CN116720489B - Page filling method and device, electronic equipment and computer readable storage medium - Google Patents
Page filling method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN116720489B CN116720489B CN202310987045.1A CN202310987045A CN116720489B CN 116720489 B CN116720489 B CN 116720489B CN 202310987045 A CN202310987045 A CN 202310987045A CN 116720489 B CN116720489 B CN 116720489B
- Authority
- CN
- China
- Prior art keywords
- page
- groups
- information units
- filling
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 91
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 75
- 238000000547 structure data Methods 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 11
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000015654 memory Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000014509 gene expression Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000013508 migration Methods 0.000 description 3
- 230000005012 migration Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 102100040653 Tryptophan 2,3-dioxygenase Human genes 0.000 description 1
- 101710136122 Tryptophan 2,3-dioxygenase Proteins 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a page filling method and device, electronic equipment and a computer readable storage medium, which can be applied to the technical field of computer front ends and the technical field of artificial intelligence. The page filling method comprises the following steps: extracting M groups of information units from the target demand statement; acquiring page structure data of a page to be filled; processing the page structure data, and determining control identifications of M input control frames which are matched with M groups of information units one by one; based on control identifications of M input control boxes, calling a preset filling operation program, and filling M groups of information units into the M input control boxes in a one-to-one matching manner; the method can realize information structuring and dynamic and intelligent matching of the form input control, and improve the accuracy and efficiency of form filling.
Description
Technical Field
The invention relates to the technical field of computer front ends and artificial intelligence, in particular to a page filling method, a device, equipment, a medium and a program product.
Background
With the development of services, service management operations often involve multiple service systems, and a large amount of unstructured text needs to be processed in service processing operations to complete the entry of service page form information.
At present, the method for inputting page form information has some problems, such as manual analysis method needs to manually analyze unstructured text to obtain filling items and then manually input, and the processing efficiency is low; for example, by identifying automatic form filling of form elements based on an RPA method, although automatic form filling can be realized, the page content identification error rate is high when the layout of the page structure is changeable.
Disclosure of Invention
In view of the foregoing, the present invention provides a page filling method, apparatus, device, medium, and program product.
In one aspect of the present invention, there is provided a page filling method including:
extracting M groups of information units from a target demand statement, wherein the target demand statement is used for representing the input demand of a user;
acquiring page structure data of a page to be filled, wherein the page to be filled comprises a form area, and the form area comprises M input control frames;
processing the page structure data, and determining control identifications of M input control frames which are matched with M groups of information units one by one;
and calling a preset filling operation program based on the control identifications of the M input control boxes, and filling the M groups of information units into the M input control boxes in a one-to-one matching manner.
According to an embodiment of the present invention, wherein each group of information units includes a tag part and a content part;
processing the page structure data, and determining control identifications of M input control frames which are matched with M groups of information units one by one comprises:
extracting M structural unit data sets corresponding to the M tag parts one by one from page structural data according to the M tag parts included in the M groups of information units;
inputting the M structural unit data sets into a first language model, performing context semantic structure analysis processing on the structural unit data sets through the first language model, and outputting control identifications of M input control boxes which are matched with the M groups of information units one by one.
According to an embodiment of the present invention, extracting M groups of information units from a target demand statement includes:
and inputting the target requirement statement into a second language model, carrying out structuring processing on the target requirement statement through the second language model, and outputting M groups of information units.
According to an embodiment of the invention, wherein:
the first language model and the second language model are obtained through training by a supervised training method or a reinforcement learning training method.
According to an embodiment of the present invention, before extracting M groups of information units from the target requirement statement, the method further includes:
Displaying a page to be filled, wherein the page to be filled further comprises a dialogue area;
based on the input operation of the user on the dialogue area, acquiring a target demand statement, and triggering the operation of extracting M groups of information units from the target demand statement through the input operation.
According to an embodiment of the present invention, the dialogue area includes an input box and a reply box, and based on an input operation of a user on the dialogue area, obtaining the target requirement sentence includes:
acquiring an input operation for an input box;
in response to an input operation, a target demand statement is populated into the input box.
According to an embodiment of the present invention, after extracting M groups of information units, the method further includes:
displaying target characters used for reflecting M groups of information units in a reply box of the dialogue area;
acquiring a drag operation aiming at a dialogue area;
and responding to the drag operation, moving the target text from the dialogue area to the form area, triggering the operation of acquiring the page structure data through the drag operation, processing the page structure data, calling a preset filling operation program, and filling M groups of information units into M input control boxes in a one-to-one matching mode.
The invention further provides a page filling device which comprises an extraction module, a first acquisition module, a processing module and a filling module.
The extraction module is used for extracting M groups of information units from target demand sentences, wherein the target demand sentences are used for representing the input demands of users;
the first acquisition module is used for acquiring page structure data of a page to be filled, wherein the page to be filled comprises a form area, and the form area comprises M input control boxes;
the processing module is used for processing the page structure data and determining control identifications of M input control frames which are matched with the M groups of information units one by one;
and the filling module is used for calling a preset filling operation program based on the control identifications of the M input control boxes and filling the M groups of information units into the M input control boxes in a one-to-one matching manner.
According to an embodiment of the present invention, wherein each group of information units includes a tag part and a content part;
the processing module comprises an extraction unit and a first processing unit.
The extraction unit is used for extracting M structural unit data groups corresponding to the M label parts one by one from the page structural data according to the M label parts included in the M groups of information units;
the first processing unit is used for inputting the M structural unit data sets into the first language model, carrying out context semantic structure analysis processing on the structural unit data sets through the first language model, and outputting control identifications of M input control boxes which are matched with the M groups of information units one by one.
According to an embodiment of the invention, the extraction module comprises:
the second processing unit is used for inputting the target requirement statement into the second language model, carrying out structuring processing on the target requirement statement through the second language model and outputting M groups of information units.
According to an embodiment of the invention, wherein:
the first language model and the second language model are obtained through training by a supervised training method or a reinforcement learning training method.
According to the embodiment of the invention, the device further comprises a first display module and a second acquisition module.
The first display module is used for displaying a page to be filled before M groups of information units are extracted from the target demand statement, wherein the page to be filled further comprises a dialogue area;
the second acquisition module is used for acquiring the target requirement statement based on the input operation of the user on the dialogue area, and triggering the operation of extracting M groups of information units from the target requirement statement through the input operation.
According to the embodiment of the invention, the dialogue area comprises an input box and a reply box, and the second acquisition module comprises an acquisition unit and a filling unit.
The input device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring input operation aiming at an input box;
and the filling unit is used for responding to the input operation and filling the target requirement statement into the input box.
According to the embodiment of the invention, the device further comprises a second display module, a third acquisition module and a mobile module.
The second display module is used for displaying target characters used for reflecting the M groups of information units in a reply frame of the dialogue area after the M groups of information units are extracted;
the third acquisition module is used for acquiring the drag operation aiming at the dialogue area;
and the moving module is used for responding to the drag operation, moving the target text from the dialogue area to the form area, triggering the operation of acquiring the page structure data through the drag operation, processing the page structure data, calling a preset filling operation program and filling M groups of information units into M input control boxes in a one-to-one matching mode.
Another aspect of the present invention provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the page filling method described above.
Another aspect of the invention also provides a computer readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above page filling method.
Another aspect of the invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the above page filling method.
According to the embodiment of the invention, the method obtains the structured information through the structuring processing of unstructured natural language, and further obtains the control identification of the input control box through the processing of page structure data, so that the matching of the information unit and the input control box is realized, and further, the filling operation program can be invoked to correctly identify the position of each input control box in the page to be filled according to the control identification, and the automatic filling of the input control box of the information unit in the form area is completed. Therefore, the information can be automatically structured according to the natural language expression of the information processing requirement input by the user, the page structure of the form can be intelligently analyzed, the automatic filling of the form item is completed, and the efficient, convenient and humanized interaction with the user is realized. In the method of the embodiment of the invention, different from the conventional visual Recognition (RPA) or layout analysis (by means of JavaScript) method, the page structure data is processed to obtain the control identification of the input control frame, so that the position of each input control frame in the page to be filled can be correctly recognized, the method is not limited to the layout of the page, has better adaptability to the page with any structural layout, solves the problems of higher page content recognition error rate and higher matching failure rate in the related art, realizes the dynamic and intelligent matching of information structuring and form input control by organically integrating the user requirement and the deconstructing capability of the form source-code, improves the accuracy and efficiency of filling, improves the working efficiency and shortens the task completion time.
Drawings
The foregoing and other objects, features and advantages of the invention will be apparent from the following description of embodiments of the invention with reference to the accompanying drawings, in which:
FIG. 1 shows an application scene diagram of a page filling method, device, equipment and medium according to an embodiment of the invention;
FIG. 2 shows a flow chart of a page filling method according to an embodiment of the invention;
FIG. 3 shows a schematic diagram of an operator interface for a page to be filled in according to an embodiment of the invention;
FIG. 4 shows a flow chart of a method of processing page structure data according to an embodiment of the invention;
FIG. 5 shows a block diagram of a page filling apparatus according to an embodiment of the present invention;
fig. 6 shows a block diagram of an electronic device adapted to implement the page filling method according to an embodiment of the invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.
Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In embodiments of the present invention, the data involved (e.g., including but not limited to user personal information) is collected, updated, analyzed, processed, used, transmitted, provided, invented, stored, etc., all in compliance with relevant legal regulations, used for legal purposes, and without violating the public welfare. In particular, necessary measures are taken for personal information of the user, illegal access to personal information data of the user is prevented, and personal information security, network security and national security of the user are maintained.
In embodiments of the present invention, the user's authorization or consent is obtained before the user's personal information is obtained or collected.
With the development of services, service management operations often involve multiple service systems, and a large amount of unstructured text needs to be processed in service processing operations to complete the entry of service page form information.
The automatic input method for the page form information in the related art comprises the following steps:
identifying the automatic form filling of the table element based on the RPA method: and (3) by identifying page elements or picture contents marked by the source system one by one, simulating the operation of a person according to a preset corresponding page layout rule, and filling the page elements or picture contents into the target system one by one. However, the method depends on a preset page layout structure in the automatic form filling process, and when the layout of the page structure is changeable, the page content identification error rate is higher, so that the method is only suitable for the scene that the page layout structure is fixed, has larger limitation and has obvious defects of insufficient flexibility.
The method analyzes the structural code of the form by experience, such as analyzing the corresponding relation between the guessed element and the structured data according to label type, id naming, class naming and the like, and has the problems of poor accuracy and high matching failure rate because the spatial position depends on the guessed result.
In view of this, an embodiment of the present invention provides a page filling method, including:
extracting M groups of information units from a target demand statement, wherein the target demand statement is used for representing the input demand of a user; acquiring page structure data of a page to be filled, wherein the page to be filled comprises a form area, and the form area comprises M input control frames; processing the page structure data, and determining control identifications of M input control frames which are matched with M groups of information units one by one; and calling a preset filling operation program based on the control identifications of the M input control boxes, and filling the M groups of information units into the M input control boxes in a one-to-one matching manner.
FIG. 1 illustrates an application scenario diagram of a page filling method, apparatus, device, medium, and program product according to an embodiment of the present invention.
As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 through the network 104 using at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various communication client applications, such as a shopping class application, a web browser application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.
The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.
In the application scenario of the embodiment of the present invention, a user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to input a requirement statement for representing the content of a form, initiate a request for structuring processing of the requirement statement to the server, respond to the user request, extract M groups of information units from the requirement statement, return the M groups of information units to the user through the first terminal device 101, the second terminal device 102, and the third terminal device 103, initiate a request for completing automatic filling of a page form to the server again through the first terminal device 101, the second terminal device 102, and the third terminal device 103, respond to the user request, the server 105 obtains page structure data of a form page, obtains control identifiers of M input control boxes that are matched with the M groups of information units one by one through processing of the page structure data, and invokes a predetermined filling operation program, and fills the M groups of information units into the M input control boxes one by one based on the control identifiers of the M input control boxes.
It should be noted that, the page filling method provided by the embodiment of the present invention may be generally performed by the server 105. Accordingly, the page filling device provided by the embodiment of the present invention may be generally disposed in the server 105. The page filling method provided by the embodiment of the present invention may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103 and/or the server 105. Accordingly, the page filling apparatus provided by the embodiment of the present invention may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103 and/or the server 105.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The page filling method according to the embodiment of the present invention will be described in detail below with reference to fig. 2 to 6 based on the scenario described in fig. 1.
Fig. 2 shows a flow chart of a page filling method according to an embodiment of the invention.
As shown in fig. 2, the page filling method of this embodiment includes operations S201 to S204.
In operation S201, extracting M groups of information units from a target requirement sentence, where the target requirement sentence is used to characterize an input requirement of a user, and M is a positive integer;
in operation S202, obtaining page structure data of a page to be filled, where the page to be filled includes a form area, and the form area includes M input control boxes;
in operation S203, the page structure data is processed, and control identifiers of M input control frames that are matched with M groups of information units one by one are determined;
in operation S204, a predetermined filling operation program is called based on the control identifications of the M input control boxes, and M groups of information units are filled into the M input control boxes in a one-to-one matching manner.
Fig. 3 shows a schematic diagram of an operation interface of a page to be filled in according to an embodiment of the present invention.
As shown in fig. 3, a page to be filled includes a form area including a plurality of input control boxes, and an object of an embodiment of the present invention is to implement automatic filling of the plurality of input control boxes in the form area based on a target requirement statement input by a user.
The target requirement statement is used for representing the input requirement of a user, and the content of the target requirement statement is related to the content to be filled of each item to be filled (input control box) of the form area of the page to be filled.
For example: aiming at the scene of logging in a travel application input system by a user, the page to be filled contains a form area of the travel application input system shown in fig. 3, wherein the form area comprises a plurality of items to be filled (input control boxes) which are respectively: business trip people: _____; business trip location: _____; departure time: _____; business trip purpose: _____; the target requirement statement input by the user is related to the contents of the filling items, and specifically can be: "three 11 months 12 days plan business trip A to company headquarters to participate in new product release meeting".
It should be noted that, the target requirement statement is unstructured natural language, only needs to include the contents to be filled of each item to be filled (input control box) in the form area, and the statement expression mode and the description sequence of the items to be filled can be random.
According to the embodiment of the invention, for unstructured sentences input by a user, in the method of the embodiment of the invention, the target demand sentences are subjected to structuring processing through operation S201, M groups of information units are extracted from the target demand sentences, and the unstructured sentences are converted into structured information.
For example, a target demand sentence "plan business trip a to company headquarters to participate in new product release meeting every 11 months and 12 days" input by a user is structured to extract a business trip name, a departure time, a business trip place, and a business trip purpose from the above information, thereby obtaining 4 sets of information units: 1-business trip: thirdly, stretching; 2-departure time: 11 months and 12 days; 3-business trip location: market A; 4-purpose of business trip: the aim of converting unstructured sentences into structured information is fulfilled when new products of headquarters are participated in the publishing meeting.
The M groups of information units obtained through processing are in one-to-one correspondence with the M input control boxes in the form area.
For example, the form area shown in FIG. 3 contains 4 input control boxes: "business trip person: _____; departure time: _____; business trip location: _____; business trip purpose: _____ ", and 4 sets of information elements described above: "1-business trip: thirdly, stretching; 2-departure time: 11 months and 12 days; 3-business trip location: market A; 4-purpose of business trip: the new product release meeting at the headquarter is "one-to-one".
According to the embodiment of the invention, after the M groups of information units are extracted from the target requirement statement, automatic filling of the M input control boxes for the M groups of information units in the form area is required to be completed. To implement automatic population, a predetermined population operation program may be invoked to complete automatic population, and when the predetermined population operation program is invoked, basic parameters need to be determined: the control identifications of the M input control boxes are used for enabling the operation program to correctly identify the positions of the input control boxes in the page to be filled according to the control identifications.
Based on this, in the embodiment of the present invention, by acquiring the page structure data of the page to be filled in operation S202, and processing the page structure data in operation S203, control identifiers of M input control boxes that are one-to-one matched with M groups of information units are determined, so that one-to-one matching of M groups of information units with M input control boxes is achieved, for example, information unit 1 "business trip: zhang San ", the corresponding control is identified as" name-1", information element 2" departure time: 11 month 12 day ", the corresponding control is identified as" date-2", etc.
The page structure data of the page to be filled is specifically form structure source code data of the page, the layout structure form of the page to be filled can be reflected, context semantic analysis is carried out on the page structure data, and control identification information of each input control box can be extracted from the page structure data according to the inherent specific data structure of the source code data.
After the control identifications of the M input control boxes are determined, a preset filling operation program can be called, and M groups of information units are automatically filled into the M input control boxes in a one-to-one matching mode.
According to the embodiment of the invention, the method obtains the structured information through the structuring processing of unstructured natural language, and further obtains the control identification of the input control box through the processing of page structure data, so that the matching of the information unit and the input control box is realized, and further, the filling operation program can be invoked to correctly identify the position of each input control box in the page to be filled according to the control identification, and the automatic filling of the input control box of the information unit in the form area is completed. Therefore, the information can be automatically structured according to the natural language expression of the information processing requirement input by the user, the page structure of the form can be intelligently analyzed, the automatic filling of the form item is completed, and the efficient, convenient and humanized interaction with the user is realized. In the method of the embodiment of the invention, different from the conventional visual Recognition (RPA) or layout analysis (by means of JavaScript) method, the page structure data is processed to obtain the control identification of the input control frames, so that the positions of the input control frames in the page to be filled can be correctly recognized, the method is not limited to the layout of the page, has better adaptability to the page with any structural layout, solves the problems of higher page content recognition error rate and higher matching failure rate in the related art, realizes the dynamic and intelligent matching of information structuring and form input control by organically integrating the user requirement and the deconstructing capability of the form source code, improves the accuracy and efficiency of filling, improves the working efficiency and shortens the task completion time.
According to an embodiment of the present invention, before extracting the M groups of information units from the target demand statement, an operation of acquiring the target demand statement is further included. Wherein obtaining the target demand statement comprises:
displaying a page to be filled, wherein the page to be filled further comprises a dialogue area;
based on the input operation of the user on the dialogue area, acquiring a target demand statement, and triggering the operation of extracting M groups of information units from the target demand statement through the input operation.
As shown in fig. 3, the page to be filled includes a dialogue area, where the dialogue area includes an input box and a reply box, and the obtaining the target requirement statement includes:
acquiring an input operation for an input box;
in response to an input operation, a target demand statement is populated into the input box.
According to an embodiment of the present invention, after extracting M groups of information units, the method further includes: and displaying target characters used for reflecting M groups of information units in a reply box of the dialogue area.
For example, as shown in fig. 3, the user logs in a travel application entry system page, and inputs a target demand statement in an input box: the method comprises the steps that a business trip A is planned to be a new product release meeting in a company headquarter on a three 11 month 12 day schedule, an operation of extracting M groups of information units from a target demand statement is triggered through input operation of a user, after the target demand statement is structured, a result of the structured processing is displayed to the user in a reply frame: "business trip person: zhang Sanzhi; "departure time: day 11 month 12 "… ….
According to an embodiment of the present invention, after extracting M groups of information units, the method further includes:
acquiring a drag operation aiming at a dialogue area;
and responding to the drag operation, moving the target text from the dialogue area to the form area, triggering the operation of acquiring the page structure data through the drag operation, processing the page structure data, calling a preset filling operation program, and filling M groups of information units into M input control boxes in a one-to-one matching mode.
For example, as shown in fig. 3, after each group of information units of the structuring process is shown to the user in the reply box, the user drags the information units in the dialogue area to the form area, and the subsequent automatic filling operation is triggered through the drag operation of the user. Specifically, after the drag interaction is identified, reading a page structure code of a form of a travel application entry system, automatically matching corresponding input controls according to the content of the dragged structured information, and filling corresponding values into corresponding input control boxes in the form.
According to the embodiment of the invention, the operation of structuring unstructured natural sentences is automatically triggered and returned through user input, the operation of automatically filling the page forms is further automatically triggered through the dragging operation of the user, in the whole process, the user can finish the automatic filling of the forms by only inputting a requirement sentence and executing the dragging action, the system can intelligently find the input control elements matched with user information and finish the final filling assignment of the contents of the forms, the dynamic and intelligent matching of the information structuring and the form input elements is realized, the operation flow is greatly simplified, the development cost and the maintenance cost of a new interface for acquiring data across systems can be reduced, and the time and resources are saved.
FIG. 4 shows a flow chart of a method of processing page structure data according to an embodiment of the invention.
As shown in FIG. 4, the method for processing the page structure data and determining the control identifications of M input control frames matched with M groups of information units one by one comprises operations S401-S402.
In operation S401, M structural unit data sets corresponding to the M tag parts one by one are extracted from the page structural data according to the M tag parts included in the M sets of information units;
in operation S402, M structural unit data sets are input into a first language model, context semantic structure analysis processing is performed on the structural unit data sets through the first language model, and control identifications of M input control boxes that are matched with M groups of information units one by one are output.
According to an embodiment of the present invention, as shown in fig. 3, each group of information elements includes a label portion (key) and a content portion (value), and each input control box also corresponds to a control label.
For example, for an information unit: "business trip person: zhang Sanzhi; label (key) = "business trip person", content (value) = "Zhang san"; the input control box corresponding to the input control box also corresponds to a control label of 'business trip person'.
The page structure data, namely page list structure source code data, can reflect the layout structure form of a page to be filled, and the code adopts a relatively fixed data structure form and can be particularly divided into a plurality of structure unit data groups; each structural unit data set corresponds to one control label, and the structural unit data set corresponding to each control label can embody the page layout structure of the input control frame area. The method specifically comprises descriptions about control labels, descriptions about input control boxes and the like, wherein the descriptions about the input control boxes comprise control identifications of the input control boxes and values to be filled corresponding to the control identifications (namely contents to be filled of the input control boxes).
According to the embodiment of the present invention, according to the tag portion included in each information unit, it is possible to match the structural unit data group corresponding to the tag portion. For example, the field value of the tag part included in the information unit is matched with the name of the control tag included in the structure unit data group, and if the name of the control tag is the same as the field value of the tag part, the control tag is matched with the structure unit data group corresponding to the tag part. For example, in the description of the control label in the structural unit data set, the name of the control label is "business trip person", and then the structural unit data set and the information unit can be determined: "business trip person: zhang san corresponds.
According to the embodiment of the invention, after the corresponding structural unit data set is matched, the structural unit data set can be input into a first language model, the structural unit data set is subjected to context semantic structure analysis processing through the first language model, and the control identification of the input control box is extracted from the description content related to the input control box.
According to the embodiment of the invention, the page structure data is subjected to the context semantic structure analysis processing through the language model to obtain the control identification of the input control frame, so that the automatic filling operation program can correctly identify the position of each input control frame in the page to be filled, and the information structuring and the dynamic intelligent matching of the form input control are realized by utilizing the deconstructing capability of the model on the form source code. The method is based on the deconstructing capability of the model on the codes and does not depend on page visual layout, so that the control codes can be identified for pages with any structural layout, and the method has good adaptability.
According to an embodiment of the present invention, specifically, extracting M groups of information units from the target demand statement includes: and inputting the target requirement statement into a second language model, carrying out structuring processing on the target requirement statement through the second language model, and outputting M groups of information units.
According to the embodiment of the invention, the structured information in the natural language can be accurately identified by utilizing the language model to identify the natural sentence, and the result of the structured processing is used as the data basis for matching with the input control box subsequently, so that the guarantee is provided for finally realizing the automatic filling of the form.
According to an embodiment of the invention, the first language model and the second language model are trained by a supervised training method or a reinforcement learning training method.
In accordance with embodiments of the present invention, for the Model to better understand the form elements and complete the extraction tasks, a Supervised Fine-Tuning (also known as a Reward Model) method and a reinforcement learning strategy may be employed to Fine-tune the Model.
Wherein, supervised Fine Tuning (Supervised Fine-Tuning) is a Supervised learning method, which Fine tunes a model by training on annotation data. The specific process is as follows:
(1) Data preparation: first, training data related to the form filling task needs to be collected. Such data should include inputs (e.g., text prompts, form types, etc.) and outputs (e.g., expected fill values). The training data may be extracted from existing form filling systems or created by manual annotation.
(2) Data preprocessing: the collected data is preprocessed so that the model can be better understood and processed. The preprocessing step may include: text cleaning, special character removal, word segmentation, vocabulary construction, and the like.
(3) Fine tuning the model: and performing supervised fine tuning on the large-scale language model on the preprocessed data set. During training, cross entropy loss is used as an optimization target, and super parameters such as learning rate, batch size and the like are adjusted to obtain the optimal performance.
(4) Model evaluation: the trimmed model is evaluated using a validation set or test set to learn the effect of the model in the actual task. The evaluation can be performed using indexes such as accuracy, F1 score, etc.
Reward Model (Reward Model), which is a reinforcement learning based method, is tuned by optimizing the expected rewards. The specific process is as follows:
(1) Data preparation: as with supervised fine tuning, training data related to the form filling task needs to be collected.
(2) Data preprocessing: the collected data is preprocessed as with the supervised fine tuning.
(3) Agent model training: first, an initial proxy model is trained on the preprocessed data set using supervised learning.
(4) And (3) bonus function design: a reward function is designed to quantify the gap between the model generated form filling result and the actual expected form filling result. The reward function may consider the number of correctly filled fields, the number of incorrectly filled fields, and other task related metrics.
(5) Reinforcement learning training: the proxy model is trained using reinforcement learning algorithms (e.g., PPO, TRPO, etc.) to optimize the expected rewards. During training, the model generates actions (filling out forms) based on the current state (form content) and calculates rewards based on the rewards function. By constantly interacting with the environment (the form filling task), the model learning generates better form filling results.
(6) Policy migration: in the reinforcement learning training process, knowledge in the large-scale language model is migrated to the proxy model through a strategy migration technology. Policy migration can be achieved through knowledge distillation, parameter sharing and other methods.
(7) Model evaluation: as with supervised fine tuning, the model after reinforcement learning training is evaluated using a validation set or a test set. Besides indexes such as accuracy and F1 score, the robustness and generalization capability of the model in solving the form filling task can be evaluated.
By means of two methods of supervised fine tuning or rewarding models, a high-performance model can be effectively trained. The two methods can complement each other, and the accuracy and the stability of the model in practical application are improved together. In the actual operation, an appropriate method may be selected according to the task demand and the data amount or a combination of the two methods may be used.
Based on the page filling method, the invention further provides a page filling device. The device will be described in detail below in connection with fig. 5.
Fig. 5 shows a block diagram of a page filling apparatus according to an embodiment of the present invention.
As shown in fig. 5, the page filling apparatus 500 of this embodiment includes an extraction module 501, a first acquisition module 502, a processing module 503, and a filling module 504.
The extracting module 501 is configured to extract M groups of information units from a target requirement sentence, where the target requirement sentence is used to characterize an input requirement of a user;
The first obtaining module 502 is configured to obtain page structure data of a page to be filled, where the page to be filled includes a form area, and the form area includes M input control boxes;
the processing module 503 is configured to process the page structure data, and determine control identifiers of M input control frames that are matched with M groups of information units one by one;
and the filling module 504 is configured to invoke a predetermined filling operation program based on control identifiers of the M input control boxes, and fill the M groups of information units into the M input control boxes in a one-to-one matching manner.
According to the embodiment of the invention, the structured information is obtained through the structured processing of the unstructured natural language by the extraction module 501, the control identification of the input control box is obtained through the processing of the page structure data by the first acquisition module 502 and the processing module 503, the matching of the information unit and the input control box is realized, the position of each input control box in the page to be filled is accurately identified according to the control identification by the filling module 504, and the automatic filling of the input control box of the information unit in the form area is completed. Therefore, the information can be automatically structured according to the natural language expression of the information processing requirement input by the user, the page structure of the form can be intelligently analyzed, the automatic filling of the form item is completed, and the efficient, convenient and humanized interaction with the user is realized. The page structure data is processed through the first acquisition module 502 and the processing module 503 to obtain the control identification of the input control frame, so that the position of each input control frame in the page to be filled can be correctly identified, the page structure data is not limited to the layout of the page, the page structure data has good adaptability to pages with any structure layout, the problems of high page content identification error rate and high matching failure rate in the related art are solved, and the information structuring and the dynamic and intelligent matching of the form input control are realized through the organic fusion of the deconstructing capability of the user requirement and the form source code, the accuracy and the efficiency of the form filling are improved, the working efficiency is improved, and the task completion time is shortened.
According to an embodiment of the invention, each group of information elements comprises a tag part and a content part.
The processing module comprises an extraction unit and a first processing unit.
The extraction unit is used for extracting M structural unit data groups corresponding to the M label parts one by one from the page structural data according to the M label parts included in the M groups of information units;
the first processing unit is used for inputting the M structural unit data sets into the first language model, carrying out context semantic structure analysis processing on the structural unit data sets through the first language model, and outputting control identifications of M input control boxes which are matched with the M groups of information units one by one.
According to an embodiment of the invention, the extraction module comprises:
the second processing unit is used for inputting the target requirement statement into the second language model, carrying out structuring processing on the target requirement statement through the second language model and outputting M groups of information units.
According to an embodiment of the invention, wherein:
the first language model and the second language model are obtained through training by a supervised training method or a reinforcement learning training method.
According to the embodiment of the invention, the device further comprises a first display module and a second acquisition module.
The first display module is used for displaying a page to be filled before M groups of information units are extracted from the target demand statement, wherein the page to be filled further comprises a dialogue area;
the second acquisition module is used for acquiring the target requirement statement based on the input operation of the user on the dialogue area, and triggering the operation of extracting M groups of information units from the target requirement statement through the input operation.
According to the embodiment of the invention, the dialogue area comprises an input box and a reply box, and the second acquisition module comprises an acquisition unit and a filling unit.
The input device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring input operation aiming at an input box;
and the filling unit is used for responding to the input operation and filling the target requirement statement into the input box.
According to the embodiment of the invention, the device further comprises a second display module, a third acquisition module and a mobile module.
The second display module is used for displaying target characters used for reflecting the M groups of information units in a reply frame of the dialogue area after the M groups of information units are extracted;
the third acquisition module is used for acquiring the drag operation aiming at the dialogue area;
and the moving module is used for responding to the drag operation, moving the target text from the dialogue area to the form area, triggering the operation of acquiring the page structure data through the drag operation, processing the page structure data, calling a preset filling operation program and filling M groups of information units into M input control boxes in a one-to-one matching mode.
Any of the extraction module 501, the first acquisition module 502, the processing module 503, and the filling module 504 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules according to an embodiment of the present invention. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. At least one of the extraction module 501, the first acquisition module 502, the processing module 503, the population module 504 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable way of integrating or packaging circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the extraction module 501, the first acquisition module 502, the processing module 503, the population module 504 may be at least partially implemented as a computer program module which, when executed, may perform the corresponding functions.
Fig. 6 shows a block diagram of an electronic device adapted to implement the page filling method according to an embodiment of the invention.
As shown in fig. 6, an electronic device 600 according to an embodiment of the present invention includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. The processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. Processor 601 may also include on-board memory for caching purposes. Processor 601 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the invention.
In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The processor 601 performs various operations of the method flow according to an embodiment of the present invention by executing programs in the ROM 602 and/or the RAM 603. Note that the program may be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to embodiments of the present invention by executing programs stored in the one or more memories.
According to an embodiment of the invention, the electronic device 600 may also include an input/output (I/O) interface 605, the input/output (I/O) interface 605 also being connected to the bus 604. The electronic device 600 may also include one or more of the following components connected to a 6 input/output (I/O) interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to a 6 input/output (I/O) interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
The present invention also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present invention.
According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the invention, the computer-readable storage medium may include ROM 602 and/or RAM 603 and/or one or more memories other than ROM 602 and RAM 603 described above.
Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the method shown in the flowcharts. The program code means for causing a computer system to carry out the page filling method provided by the embodiment of the invention when the computer program product is run in the computer system.
The above-described functions defined in the system/apparatus of the embodiment of the present invention are performed when the computer program is executed by the processor 601. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the invention.
In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and/or installed from the removable medium 611. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the embodiment of the present invention are performed when the computer program is executed by the processor 601. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the invention.
According to embodiments of the present invention, program code for carrying out computer programs provided by embodiments of the present invention may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or in assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that the features recited in the various embodiments of the invention and/or in the claims may be combined in various combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the invention. In particular, the features recited in the various embodiments of the invention and/or in the claims can be combined in various combinations and/or combinations without departing from the spirit and teachings of the invention. All such combinations and/or combinations fall within the scope of the invention.
The embodiments of the present invention are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the invention is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the invention, and such alternatives and modifications are intended to fall within the scope of the invention.
Claims (8)
1. A method of page filling, comprising:
extracting M groups of information units from a target demand statement, wherein the target demand statement is used for representing the input demand of a user; wherein extracting M groups of information units from the target demand statement comprises: inputting the target requirement statement into a second language model, carrying out structuring processing on the target requirement statement through the second language model, and outputting the M groups of information units;
Acquiring page structure data of a page to be filled, wherein the page to be filled comprises a form area, and the form area comprises M input control boxes;
processing the page structure data, and determining control identifications of M input control frames which are matched with the M groups of information units one by one; wherein each group of the information units includes a tag part and a content part; processing the page structure data, wherein determining control identifications of M input control frames which are matched with the M groups of information units one by one comprises: extracting M structural unit data sets corresponding to the M tag parts one by one from the page structural data according to the M tag parts included in the M groups of information units; inputting the M structural unit data sets into a first language model, performing context semantic structure analysis processing on the structural unit data sets through the first language model, and outputting control identifications of M input control boxes which are matched with the M groups of information units one by one;
and calling a preset filling operation program based on the control identifications of the M input control boxes, and filling the M groups of information units into the M input control boxes in a one-to-one matching manner.
2. The method according to claim 1, characterized in that:
The first language model and the second language model are obtained through training by a supervised training method or a reinforcement learning training method.
3. The method of claim 1, further comprising, prior to extracting M sets of information elements from the target demand statement:
displaying the page to be filled, wherein the page to be filled further comprises a dialogue area;
and acquiring the target demand statement based on the input operation of the user on the dialogue area, and triggering the operation of extracting M groups of information units from the target demand statement through the input operation.
4. The method of claim 3, wherein the conversation zone includes an input box and a reply box, wherein obtaining the target demand statement based on a user input operation for the conversation zone includes:
acquiring an input operation aiming at the input box;
and responding to the input operation, and filling the target requirement statement into the input box.
5. The method of claim 4, further comprising, after extracting the M sets of information units:
displaying target characters used for reflecting the M groups of information units in the reply box of the dialogue area;
Acquiring a drag operation aiming at the dialogue area;
and responding to the drag operation, moving the target text from the dialogue area to the form area, triggering the operation of acquiring the page structure data through the drag operation, processing the page structure data, calling the preset filling operation program, and filling the M groups of information units into M input control boxes in a one-to-one matching mode.
6. A page filling apparatus, comprising:
the extraction module is used for extracting M groups of information units from target requirement sentences, wherein the target requirement sentences are used for representing the input requirements of users; the extraction module comprises a second processing unit, a first processing unit and a second processing unit, wherein the second processing unit is used for inputting a target requirement sentence into a second language model, carrying out structuring processing on the target requirement sentence through the second language model, and outputting M groups of information units;
the first acquisition module is used for acquiring page structure data of a page to be filled, wherein the page to be filled comprises a form area, and the form area comprises M input control boxes;
the processing module is used for processing the page structure data and determining control identifications of M input control frames which are matched with the M groups of information units one by one; wherein each group of information units includes a tag part and a content part; the processing module comprises an extraction unit and a first processing unit; the extraction unit is used for extracting M structural unit data groups corresponding to the M label parts one by one from the page structural data according to the M label parts included in the M groups of information units; the first processing unit is used for inputting the M structural unit data sets into the first language model, carrying out context semantic structure analysis processing on the structural unit data sets through the first language model, and outputting control identifications of M input control frames which are matched with the M groups of information units one by one;
And the filling module is used for calling a preset filling operation program based on the control identifications of the M input control boxes, and filling the M groups of information units into the M input control boxes in a one-to-one matching manner.
7. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-5.
8. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310987045.1A CN116720489B (en) | 2023-08-08 | 2023-08-08 | Page filling method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310987045.1A CN116720489B (en) | 2023-08-08 | 2023-08-08 | Page filling method and device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116720489A CN116720489A (en) | 2023-09-08 |
| CN116720489B true CN116720489B (en) | 2023-11-07 |
Family
ID=87875530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310987045.1A Active CN116720489B (en) | 2023-08-08 | 2023-08-08 | Page filling method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116720489B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117010349B (en) * | 2023-09-28 | 2023-12-19 | 杭州今元标矩科技有限公司 | Form filling method, system and storage medium based on neural network model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002041277A (en) * | 2000-07-28 | 2002-02-08 | Sharp Corp | Information processing unit and recording medium in which web browser controlling program is recorded |
| CA2805150A1 (en) * | 2013-02-06 | 2014-08-06 | Patientordersets.Com Ltd. | Automated generation of structured electronic representations of user-fillable forms |
| CN107885839A (en) * | 2017-11-10 | 2018-04-06 | 山东浪潮通软信息科技有限公司 | A kind of method and apparatus that information is read in Word file |
| CN108428112A (en) * | 2018-03-12 | 2018-08-21 | 武汉斗鱼网络科技有限公司 | A kind of generation method of list, device, computer and storage medium |
| CN110929489A (en) * | 2019-11-18 | 2020-03-27 | 有时数联科技（北京）有限公司 | Form generation and form data processing method and system |
| CN112765944A (en) * | 2020-12-30 | 2021-05-07 | 维沃移动通信有限公司 | Form filling method, device, equipment and medium |
| CN114238807A (en) * | 2021-11-29 | 2022-03-25 | 中国工商银行股份有限公司 | Processing method and device for data visualization page |
| WO2023278124A1 (en) * | 2021-07-01 | 2023-01-05 | Microsoft Technology Licensing, Llc | Classification and augmentation of unstructured data for autofill |
| CN115983202A (en) * | 2023-01-28 | 2023-04-18 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9218331B2 (en) * | 2013-02-06 | 2015-12-22 | Patientordersets.Com Ltd. | Automated generation of structured electronic representations of user-fillable forms |
| US10416877B2 (en) * | 2015-08-25 | 2019-09-17 | Myscript | System and method of guiding handwriting input |
-
2023
- 2023-08-08 CN CN202310987045.1A patent/CN116720489B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002041277A (en) * | 2000-07-28 | 2002-02-08 | Sharp Corp | Information processing unit and recording medium in which web browser controlling program is recorded |
| CA2805150A1 (en) * | 2013-02-06 | 2014-08-06 | Patientordersets.Com Ltd. | Automated generation of structured electronic representations of user-fillable forms |
| CN107885839A (en) * | 2017-11-10 | 2018-04-06 | 山东浪潮通软信息科技有限公司 | A kind of method and apparatus that information is read in Word file |
| CN108428112A (en) * | 2018-03-12 | 2018-08-21 | 武汉斗鱼网络科技有限公司 | A kind of generation method of list, device, computer and storage medium |
| CN110929489A (en) * | 2019-11-18 | 2020-03-27 | 有时数联科技（北京）有限公司 | Form generation and form data processing method and system |
| CN112765944A (en) * | 2020-12-30 | 2021-05-07 | 维沃移动通信有限公司 | Form filling method, device, equipment and medium |
| WO2023278124A1 (en) * | 2021-07-01 | 2023-01-05 | Microsoft Technology Licensing, Llc | Classification and augmentation of unstructured data for autofill |
| CN114238807A (en) * | 2021-11-29 | 2022-03-25 | 中国工商银行股份有限公司 | Processing method and device for data visualization page |
| CN115983202A (en) * | 2023-01-28 | 2023-04-18 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116720489A (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11307830B2 (en) | Intelligent digital experience development platform (IDXDP) | |
| US11380116B2 (en) | Automatic delineation and extraction of tabular data using machine learning | |
| CN111147431A (en) | Method and apparatus for generating information | |
| CN113032257B (en) | Automated testing method, apparatus, computer system, and readable storage medium | |
| CN116720489B (en) | Page filling method and device, electronic equipment and computer readable storage medium | |
| US10379840B2 (en) | Crowd sourcing accessibility rendering system for non-accessible applications | |
| CN113128773A (en) | Training method of address prediction model, address prediction method and device | |
| US10824777B2 (en) | Employing natural language processing to facilitate geospatial analysis | |
| CN115062617A (en) | Task processing method, device, equipment and medium based on prompt learning | |
| CN113392215A (en) | Training method of production problem classification model, and production problem classification method and device | |
| CN113515625A (en) | Test result classification model training method, classification method and device | |
| CN113032256A (en) | Automatic test method, device, computer system and readable storage medium | |
| CN117216393A (en) | Information recommendation method, training method and device of information recommendation model and equipment | |
| US20230161948A1 (en) | Iteratively updating a document structure to resolve disconnected text in element blocks | |
| CN114117227A (en) | Operation maintenance method, system, electronic equipment and storage medium | |
| CN115686660A (en) | Method, apparatus, device and medium for determining automation component | |
| CN114676694A (en) | Method, device, equipment, medium and program product for generating business model | |
| CN114021827A (en) | Operation strategy generation method and device | |
| CN111767290B (en) | Method and apparatus for updating user portraits | |
| KR20230059364A (en) | Public opinion poll system using language model and method thereof | |
| CN113609018A (en) | Test method, training method, device, apparatus, medium, and program product | |
| CN113392014A (en) | Test case generation method and device, electronic equipment and medium | |
| CN112446738A (en) | Advertisement data processing method, device, medium and electronic equipment | |
| CN112860259B (en) | Interface processing method, device, electronic equipment and storage medium | |
| US11907311B2 (en) | Dynamic website characterization for search optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |