Stroke data robot production method, device, equipment and storage medium

Abstract

The present application provides a method, device, equipment and storage medium for producing a stroke data robot, which relates to the field of robotic process automation technology. The method compares each to-be-queried image and the to-be-queried field, and when the to-be-queried field exists in the to-be-queried image, determines the coordinate range of the to-be-queried field in the target image and the image level path of the target image to generate a stroke data robot. In this way, a stroke data robot can be automatically generated, and the stroke data robot can also automatically obtain each to-be-queried field for reporting based on the coordinate range of the to-be-queried field in the target image and the image level path of the target image. There is no need to manually produce the stroke data robot, which can improve the production efficiency of the stroke data robot and reduce the cost of producing the stroke data robot.

Description

Technical Field

[0001] The present application relates to the field of robotic process automation technology, and in particular to a method, device, equipment and storage medium for robot production of stroke data. Background Art

[0002] After receiving a stroke patient, the hospital needs to upload the relevant data of the stroke patient during hospitalization to the stroke database.

[0003] With the rapid development of information technology and the widespread application of artificial intelligence, it is necessary to build a set of software robots based on RPA (Robotic Process Automation) technology to automatically extract, review and report stroke center data, and assist hospitals in reporting stroke data for thousands of hospital stroke centers across the country. However, in the RPA development process, customized development is required for different vendors and / or data source software versions. Each company has many versions of the same system, and each version of the software requires a new robot to be created, resulting in a sharp increase in the workload of manual RPA robot production, which is not only inefficient but also costly. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for producing a stroke data robot, which can improve the production efficiency of the stroke data robot and reduce the cost of producing the stroke data robot.

[0005] The present application provides a method for producing a stroke data robot, comprising:

[0006] Acquire multiple target fields, where the target fields are fields related to stroke data;

[0007] Executing a step of obtaining a field to be queried, the step of obtaining a field to be queried comprising: selecting an unmatched target field from a plurality of target fields as the field to be queried;

[0008] Determine the initial interface of the system to be queried as the image to be queried;

[0009] Executing a field comparison step, the field comparison step comprising: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried;

[0010] If it exists, the image to be queried is determined as the target image, the coordinate range of the field to be queried in the target image and the image level path of the target image are determined, and the step of obtaining the field to be queried is performed; if it does not exist, the next user interface of the image to be queried is determined as the image to be queried according to the preset interface screening strategy, and the step of comparing the fields is performed;

[0011] A stroke data robot is generated based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

[0012] In one embodiment of the present application, comparing the image to be queried and the field to be queried to determine whether the field to be queried exists in the image to be queried includes:

[0013] Performing image recognition on the image to be queried to determine text information of the image to be queried;

[0014] Comparing the text information of the image to be queried with the field to be queried;

[0015] If the text information of the image to be queried contains the same text as the field to be queried, then determining that the field to be queried exists in the image to be queried;

[0016] If the text information of the image to be queried does not contain the same text as the field to be queried, it is determined that the field to be queried does not exist in the image to be queried.

[0017] In one embodiment of the present application, determining the coordinate range of the field to be queried in the target image includes:

[0018] Determine the field coordinates of the field to be queried in the target image;

[0019] Identifying a text box associated with the field to be queried in the target image, and determining a coordinate range of the text box;

[0020] Based on the field coordinates and the coordinate range of the text box, the coordinate range of the field to be queried in the target image is determined.

[0021] In one embodiment of the present application, after generating a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image, the method further includes:

[0022] According to the image level path of the target image, obtaining the image to be checked in the query system; comparing the target image with the image to be checked to obtain a first checking result;

[0023] Based on the coordinate range of the field to be queried in the target image, the field to be checked is determined in the image to be checked, and the field to be checked is compared with the field to be queried to obtain a second checking result.

[0024] To achieve the above objectives and other related objectives, the present application provides a stroke data robot production device, comprising:

[0025] A data acquisition module, used for acquiring a plurality of target fields, wherein the target fields are fields related to stroke data;

[0026] A first execution module is used to execute a step of obtaining a field to be queried, wherein the step of obtaining a field to be queried includes: selecting an unmatched target field from a plurality of target fields as the field to be queried;

[0027] A first determining module, used to determine the initial interface of the system to be queried as the image to be queried;

[0028] A second execution module is used to execute a field comparison step, wherein the field comparison step includes: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried;

[0029] The second determination module is used to determine the image to be queried as the target image if it exists, determine the coordinate range of the field to be queried in the target image, and the image level path of the target image, and execute the step of obtaining the field to be queried; if it does not exist, determine the next user interface of the image to be queried as the image to be queried according to a preset interface screening strategy, and execute the step of comparing the fields;

[0030] A generation module is used to generate a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

[0031] In one embodiment of the present application, the second execution module includes:

[0032] A first recognition unit, configured to perform image recognition on the image to be queried to determine text information of the image to be queried;

[0033] A comparison unit, used for comparing the text information of the image to be queried with the field to be queried;

[0034] A first result determination unit, configured to determine that the to-be-queried field exists in the to-be-queried image if the text information of the to-be-queried image contains the same text as the to-be-queried field;

[0035] The second result determination unit is configured to determine that the to-be-queried field does not exist in the to-be-queried image if the text information of the to-be-queried image does not contain the same text as the to-be-queried field.

[0036] In one embodiment of the present application, the second determining module includes:

[0037] A first coordinate determination unit, used to determine the field coordinates of the field to be queried in the target image;

[0038] A second recognition unit, used to recognize a text box associated with the field to be queried in the target image, and determine a coordinate range of the text box;

[0039] The second coordinate determining unit is used to determine the coordinate range of the field to be queried in the target image based on the field coordinates and the coordinate range of the text box.

[0040] In one embodiment of the present application, the device further includes:

[0041] A first result determination module is used to obtain the image to be checked in the query system according to the image level path of the target image; compare the target image with the image to be checked to obtain a first checking result;

[0042] The second result determination module is used to determine the field to be checked in the image to be checked based on the coordinate range of the field to be checked in the target image, compare the field to be checked with the field to be queried, and obtain a second checking result.

[0043] To achieve the above objectives and other related objectives, the present application also provides an electronic device, the electronic device comprising:

[0044] one or more processors;

[0045] a memory for storing program code executable by the processor;

[0046] Wherein, the processor is configured to execute the program code to implement the above-mentioned stroke data robot production method.

[0047] To achieve the above objectives and other related objectives, the present application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the above-mentioned stroke data robot production method.

[0048] As described above, the stroke data robot production method, device, equipment and storage medium provided by the present application have the following beneficial effects:

[0049] A method for producing a stroke data robot in the present application compares each image to be queried and the field to be queried. When the field to be queried exists in the image to be queried, the coordinate range of the field to be queried in the target image and the image level path of the target image are determined to generate a stroke data robot. In this way, a stroke data robot can be automatically generated, and the stroke data robot can also automatically obtain each field to be queried for reporting based on the coordinate range of the field to be queried in the target image and the image level path of the target image. There is no need to manually produce the stroke data robot, which can improve the production efficiency of the stroke data robot and reduce the cost of producing the stroke data robot.

[0050] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0052] Figure 1 is a flow chart of a method for producing stroke data robot shown in an exemplary embodiment of the present application;

[0053] Figure 2 It is a structural block diagram of a stroke data robot production device shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0055] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0056] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0057] It should be noted that the stroke data robot production method provided in the embodiment of the present application can be executed by one robot, and the robot can be deployed on a terminal running the system to be queried. The stroke data robot production method provided in the embodiment of the present application can also be executed by three robots, and the three robots may include a first robot, a second robot and a third robot. The first robot can obtain the target field from the cloud and transmit the target field to the second robot. After obtaining the target field, the second robot can compare the field to be queried and the image to be queried to determine the coordinate range of the field to be queried in the target image, and the image level path of the target image, and send the coordinate range of the field to be queried in the target image, and the image level path of the target image to the third robot. The third robot can generate a stroke data robot based on the data sent by the second robot.

[0058] In the embodiments of the present application, each robot can be obtained based on the robotic process automation technology and work according to the steps provided in the embodiments of the present application. Robotic process automation (RPA) is a technical solution that allows software robots (also known as "digital employees") to automatically execute rule-based business processes. These robots can imitate the way humans operate computer systems and perform repetitive, standardized tasks without writing new code.

[0059] See also Figure 1 , Figure 1 FIG. 1 is a flowchart of a method for producing stroke data by a robot, as shown in an exemplary embodiment of the present application. Figure 1 It can be seen that the stroke data robot production method may include:

[0060] Step S110, obtaining multiple target fields, where the target fields are fields related to stroke data.

[0061] In one embodiment of the present application, the plurality of target fields may be stored in the cloud, and the robot may obtain the plurality of target fields from the cloud. The plurality of target fields may be fields that need to be uploaded to the stroke database.

[0062] Exemplarily, the number of target fields may be 357.

[0063] It should be noted that the fields related to stroke data (that is, target fields) may include:

[0064] 1. Basic information: such as patient's name, gender, age, ID number (de-identified), contact information, address, etc.

[0065] 2. Medical history information: including past medical history, family medical history, allergy history, smoking and drinking history, etc.

[0066] 3. Admission information: admission time, admission method (emergency, outpatient, etc.), initial diagnosis, etc.

[0067] 4. Clinical manifestations: symptom description, physical signs, vital signs (blood pressure, heart rate, respiratory rate, etc.).

[0068] 5. Auxiliary examination results: imaging examination (CT, MRI), laboratory examination (blood routine, biochemical indicators, coagulation function, etc.).

[0069] 6. Treatment measures: detailed records of drug treatment, surgical treatment, rehabilitation treatment, nursing measures, etc.

[0070] 7. Disease progression: changes in the condition, occurrence of complications, response to treatment, etc.

[0071] 8. Discharge status: discharge time, discharge diagnosis, outcome (improvement, cure, death, etc.).

[0072] 9. Follow-up information: follow-up plan, follow-up results, etc.

[0073] Step S120, executing a step of obtaining a field to be queried, the step of obtaining a field to be queried comprising: selecting an unmatched field from a plurality of target fields as a field to be queried.

[0074] In one embodiment of the present application, a step of obtaining a field to be queried may be performed to select a target field that has not been compared from a plurality of target fields as a field to be queried. Each target field may be numbered, and each target field may be determined as a field to be queried in sequence based on the order of the numbers. The step of obtaining a field to be queried needs to be repeated until all target fields are determined as fields to be queried and compared.

[0075] Step S130: determining the initial interface of the system to be queried as the image to be queried.

[0076] In one embodiment of the present application, the robot can log in to the system to be queried on a hospital terminal, which is a terminal of any hospital that needs to upload stroke data. The initial interface can be the first interface displayed after the robot or user logs in to the system to be queried.

[0077] In one possible implementation, the robot can pre-record the operator's operating steps for the system to be queried, such as logging into the system to be queried at the hospital terminal and clicking the icon of the user interface of the system to be queried. After recording the aforementioned relevant data, the robot can automatically log into the system to be queried and click the icon of the user interface of the system to be queried to enter the next level user interface of each user interface.

[0078] In another possible implementation, automation can be performed by identifying objects on the user interface. The RPA tool can identify elements on the user interface (such as buttons, text boxes, etc.) and can interact directly with these objects.

[0079] In yet another possible implementation, an application programming interface (API) may be called to enable the robot to automatically log in to the system to be queried and display different user interfaces.

[0080] Step S140, executing a field comparison step, the field comparison step includes: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried.

[0081] In one embodiment of the present application, the image to be queried and the field to be queried may be compared to determine whether there is a field to be queried that needs to be uploaded in the image to be queried.

[0082] Step S150, if it exists, the image to be queried is determined as the target image, the coordinate range of the field to be queried in the target image, and the image level path of the target image are determined, and the step of obtaining the field to be queried is executed; if it does not exist, the next user interface of the image to be queried is determined as the image to be queried according to the preset interface screening strategy, and the field comparison step is executed.

[0083] In one embodiment of the present application, if there is a field to be queried in the image to be queried, it indicates that the stroke data robot can obtain the field to be queried in the image to be queried for uploading, so the image to be queried can be determined as the target image, and the coordinate range of the field to be queried in the target image and the hierarchical path of the target image can be determined, so that the stroke data robot can find the target image after logging into the system to be identified according to the hierarchical path of the target image, and find the field to be queried in the aforementioned coordinate range according to the coordinate range of the field to be queried in the target image, and report it. After this, the step of obtaining the field to be queried can be performed, and the target fields that have not been compared in the target field can be compared, until all target fields are determined as fields to be queried and compared with each image to be queried.

[0084] In one embodiment of the present application, if the field to be queried does not exist in the image to be queried, it indicates that other user interfaces need to be compared. Therefore, according to the preset interface screening strategy, the next user interface of the current image to be queried can be determined as the image to be queried, and the field comparison step can be performed.

[0085] In a possible implementation, the preset interface screening strategy may be to start from the initial interface, sequentially determine each user interface of the second level as the image to be queried, and after the second level user interface is screened, sequentially determine each user interface of the third level as the image to be queried, and so on. The first level user interface may be the initial interface, the second level user interface may be the next level user interface entered by clicking any button or other key on the initial interface, and the third level user interface may be the next level user interface entered by clicking any button or other key on the second level user interface.

[0086] In another possible implementation, the preset interface screening strategy may be to start from the initial interface and sequentially determine the user interfaces on each hierarchical path as the image to be queried. For example, the first user interface may be the initial interface, and the user interface entered by clicking any button or other key on the initial interface may be determined as the second user interface, and the user interface entered by clicking any button or other key on the second user interface may be determined as the third user interface, and so on until one user interface is stepped back, and all user interfaces of the system to be queried may be traversed in this manner.

[0087] It should be noted that each user interface of the system to be queried should include all target fields. If any field to be queried does not exist in all user interfaces, the field to be queried should be marked, and the next target field that has not been compared should be determined as the field to be queried and step S140 should be executed.

[0088] When the robot displays the interface to be queried by operating the system to be queried, each image to be queried may correspond to an image hierarchy path, and the image hierarchy path may instruct the robot to operate on the display interface of the system to be queried to display the image to be queried.

[0089] Exemplarily, the target image may be the second sub-interface, and the image hierarchy path of the second image may include entering the first sub-interface after clicking a first button on the initial interface, selecting a second option in a first selection box in the first sub-interface, and then entering the second sub-interface after clicking a second button.

[0090] In the embodiment of the present application, the robot can first obtain all user interfaces of the system to be queried, each user interface corresponds to an image hierarchy path, and each user interface is determined as an image to be queried in turn, and compared with the field to be queried. After logging into the system to be queried, the robot can also obtain the image to be queried for any field to be queried, starting from the initial interface, according to the preset interface screening strategy, and if the field to be queried does not exist in the image to be queried, the image to be queried can be deleted to free up the storage space of the robot.

[0091] It should be noted that, in the embodiment of the present application, the image resolution of each image to be identified should be 1920*1080, which can ensure that an accurate coordinate range is obtained. When the robot obtains the image to be identified, the image to be identified should be displayed in full screen on the display.

[0092] Step S160, generating a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

[0093] In one embodiment of the present application, a stroke data robot can be generated based on the image level path of each target image and the coordinate range of each field to be queried in the target image. Multiple sub-robots can be generated based on the image level path of each target image and the coordinate range of each image to be queried in the target image. Each sub-robot can obtain the actual image in the system to be queried based on the image level path of the target image, and obtain the field to be queried in the actual image based on the coordinate range of the field to be queried in the target image. Multiple sub-robots can be combined into a collection robot chain, and the collection robot chain is determined as a stroke data robot.

[0094] In one embodiment, the process of comparing the image to be queried and the field to be queried in step S140 to determine whether the field to be queried exists in the image to be queried may include steps S141 to S144.

[0095] Step S141: performing image recognition on the query image to determine text information of the query image.

[0096] In one embodiment of the present application, image recognition can be performed on the query image to determine the text information of the query image. The image to be recognized can be preprocessed, and then file detection can be performed to determine the text position, and then text recognition can be performed to determine the actual content of the text to obtain the text information.

[0097] Step S142, comparing the text information of the image to be queried with the field to be queried.

[0098] In one embodiment of the present application, the text information of the image to be queried and the field to be queried may be compared.

[0099] Step S143: If the text information of the image to be queried contains the same text as the field to be queried, it is determined that the field to be queried exists in the image to be queried.

[0100] Step S144: if the text information of the image to be queried does not contain the same text as the field to be queried, it is determined that the field to be queried does not exist in the image to be queried.

[0101] In one embodiment, the process of determining the coordinate range of the field to be queried in the target image in step S150 may include steps S151 to S153.

[0102] Step S151, determining the field coordinates of the field to be queried in the target image.

[0103] In one embodiment of the present application, the field coordinates of the field to be queried in the target image may be determined, and the field coordinates may be the coordinates of a boundary box of the field to be queried.

[0104] Before obtaining the field coordinates, the target image can be preprocessed to improve the accuracy and efficiency of subsequent recognition. The preprocessing steps can include:

[0105] Scaling: Resize the image to fit the algorithm's requirements.

[0106] Crop: Remove unnecessary background and keep only the part containing text.

[0107] Grayscale: Convert a color image to a grayscale image to reduce the amount of calculation.

[0108] Binarization: Convert the image into black and white to highlight the text.

[0109] Noise Removal: Remove interfering noise from images, such as salt and pepper noise.

[0110] After preprocessing, text detection can be performed. Text detection refers to the process of finding text areas in an image. Text detection algorithms can include: Haar features + Adaboost classifier; CNN (convolutional neural network), such as EAST text detection network.

[0111] After that, text recognition can be performed to determine the content of each character. Text recognition can include: OCR (optical character recognition); deep learning methods, such as using deep learning models (such as LSTM, CRNN, etc.) for text recognition.

[0112] After recognizing the text, you also need to determine the position of the text in the image. You can directly use pixel coordinates to represent the position of the text.

[0113] Step S152, identifying a text box associated with the field to be queried in the target image, and determining a coordinate range of the text box.

[0114] In one embodiment of the present application, the text box associated with the field to be queried can be used for the user to input actual information. The text box associated with the field to be queried can be a blank area located on the right side of the field to be queried, and the blank area is generally different from the display background color of the user interface. The text box can be identified by identifying the boundary of the text box, and the coordinate range of the text box can be determined.

[0115] Exemplarily, for example, when the field to be queried is "name", "xxx" can be entered in the text box associated with the field to be queried.

[0116] Step S153: determining the coordinate range of the field to be queried in the target image based on the field coordinates and the coordinate range of the text box.

[0117] In one embodiment of the present application, the coordinate range of the field to be queried in the target image can be determined based on the field coordinates and the coordinate range of the text box. The coordinate range of the field to be queried in the target image should include the field coordinates and the coordinate range of the text box, and there should be no other fields in the coordinate range of the field to be queried in the target image. In this coordinate range, not only the length range is limited, but also the height range needs to be limited to identify the complete field to be identified and the actual information.

[0118] In one embodiment, the stroke data robot production method provided in the embodiment of the present application may also include step S210 and step S220.

[0119] Step S210 , obtaining the image to be checked in the system to be queried according to the image level path of the target image; comparing the target image with the image to be checked to obtain a first checking result.

[0120] In one embodiment of the present application, after the stroke data robot is generated, the validity of the stroke data robot can be checked. The stroke data robot can obtain the image to be checked in the user interface of the system to be queried according to the image hierarchy path of the target image, and compare the target image with the image to be checked to identify whether the features of the two images match, and obtain a first check result, which can indicate whether the target image and the image to be checked are the same.

[0121] For example, features can be extracted for the target image, such as which fields are included in the target image and where the fields are located. Features can also be extracted for the image to be checked to identify which fields are included in the image to be checked and where the fields are located. By comparing the features of two images, it can be determined whether the two images are the same.

[0122] Step S220 , based on the coordinate range of the field to be queried in the target image, determine the field to be checked in the image to be checked, compare the field to be checked with the field to be queried, and obtain a second checking result.

[0123] In one embodiment of the present application, the field to be checked can be determined in the image to be checked based on the coordinate range of the field to be queried in the target image. The target image in step S220 is consistent with the target image in step S210. In step S150, if there is a field to be identified in the image to be queried, the image to be queried is determined as the target image, the coordinate range of the field to be queried in the target image, and the image level path of the target image are determined, and the field to be queried and the target image can also be associated. The query field in step S220 is the query field associated with the target image in step S210.

[0124] It should be noted that the second verification result may indicate whether the field to be verified is consistent with the field to be queried, and the second verification result may also indicate whether the field to be verified is completely displayed within the coordinate range.

[0125] For example, when the field to be queried is "name", the complete display of the field to be checked in the image to be checked can be "name xxxxxx". If the text box associated with the field to be queried can only display 4.5 characters, then in the target image, the only identifiable field to be checked is "name xxxx", and the field to be checked is not displayed completely.

[0126] It should be noted that, for each target image, a first verification result can be obtained, and for each field to be queried, a second verification result can be obtained.

[0127] Figure 2 FIG. 1 is a block diagram of a stroke data robot production device shown in an exemplary embodiment of the present application. Figure 2 As shown, the exemplary stroke data robot production device 200 includes:

[0128] The data acquisition module 210 is used to acquire multiple target fields, where the target fields are fields related to stroke data;

[0129] The first execution module 220 is used to execute a step of obtaining a field to be queried, the step of obtaining a field to be queried comprising: selecting an unmatched target field from a plurality of target fields as the field to be queried;

[0130] A first determining module 230, configured to determine the initial interface of the system to be queried as the image to be queried;

[0131] The second execution module 240 is used to execute a field comparison step, which includes: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried;

[0132] The second determination module 250 is used to determine the image to be queried as the target image, determine the coordinate range of the field to be queried in the target image, and the image level path of the target image, and execute the step of obtaining the field to be queried if the image to be queried exists; if the image to be queried does not exist, determine the next user interface of the image to be queried as the image to be queried according to the preset interface screening strategy, and execute the step of comparing the fields;

[0133] The generation module 260 is used to generate a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

[0134] In one embodiment of the present application, the second execution module includes:

[0135] A first recognition unit, used for performing image recognition on the query image to determine text information of the query image;

[0136] A comparison unit, used for comparing text information of the image to be queried with the field to be queried;

[0137] A first result determination unit, configured to determine that the field to be queried exists in the image to be queried if the text information of the image to be queried contains the same text as the field to be queried;

[0138] The second result determination unit is configured to determine that the to-be-queried field does not exist in the to-be-queried image if the text information of the to-be-queried image does not contain the same text as the to-be-queried field.

[0139] In one embodiment of the present application, the second determination module includes:

[0140] A first coordinate determination unit, used to determine the field coordinates of the field to be queried in the target image;

[0141] A second recognition unit is used to recognize a text box associated with the field to be queried in the target image and determine a coordinate range of the text box;

[0142] The second coordinate determining unit is used to determine the coordinate range of the field to be queried in the target image based on the field coordinates and the coordinate range of the text box.

[0143] In one embodiment of the present application, the device further includes:

[0144] A first result determination module is used to obtain the image to be checked in the query system according to the image level path of the target image; compare the target image with the image to be checked to obtain a first checking result;

[0145] The second result determination module is used to determine the field to be checked in the image to be checked based on the coordinate range of the field to be checked in the target image, compare the field to be checked with the field to be queried, and obtain a second verification result.

[0146] It should be noted that the stroke data robot production device provided in the above embodiment and the stroke data robot production method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual application, the stroke data robot production device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0147] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic device implements the stroke data robot production method provided in the above-mentioned embodiments.

[0148] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to execute the stroke data robot production method provided in each of the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

[0149] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the stroke data robot production method provided in each of the above embodiments.

[0150] In the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. "Including" and "comprising" mentioned throughout the specification and claims are open-ended terms and should be interpreted as "including but not limited to".

[0151] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for producing a stroke data robot, characterized in that: include: Acquire multiple target fields, where the target fields are fields related to stroke data; Executing a step of obtaining a field to be queried, the step of obtaining a field to be queried comprising: selecting an unmatched target field from a plurality of target fields as the field to be queried; Determine the initial interface of the system to be queried as the image to be queried; Executing a field comparison step, the field comparison step comprising: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried; If it exists, the image to be queried is determined as the target image, the coordinate range of the field to be queried in the target image and the image level path of the target image are determined, and the step of obtaining the field to be queried is performed; if it does not exist, the next user interface of the image to be queried is determined as the image to be queried according to the preset interface screening strategy, and the step of comparing the fields is performed; A stroke data robot is generated based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

2. The method for producing a stroke data robot according to claim 1, characterized in that: Comparing the image to be queried and the field to be queried to determine whether the field to be queried exists in the image to be queried, including: Performing image recognition on the image to be queried to determine text information of the image to be queried; Comparing the text information of the image to be queried with the field to be queried; If the text information of the image to be queried contains the same text as the field to be queried, then determining that the field to be queried exists in the image to be queried; If the text information of the image to be queried does not contain the same text as the field to be queried, it is determined that the field to be queried does not exist in the image to be queried.

3. The method for producing a stroke data robot according to claim 1, characterized in that: Determining the coordinate range of the field to be queried in the target image includes: Determine the field coordinates of the field to be queried in the target image; Identify a text box associated with the field to be queried in the target image, and determine a coordinate range of the text box; Based on the field coordinates and the coordinate range of the text box, the coordinate range of the field to be queried in the target image is determined.

4. The method for producing a stroke data robot according to claim 1, characterized in that: After generating a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image, the method further includes: According to the image level path of the target image, obtaining the image to be checked in the query system; comparing the target image with the image to be checked to obtain a first checking result; Based on the coordinate range of the field to be queried in the target image, the field to be checked is determined in the image to be checked, and the field to be checked is compared with the field to be queried to obtain a second checking result.

5. A stroke data robot production device, characterized in that: include: A data acquisition module, used for acquiring a plurality of target fields, wherein the target fields are fields related to stroke data; A first execution module is used to execute a step of obtaining a field to be queried, wherein the step of obtaining a field to be queried includes: selecting an unmatched target field from a plurality of target fields as the field to be queried; A first determining module, used to determine the initial interface of the system to be queried as the image to be queried; A second execution module is used to execute a field comparison step, wherein the field comparison step includes: comparing the image to be queried with the field to be queried to determine whether the field to be queried exists in the image to be queried; The second determination module is used to determine the image to be queried as the target image if it exists, determine the coordinate range of the field to be queried in the target image, and the image level path of the target image, and execute the step of obtaining the field to be queried; if it does not exist, determine the next user interface of the image to be queried as the image to be queried according to a preset interface screening strategy, and execute the step of comparing the fields; A generation module is used to generate a stroke data robot based on the image level path of each target image and the coordinate range of each field to be queried in the target image.

6. The stroke data robot production device according to claim 5, characterized in that: The second execution module includes: A first recognition unit, configured to perform image recognition on the image to be queried to determine text information of the image to be queried; A comparison unit, used for comparing the text information of the image to be queried with the field to be queried; A first result determination unit, configured to determine that the to-be-queried field exists in the to-be-queried image if the text information of the to-be-queried image contains the same text as the to-be-queried field; The second result determination unit is configured to determine that the to-be-queried field does not exist in the to-be-queried image if the text information of the to-be-queried image does not contain the same text as the to-be-queried field.

7. The stroke data robot production device according to claim 5, characterized in that: The second determination module includes: A first coordinate determination unit, used to determine the field coordinates of the field to be queried in the target image; A second recognition unit, used to recognize a text box associated with the field to be queried in the target image, and determine a coordinate range of the text box; The second coordinate determining unit is used to determine the coordinate range of the field to be queried in the target image based on the field coordinates and the coordinate range of the text box.

8. The stroke data robot production device according to claim 5, characterized in that: The device also includes: A first result determination module is used to obtain the image to be checked in the query system according to the image level path of the target image; compare the target image with the image to be checked to obtain a first checking result; The second result determination module is used to determine the field to be checked in the image to be checked based on the coordinate range of the field to be checked in the target image, compare the field to be checked with the field to be queried, and obtain a second checking result.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing program code executable by the processor; Wherein, the processor is configured to execute the program code to implement the stroke data robot production method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the stroke data robot production method as described in any one of claims 1 to 4.

Images