Method and medium for making RPA robot based on location-based data extraction

Abstract

The present invention relates to a method and medium for producing an RPA robot for data extraction based on position positioning, and relates to the field of computer data processing technology. By obtaining a screenshot with a preset field, and identifying the preset field based on the screenshot, a screenshot ID corresponding to the preset field is obtained, and the preset field is obtained from the obtained screenshot identification. Based on the identified preset field, the location of the content data corresponding to the preset field is identified, and the location of the data content corresponding to the preset field to be extracted is obtained. In this way, an RPA robot can be produced based on the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field, thereby obtaining a data extraction RPA robot based on position positioning, reducing the workload of RPA robot production and greatly reducing labor costs.

Description

Technical Field

[0001] The present invention relates to the field of computer data processing technology, and in particular to a method and medium for producing a data extraction RPA robot based on position positioning. Background Art

[0002] Currently, after a stroke patient is discharged from the hospital, the hospital is required to promptly upload 357 treatment data indicators of the stroke patient during the hospitalization period to the prescribed stroke database, so as to further conduct stroke case quality control and data analysis, optimize treatment measures, improve treatment rates, and reduce the disease burden.

[0003] With the rapid development of information technology and the widespread application of artificial intelligence, it is necessary to develop a software robot based on RPA (Robotic Process Automation) technology to automatically extract, review, and report stroke center data. This robot will be used by thousands of hospital stroke centers nationwide to assist hospitals in reporting stroke data. However, RPA development requires customization for different vendors and / or data source software versions. Each company has multiple versions of the same system, and each version requires a new robot, which significantly increases the manual RPA workload. Reducing the workload of RPA robot development has become a pressing issue. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a method and medium for producing an RPA robot based on location-based data extraction, which has the characteristics of reducing the workload of RPA robot production and reducing labor costs.

[0005] In a first aspect, an embodiment provides a method for creating a data extraction RPA robot based on location positioning, including:

[0006] Obtaining a screenshot containing a preset field, and identifying the preset field based on the screenshot;

[0007] Based on the identified preset field, identifying the location of the content data corresponding to the preset field;

[0008] Create an RPA robot, including the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field.

[0009] In one embodiment, obtaining a screenshot containing preset fields includes:

[0010] A screenshot is obtained, and preset fields in the screenshot are obtained through OCR recognition based on the obtained screenshot, so as to obtain a screenshot containing the preset fields.

[0011] In one embodiment, obtaining a screenshot containing preset fields includes:

[0012] Based on the correspondence between the preset fields and the screenshots, the screenshot containing the content data corresponding to the preset fields to be extracted is obtained.

[0013] In one embodiment, the step of identifying the location of the content data corresponding to the preset field based on the identified preset field includes:

[0014] For any identified preset field, identifying whether there is a first text box in which the first text content only includes the preset field, and the first text content does not include punctuation marks;

[0015] If a first text box exists, search to the right for a second text box adjacent to the right within the first identical content area; if a second text box adjacent to the right exists, use the position of the second text box as the position of the content data of any one of the preset fields; if a second text box adjacent to the right does not exist, search downward for a second text box adjacent to the bottom that is aligned with the left end of the first text box, and use the position of the second text box adjacent to the bottom as the position of the content data of any one of the preset fields; the position of the second text box includes: the upper left corner coordinate point and the lower right corner coordinate point of the second text box, or the lower left corner coordinate point and the upper right corner coordinate point of the second text box; the first identical content area refers to the area within a first preset distance threshold range from the right edge of the first text box.

[0016] If the first text box does not exist, the first starting coordinate point and the first ending coordinate point of the preset field are identified; based on the first ending coordinate point, the adjacent first character is searched to the right in the second same content area, and it is determined whether the adjacent first character is a preset spacing character. If so, based on the second ending coordinate point of the first character, the second character adjacent to the right is searched to the right in the second same content area. If the second character is searched, the starting coordinate position of the searched second character is used as the starting coordinate position of the content data of any one of the preset fields; if the first character is not a preset spacing character, the starting coordinate position of the first character is used as the starting coordinate position of the content data of any one of the preset fields; if the first character or the second character is not searched, the X-axis coordinate of the first starting coordinate point is used as the starting horizontal coordinate of the next row to search for the third character adjacent to the right, and the starting coordinate position of the third character is used as the starting coordinate position of the content data of any one of the preset fields; the second same content area refers to the preset field isoheight area within the second preset distance threshold range of the coordinate point based on the first starting coordinate point, and the spacing characters include ":" and / or "—".

[0017] In one embodiment, when there is a first text box, the RPA robot is produced, including a screenshot ID, a corresponding preset field, and the location of the content data corresponding to the corresponding preset field, including: producing an RPA robot, including a screenshot ID, a corresponding preset field, a second text box content extraction algorithm and the location of the second text box corresponding to the corresponding preset field.

[0018] In one embodiment, when the first text box does not exist, the making of the RPA robot, including the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field, includes: making the RPA robot, including the screenshot ID, the corresponding preset field, the starting coordinate location of the content data corresponding to the corresponding preset field, a text dynamic extension recognition algorithm, and semantic recognition;

[0019] The dynamic text extension recognition includes extending rightward and downward based on the starting coordinate position of the content data to identify adjacent characters, and judging whether the adjacent characters belong to the content data to be extracted based on semantic recognition, thereby obtaining the content data to be extracted.

[0020] In one embodiment, the starting coordinate position of the first character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the first character; the starting coordinate position of the second character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the second character; the starting coordinate position of the third character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the third character.

[0021] In one embodiment, the first starting coordinate point is the upper left corner of the starting position, and the first ending coordinate point is the lower right corner of the ending position; or, the first starting coordinate point is the lower left corner of the starting position, and the first ending coordinate point is the upper right corner of the ending position.

[0022] In one embodiment, the screenshot ID retains the serial number, name or other unique identification code of the screenshot.

[0023] In a second aspect, an embodiment provides a computer-readable storage medium, wherein the medium stores a program, and the program can be loaded by a processor to execute the data extraction RPA robot production method described in any one of the above embodiments.

[0024] The beneficial effects of the present invention are:

[0025] By obtaining a screenshot containing a preset field and identifying the preset field based on the screenshot, the screenshot ID corresponding to the preset field can be obtained, and the preset field can be identified based on the obtained screenshot. Since the location of the content data corresponding to the preset field is identified based on the identified preset field, the location of the data content corresponding to the preset field to be extracted can be obtained. In this way, an RPA robot can be created based on the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field, thereby obtaining a data extraction RPA robot based on location positioning, reducing the workload of RPA robot creation and greatly reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flowchart of a method for producing a data extraction RPA robot based on location positioning according to an embodiment of the present application;

[0027] Figure 2 This is a schematic diagram of the arrangement of field names and content data in the first embodiment of the present application;

[0028] Figure 3 This is a schematic diagram of the arrangement of field names and content data in the second embodiment of the present application;

[0029] Figure 4 This is a schematic diagram of the arrangement of field names and content data in the third embodiment of the present application;

[0030] Figure 5 This is a schematic diagram of the arrangement of field names and content data in the fourth embodiment of the present application. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below by means of specific embodiments in conjunction with the accompanying drawings. Similar elements in different embodiments are numbered with associated similar elements. In the following embodiments, many detailed descriptions are provided to enable the present application to be better understood. However, those skilled in the art will readily appreciate that some of the features may be omitted in different circumstances, or may be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification. This is to avoid the core portion of the present application being overwhelmed by excessive descriptions, and for those skilled in the art, it is not necessary to describe these related operations in detail. They will fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0032] In addition, the features, operations, or characteristics described in the specification may be combined in any appropriate manner to form various embodiments. Furthermore, the steps or actions in the method description may be reordered or adjusted in a manner readily apparent to those skilled in the art. Therefore, the various sequences in the specification and drawings are provided solely for the purpose of clearly describing a particular embodiment and are not intended to be mandatory, unless otherwise specified.

[0033] The serial numbers assigned to the components in this document, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0034] Currently, data extraction at stroke centers requires manual data extraction for each version of the data source software. The stroke center requires a total of 357 fields, and the data for these fields comes from various systems. RPA is needed to create a robot for collecting and processing each field. The information systems used by different hospitals are likely provided by different information companies, which may also have multiple versions of the same system. With over a hundred HIS software companies nationwide, locating the specific software and interface for a field is extremely labor-intensive. If RPA could also automatically locate the software system and interface where a field resides, labor costs would be significantly reduced.

[0035] During the research, the applicant found that if RPA is to automatically locate the software system and interface where the field is located, it is a feasible option to first find a screenshot of the software interface where the field is located and automatically locate it from the screenshot. However, in order to further improve work efficiency and reduce the workload of RPA robot production, it becomes an urgent problem to realize automatic positioning of preset field-related data based on the obtained screenshots to obtain an RPA robot that extracts data through automatic positioning.

[0036] In view of this, an embodiment of the present application provides a method and medium for producing a data extraction RPA robot based on position positioning. By obtaining a screenshot with a preset field and identifying the preset field based on the screenshot, a screenshot ID corresponding to the preset field can be obtained, and the preset field can be obtained from the obtained screenshot. Based on the identified preset field, the location of the content data corresponding to the preset field is identified, and the location of the data content corresponding to the preset field to be extracted can be obtained. In this way, an RPA robot can be produced based on the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field, thereby obtaining a data extraction RPA robot based on position positioning, reducing the workload of RPA robot production and greatly reducing labor costs.

[0037] The location-based data extraction RPA robot production method of an embodiment of the present application can be applied to a computer system, which includes a processor and a computer storage medium, at least one processor being used to load and execute the program of the location-based data extraction RPA robot production method and perform processing.

[0038] A method for producing a data extraction RPA robot based on location positioning in the embodiment of this application, please refer to Figure 1 ,include:

[0039] Step S10: obtaining a screenshot containing a preset field, and identifying the preset field based on the screenshot.

[0040] By obtaining a screenshot with preset fields, the preset fields in the screenshot can be first identified based on the screenshot.

[0041] In one embodiment, when the correspondence between the preset fields and the screenshots is unclear, in order to obtain a screenshot containing the preset fields, the screenshot can be first obtained, and then, based on the obtained screenshot, the preset fields in the screenshot can be obtained through OCR recognition to obtain the screenshot containing the preset fields. For example, it may be known that a certain screenshot contains preset fields, but it is not known which preset fields exist. It may also be unknown whether the screenshot contains preset fields, but it can be determined through OCR recognition whether and which preset fields exist in the screenshot.

[0042] In one embodiment, if the correspondence between preset fields and screenshots is clear, to obtain a screenshot containing a preset field, the screenshot containing the content data corresponding to the preset field can be directly obtained. For example, if both preset field A and preset field B have a correspondence with screenshot M, if the content data corresponding to preset field A is to be extracted, screenshot M can be directly obtained based on this correspondence.

[0043] Step S20 : Based on the identified preset field, the location of the content data corresponding to the preset field is identified.

[0044] Based on the identified preset field, the location of the content data corresponding to the preset field is identified, and the location of the data content corresponding to the preset field to be extracted can be obtained.

[0045] The applicant found in the research that there may be corresponding text boxes for the preset fields to be identified and their corresponding content data, or there may not be corresponding text boxes. Please refer to Figures 2 to 4 , are all ways of expressing the patient's basic information, among which name and gender are preset fields, Zhang San is the content data of the name, and male is the content data of the gender. Figure 2 and Figure 3For preset fields and their corresponding content data, there are corresponding text boxes. Figure 4 For the case where there is no corresponding text box for the preset field and its corresponding content data. Therefore, how to get a solution that takes into account the above two situations becomes a technical difficulty. In view of this problem, in one embodiment of the present application, step S20 includes:

[0046] For any preset field identified, such as "name", identify whether there is a first text box in which the first text content only includes the preset field, wherein the first text content does not include punctuation marks. If Figure 2 and Figure 3 If there is a first text box, then search rightward within the first identical content area for a second text box adjacent to the right. The first identical content area refers to an area within a preset distance threshold from the right edge of the first text box, for example, an area within a preset distance threshold from the right edge of the first text box for the name. If Figure 2 As shown, if the border of the text box adjacent to the right is found in the first same content area, it is considered that there is a second text box adjacent to the right, and the position of the second text box is used as the position of the content data of any of the above-mentioned preset fields (such as name).

[0047] If Figure 3 As shown, if the border of the text box adjacent to the right is not found in the first same content area, it means that the second text box is not to the right of the first text box, but below the first text box, then a search is made downward for the second text box adjacent to the bottom that is aligned with the left end of the first text box, and the position of the second text box adjacent to the bottom is used as the position of the content data of any of the above-mentioned preset fields.

[0048] In one embodiment, the position of the second text box can be represented by a diagonal coordinate point, or by coordinate points at three or four corners. In the case of a diagonal coordinate point, it can be the upper left corner coordinate point and the lower right corner coordinate point, or it can be the lower left corner coordinate point and the upper right corner coordinate point of the second text box.

[0049] It is understandable that for those skilled in the art, the first preset distance threshold can be set according to actual needs. In one embodiment, the first preset distance threshold is 10px.

[0050] If the first text box does not exist, it may be Figure 4In the case shown, if the first text box does not exist, the content data corresponding to the preset field may be on the right side of the preset field or below the preset field. Therefore, in one embodiment, if the first text box does not exist, the first starting coordinate point and the first ending coordinate point of the preset field are identified, for example, the starting coordinate point of the "surname" preset field and the ending coordinate point of the "name" preset field are identified. In one embodiment, taking "name" as an example, the first starting coordinate point is the upper left corner of the starting position, that is, the upper left corner of "surname", and the first ending coordinate point is the lower right corner of the ending position, that is, the lower right corner of "name". In one embodiment, the first starting coordinate point is the lower left corner of the starting position, that is, the lower left corner of "surname", and the first ending coordinate point is the upper right corner of the ending position, that is, the upper right corner of "name".

[0051] First, determine whether corresponding content data exists on the right side. Specifically, based on the first end coordinate point, search rightward for the first character adjacent to the right within the second identical content area. Then determine whether the first character adjacent to the right is a preset separator character. If so, search rightward for the second character adjacent to the right within the second identical content area based on the second end coordinate point of the first character. If the second character is found, the starting coordinate position of the searched second character is used as the starting coordinate position of the content data of any of the preset fields, thereby finding the starting coordinate position of the content data corresponding to the preset field. Separator characters include ":" (colon) and / or "—" (dash). The applicant discovered during research that, because a preset field may be followed by ":" or "—," in this case, the identified first character is not the corresponding content data. Therefore, it is necessary to further search rightward in the same manner to determine whether a second character adjacent to the right exists. If the second character is found, the starting coordinate position of the searched second character is used as the starting coordinate position of the content data of any of the preset fields. If the first character is not a preset separator character, the starting coordinate position of the first character is used as the starting coordinate position of the content data of any of the preset fields. The second identical content area refers to an area of equal height to the preset field within a second preset distance threshold range from the coordinate point based on the search. For example, when searching for the first character, the area is based on the first end coordinate point. In this case, the second identical content area refers to an area of equal height to the preset field within a second preset distance threshold range from the right distance of the first end coordinate point. When searching for the second character, the area is based on the second end coordinate point. In this case, the second identical content area refers to an area of equal height to the preset field within a second preset distance threshold range from the right distance of the second end coordinate point.

[0052] It is understandable that for those skilled in the art, the second preset distance threshold can be set according to actual needs. In one embodiment, the second preset distance threshold is 10px.

[0053] In some embodiments, the starting coordinate position of the first character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the first character; the starting coordinate position of the second character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the second character.

[0054] If the first or second character is not found, it means that the corresponding content data is not to the right of the preset field, but below it. In this case, the X-axis coordinate of the first starting coordinate point is used as the starting horizontal coordinate of the next row to search for the third character below and to the right. The starting coordinate position of the third character is used as the starting coordinate position of the content data of any of the above preset fields. Because the starting position of the content data may not be aligned with the starting position of the preset field in the vertical direction, the X-axis coordinate of the first starting coordinate point is used as the starting horizontal coordinate of the next row to search for the third character below and to the right.

[0055] In one embodiment, the starting coordinate position of the third character includes the coordinate position of the upper left corner and / or the coordinate position of the lower left corner of the third character.

[0056] Step S30: Create an RPA robot, including a screenshot ID, a corresponding preset field, and the location of the content data corresponding to the corresponding preset field.

[0057] In one embodiment, an RPA robot is created, including a screenshot ID, a corresponding preset field, an algorithm based on the second text box content extraction, and the location of the second text box corresponding to the corresponding preset field. Based on the explanation of step S20 above, for example, Figure 2 and Figure 3 As shown, based on the obtained screenshot ID, the corresponding preset field "Name," the algorithm for extracting the content of the second text box (i.e., the algorithm for extracting all the content data in the second text box where "Zhang San" is located), and the location of the second text box corresponding to the preset field (i.e., the location of the second text box where "Zhang San" is located), a data extraction RPA is created to obtain the content data corresponding to the preset field "Name." This implements the creation of a data extraction RPA robot.

[0058] In one embodiment, when the first text box does not exist, an RPA robot can be created based on the screenshot ID, the corresponding preset field, the starting coordinate position of the content data corresponding to the corresponding preset field, the text dynamic extension recognition algorithm and the semantic recognition. The text dynamic extension recognition includes extending rightward and downward to identify adjacent characters based on the starting coordinate position of the content data, and judging whether the adjacent characters belong to the content data to be extracted based on the semantic recognition, thereby obtaining the content data to be extracted. For example, please refer to Figure 5, based on the obtained screenshot ID and the corresponding preset field "department name", there is a second character on the right. Therefore, the starting coordinate position of the second character "new" is used as the starting coordinate position where the content data is located, and adjacent characters are identified by extending to the right and downwards. In one embodiment, the rightward extension is based on the end coordinate point of the current character, and whether there are adjacent characters on the right is searched in the second same content area until the end. In Figure 5 the shown embodiment, the rightward extension is recognized until "three" ends. The downward extension is based on the starting coordinate position of the content data, that is, the X-axis coordinate of the starting coordinate position of "new" is used as the starting abscissa of the next line to search for the third adjacent character below. Combining the above rightward and downward extensions to identify adjacent characters and semantic recognition, the content data to be extracted is obtained. In Figure 5 the embodiment, after the RPA robot made obtains the starting coordinate position of the content data, it can obtain the content data to be extracted, namely "Neonatal and Maternal and Child Health Care Department", based on the text dynamic extension recognition algorithm and semantic recognition plug-in set inside the RPA robot. Those skilled in the art can understand that since the semantic recognition model can adopt the existing technology model and can be used as a plug-in to be called during the execution of the RPA robot, the specific semantic recognition algorithm will not be elaborated.

[0059] Based on the above method for making an RPA robot for data extraction based on position positioning in one embodiment, by obtaining a screenshot with a preset field and identifying the preset field based on the screenshot, the screenshot ID corresponding to the preset field can be obtained, and the preset field can be recognized from the screenshot obtained. Based on the recognized preset field, the position where the content data corresponding to the preset field is located can be recognized, and the position where the data content corresponding to the preset field to be extracted is located can be obtained. In this way, an RPA robot can be made based on the screenshot ID, the corresponding preset field, and the position where the content data corresponding to the preset field is located, so as to obtain an RPA robot for data extraction based on position positioning, reducing the workload of making the RPA robot and greatly reducing the labor cost.

[0060] In one embodiment of the present application, a computer-readable storage medium is provided, and a program is stored on the storage medium. The stored program includes the method that can be loaded and processed by a processor in any of the above embodiments.

[0061] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer program. When all or part of the functions in the above embodiments are implemented by computer program, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above functions can be implemented. In addition, when all or part of the functions in the above embodiments are implemented by computer program, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and saved in the memory of the local device by downloading or copying, or the system of the local device is updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be implemented.

[0062] The above examples are used to illustrate the present invention, which are only used to help understand the present invention and are not intended to limit the present invention. Those skilled in the art can make several simple deductions, modifications or substitutions based on the concept of the present invention.

Claims

1. A method for producing a data extraction RPA robot based on location positioning, characterized in that: include: Obtaining a screenshot containing a preset field, and identifying the preset field based on the screenshot; Based on the identified preset field, identifying the location of the content data corresponding to the preset field includes: For any identified preset field, identifying whether there is a first text box in which the first text content only includes the preset field, and the first text content does not include punctuation marks; If a first text box exists, a search is performed to the right within the first identical content area for a second text box adjacent to the right. If a second text box adjacent to the right exists, the position of the second text box is used as the position of the content data of any one of the preset fields. If a second text box adjacent to the right does not exist, a search is performed downward for a second text box adjacent to the bottom that is aligned with the left end of the first text box, and the position of the second text box adjacent to the bottom is used as the position of the content data of any one of the preset fields. The position of the second text box includes: the coordinate points of the upper left corner and the lower right corner of the second text box, or the coordinate points of the lower left corner and the upper right corner of the second text box. The first identical content area refers to an area within a first preset distance threshold range from the right edge of the first text box. If the first text box does not exist, identify the first starting coordinate point and the first ending coordinate point of the preset field; based on the first ending coordinate point, search the adjacent first character to the right in the second same content area, and determine whether the adjacent first character is a preset spacing character; if so, based on the second ending coordinate point of the first character, search the second character adjacent to the right to the right in the second same content area; if the second character is found, use the starting coordinate position of the searched second character as the starting coordinate position of the content data of any one of the preset fields; if the first character is not a preset spacing character, use the starting coordinate position of the first character as the starting coordinate position of the content data of any one of the preset fields; if the first character or the second character is not found, use the X-axis coordinate of the first starting coordinate point as the starting horizontal coordinate of the next row to search the adjacent third character to the right, and use the starting coordinate position of the third character as the starting coordinate position of the content data of any one of the preset fields; the second same content area refers to an area of equal height to the preset field within a second preset distance threshold range from the coordinate point based on the first starting coordinate point, and the spacing characters include ":" and / or "—"; Create an RPA robot, including the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field.

2. The method for producing a data extraction RPA robot according to claim 1, wherein: The method of obtaining a screenshot of a preset field includes: A screenshot is obtained, and preset fields in the screenshot are obtained through OCR recognition based on the obtained screenshot, so as to obtain a screenshot containing the preset fields.

3. The method for producing a data extraction RPA robot according to claim 1, wherein: The method of obtaining a screenshot of a preset field includes: Based on the correspondence between the preset fields and the screenshots, the screenshot containing the content data corresponding to the preset fields to be extracted is obtained.

4. The method for producing a data extraction RPA robot according to claim 1, wherein: When there is a first text box, the RPA robot is produced, including a screenshot ID, a corresponding preset field, and the location of the content data corresponding to the corresponding preset field, including: producing an RPA robot, including a screenshot ID, a corresponding preset field, a second text box content extraction algorithm and the location of the second text box corresponding to the corresponding preset field.

5. The method for producing a data extraction RPA robot according to claim 1, wherein: In the absence of the first text box, the production of the RPA robot, including the screenshot ID, the corresponding preset field, and the location of the content data corresponding to the corresponding preset field, includes: production of the RPA robot, including the screenshot ID, the corresponding preset field, the starting coordinate location of the content data corresponding to the corresponding preset field, the text dynamic extension recognition algorithm and semantic recognition; The dynamic text extension recognition includes extending rightward and downward based on the starting coordinate position of the content data to identify adjacent characters, and judging whether the adjacent characters belong to the content data to be extracted based on semantic recognition, thereby obtaining the content data to be extracted.

6. The method for producing a data extraction RPA robot according to claim 1, wherein: The starting coordinate position of the first character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the first character; the starting coordinate position of the second character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the second character; the starting coordinate position of the third character includes the upper left corner coordinate position and / or the lower left corner coordinate position of the third character.

7. The method for producing a data extraction RPA robot according to claim 1, wherein: The first starting coordinate point is the upper left corner of the starting position, and the first ending coordinate point is the lower right corner of the ending position; or, the first starting coordinate point is the lower left corner of the starting position, and the first ending coordinate point is the upper right corner of the ending position.

8. The method for producing a data extraction RPA robot according to claim 4 or 5, wherein: The screenshot ID retains the serial number, name or other unique identification code of the screenshot.

9. A computer-readable storage medium, characterized in that The medium stores a program, which can be loaded by a processor and execute the data extraction RPA robot production method according to any one of claims 1 to 8.

Images