then step 409 can be executed.

[0081] 408. A work tool that, in response to a correction operation performed by the worker based on the prompt information, corrects the erroneous data until no erroneous data remains in the map data.

[0082] If there are errors in the map data, operators may be prohibited from uploading data to the map data production server.

[0083] In this embodiment, by displaying prompts to the operators, it is easier for them to promptly identify and correct erroneous data, thereby improving the reliability of map data.

[0084] 409. The work tool uses map data that does not contain erroneous data as the map data for the completion of the work by the workers.

[0085] 410. The task tool uploads the completed map data to the map data creation server.

[0086] If the map data does not contain any errors, operators can upload the map data to the map data creation server using the upload button on the work interface. Subsequent personnel can then use this map data to create electronic maps, etc.

[0087] In some embodiments, the training data for the detection model can be an error sample set, which refers to a set of map feature samples containing errors. For example... Figure 6 As shown, a neural network model can be trained using a set of error samples to obtain a detection model.

[0088] After obtaining the detection results, the operation tool may further include: generating an update instruction in response to the appeal instruction from the operator; wherein the appeal instruction is used to indicate that there is an error in the detection results; and sending the update instruction to the map data detection server, wherein the update instruction is used to trigger the map data detection server to update the error sample set.

[0089] An error in the detection result could be that the map element is correct, but the detection result indicates that the map element is incorrect, or it could be that the map element is incorrect, but the detection result indicates that the map element is correct.

[0090] If a map element is correct, but the detection result indicates that the map element is incorrect, the update instruction can be to trigger the server to delete the pixel value data corresponding to the map element in the error sample set; if a map element is incorrect, but the detection result indicates that the map element is correct, the update instruction can be to trigger the server to add the pixel value data corresponding to the map element in the error sample set.

[0091] After updating the error sample set, the detection model can be updated periodically using the updated error sample set, and then the updated detection model can be used for subsequent detection.

[0092] In this embodiment, since the detection model is trained using an error sample set, updating the error sample set can improve the accuracy of the detection model, thereby ensuring the accuracy of map data detection.

[0093] Figure 7 This is a schematic diagram based on the fourth embodiment of the present disclosure, which provides a map data processing device. For example... Figure 7 As shown, the map data processing device 700 includes: a screenshot module 701, an acquisition module 702, a correction module 703, and a generation module 704.

[0094] The screenshot module 701 is used to take screenshots of the map data used by the workers to obtain screenshot images of the map data; the acquisition module 702 is used to obtain the detection results of the map data based on the screenshot images, and the detection results are used to indicate whether there is erroneous data in the map data; the correction module 703 is used to correct the erroneous data until there is no erroneous data in the map data; the generation module 704 is used to use the map data without erroneous data as the map data after the workers have completed their work.

[0095] In this embodiment, during the operation, erroneous data in the map data is corrected, and map data without erroneous data is used as the map data completed by the operators. The entire process no longer includes the three stages of "operation-quality inspection-acceptance," but only the "operation" stage, thus saving steps and improving production efficiency. Furthermore, the operation stage allows for the inspection and correction of erroneous data in the map data processed by the operators, improving the accuracy of the operation data.

[0096] In some embodiments, the acquisition module 702 is further configured to: acquire pixel value data corresponding to the screenshot image; send the pixel value data to a map data detection server through a preset interface; receive feedback results sent by the map data detection server, wherein the feedback results are obtained by the map data detection server after processing the pixel value data using a preset detection model; and acquire the detection result based on the feedback results.

[0097] In this embodiment, the detection result is obtained based on the feedback result, which is obtained by the detection model after processing the input pixel value data. Therefore, the detection result can be obtained based on the detection model. Since the detection model is usually a deep learning model, its accuracy is high, thus improving the accuracy of the detection result.

[0098] In some embodiments, the acquisition module 702 is further configured to: determine that the detection result indicates the presence of erroneous data in the map data if the error confidence level is greater than or equal to a first preset value; or determine that the detection result indicates the absence of erroneous data in the map data if the error confidence level is less than a second preset value; or obtain the detection result based on manual verification if the error confidence level is greater than or equal to the second preset value and less than the first preset value; wherein the first preset value is greater than the second preset value.

[0099] In this embodiment, the detection result can be easily determined by comparing the error confidence level with the preset value. Furthermore, by setting the first preset value and the second preset value, multiple numerical ranges can be formed based on the first preset value and the second preset value, thereby improving the accuracy of the detection result.

[0100] In some embodiments, the detection model is trained based on an error sample set, and the device further includes: an appeal module for generating an update instruction in response to an appeal instruction from an operator; wherein the appeal instruction is used to indicate that the detection result contains an error; and an update module for sending the update instruction to the map data detection server, wherein the update instruction is used to trigger the map data detection server to update the error sample set.

[0101] In some embodiments, the correction module 703 is further configured to: if the detection result indicates that there is erroneous data in the map data, display a prompt message to the operator, the prompt message being used to indicate that there is erroneous data in the map data; and, in response to a correction operation performed by the operator based on the prompt message, perform correction processing on the erroneous data.

[0102] In this embodiment, since the detection model is trained using an error sample set, updating the error sample set can improve the accuracy of the detection model, thereby ensuring the accuracy of map data detection.

[0103] In some embodiments, the correction module 703 is further configured to: pop up a prompt box on the work interface where the map data is located, and display the prompt information in the prompt box; or, display the erroneous data at the location of the erroneous data on the work interface in a preset display mode; wherein the preset display mode is different from the display mode of the correct data.

[0104] In this embodiment, by using the aforementioned prompt box or different display methods, various interactive methods can be employed to display prompt information to the operators, thereby increasing the diversity of interactive methods.

[0105] In some embodiments, the map data is map elements drawn by the operator, and the screenshot module 701 is further used to: take the center point of the map element as the center point of the screenshot image, and capture a screenshot image of a preset size as the screenshot image of the map element.

[0106] In this embodiment, by using the center point of the map element as the center point of the screenshot image and taking a screenshot image of a preset size, the standardization of the screenshot image can be achieved, thereby improving the reliability of error data detection.

[0107] It is understood that the same or similar content in different embodiments of this disclosure can be referred to each other.

[0108] It is understood that the terms "first" and "second" in the embodiments of this disclosure are only used for distinction and do not indicate the degree of importance or the order of events.

[0109] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0110] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0111] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may 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 merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0112] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0113] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0114] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 performs the various methods and processes described above, such as map data processing methods. For example, in some embodiments, the electronic map data production method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the map data processing method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform map data processing methods by any other suitable means (e.g., by means of firmware).

[0115] Various embodiments of the systems and techniques described above herein 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), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to the processor or controller of a general-purpose computer, special-purpose computer, or other programmable map data acquisition device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).

[0119] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0120] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0121] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for processing map data, an operational tool applied to a stage of the map data production process, wherein the production process only includes the operational stage, comprising: A screenshot of the map data used by the workers is taken to obtain a screenshot of the map data. Based on the screenshot, the detection result of the map data is obtained. The detection result indicates whether there is erroneous data in the map data. This includes: obtaining the pixel value data corresponding to the screenshot; sending the pixel value data to the map data detection server through a preset interface; receiving feedback results from the map data detection server, where the feedback results are obtained after the map data detection server processes the pixel value data using a preset detection model; obtaining the detection result based on the feedback result; where the feedback result is an error confidence level, and the work tool obtains the error confidence level from the map data detection server via API using a centralized request method or a synchronous request method; and correcting the erroneous data until there is no erroneous data in the map data. Specifically, this includes: the operator correcting the erroneous data based on the detection result, repeating the above process until there is no erroneous data in the map data. Map data without errors is uploaded to the map data creation server as the map data completed by the operators. The detection model is trained based on a set of error samples. After obtaining the detection results of the map data, the method further includes: In response to an appeal instruction from the operator, an update instruction is generated; wherein the appeal instruction is used to indicate that the test result is incorrect; The update instruction is sent to the map data detection server. The update instruction is used to trigger the map data detection server to update the error sample set, including: if the map element is correct but the detection result is incorrect, triggering the deletion of the corresponding pixel value data in the error sample set; if the map element is incorrect but the detection result is correct, triggering the addition of the corresponding pixel value data in the error sample set.

2. The method according to claim 1, wherein, The step of obtaining the detection result based on the feedback result includes: If the error confidence level is greater than or equal to a first preset value, the detection result indicates that erroneous data exists in the map data; or... If the error confidence level is less than a second preset value, it is determined that the detection result indicates that there is no erroneous data in the map data; or... If the error confidence level is greater than or equal to the second preset value and less than the first preset value, the detection result is obtained based on manual verification. Wherein, the first preset value is greater than the second preset value.

3. The method according to any one of claims 1-2, wherein, The process of correcting the erroneous data includes: If the detection result indicates that there is erroneous data in the map data, a prompt message is displayed to the operator, the prompt message being used to indicate that there is erroneous data in the map data; In response to the corrective action performed by the operator based on the prompt information, the erroneous data is corrected.

4. The method according to claim 3, wherein, The step of displaying prompt information to the operator includes: A prompt box will pop up on the work interface where the map data is located, displaying the prompt information; or... The error data is displayed at the location of the error data on the work interface in a preset display mode; wherein the preset display mode is different from the display mode of the correct data.

5. The method according to any one of claims 1-2, wherein, The map data consists of map features drawn by the workers. The step of taking a screenshot of the map data created by the workers to obtain a screenshot image of the map data includes: The center point of the map element is used as the center point of the screenshot image, and a screenshot image of a preset size is taken as the screenshot image of the map element.

6. A map data processing apparatus, an application tool in a processing stage of a map data production process, wherein the production process only includes the processing stage, comprising: The screenshot module is used to take screenshots of the map data used by the workers to obtain screenshot images of the map data. The acquisition module is used to acquire the detection result of the map data based on the screenshot image. The detection result is used to indicate whether there is erroneous data in the map data. This includes: acquiring the pixel value data corresponding to the screenshot image; sending the pixel value data to the map data detection server through a preset interface; receiving feedback results sent by the map data detection server, where the feedback results are obtained after the map data detection server processes the pixel value data using a preset detection model; acquiring the detection result based on the feedback results; where the feedback result is the error confidence level, and the operation tool obtains the error confidence level from the map data detection server via API using a centralized request method or a synchronous request method. The correction module is used to correct the erroneous data until there is no erroneous data in the map data. Specifically, it includes: the operator correcting the erroneous data based on the detection results, and repeating the above process until there is no erroneous data in the map data. The generation module is used to upload map data without errors, as the map data completed by the operators, to the map data creation server. The detection model is trained based on a set of error samples, and the device further includes: The appeal module is used to generate an update instruction in response to an appeal instruction from the operator; wherein the appeal instruction is used to indicate that the detection result is incorrect; An update module is used to send the update instruction to the map data detection server. The update instruction is used to trigger the map data detection server to update the error sample set, including: if the map element is correct but the detection result is incorrect, triggering the deletion of the corresponding pixel value data in the error sample set; if the map element is incorrect but the detection result is correct, triggering the addition of the corresponding pixel value data in the error sample set.

7. The apparatus according to claim 6, wherein, The acquisition module is further used for: If the error confidence level is greater than or equal to the first preset value, it is determined that the detection result indicates that there is erroneous data in the map data; or, If the error confidence level is less than the second preset value, it is determined that the detection result indicates that there is no erroneous data in the map data; or, If the error confidence level is greater than or equal to the second preset value and less than the first preset value, the detection result is obtained based on manual verification. Wherein, the first preset value is greater than the second preset value.

8. The apparatus according to any one of claims 6-7, wherein, The correction module is further used for: If the detection result indicates that there is erroneous data in the map data, a prompt message is displayed to the operator, the prompt message being used to indicate that there is erroneous data in the map data; In response to the corrective action performed by the operator based on the prompt information, the erroneous data is corrected.

9. The apparatus according to claim 8, wherein, The correction module is further used for: A prompt box will pop up on the work interface where the map data is located, displaying the prompt information; or... The error data is displayed at the location of the error data on the work interface in a preset display mode; wherein the preset display mode is different from the display mode of the correct data.

10. The apparatus according to any one of claims 6-7, wherein, The map data consists of map elements drawn by the operators, and the screenshot module is further used for: The center point of the map element is used as the center point of the screenshot image, and a screenshot image of a preset size is taken as the screenshot image of the map element.

11. 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 1-5.

12. 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 1-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images