Intelligent form filling method and intelligent form filling system

Abstract

The invention provides an intelligent form filling method and an intelligent form filling system. The problems that in the prior art, an intelligent form filling mode is difficult to fill accurately, and a corresponding program is rapidly matched are solved or improved. According to the intelligent form filling method provided by the invention, firstly, the rule engine is adopted to identify the first identification information of the to-be-filled information, then the AI identification model is adopted to identify the second identification information of the to-be-filled information, and the to-be-filled information of the to-be-filled information is obtained according to the target calling program. And fusing the first identification information and the second identification information to generate target form filling information, and finally filling a target form in the target calling program with the target form filling information. In the whole form filling process, the target form filling information can be recognized more accurately through double recognition. Besides, two different identification mechanisms are adopted to identify the information to be filled, so that more scenes can be used, and the adaptation rate of the form filling method is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to an intelligent form filling method and an intelligent form filling system. Background Art

[0002] With the development of technology, users often need to fill in various forms on the Internet. For example, when shopping online or submitting questions online, users are usually required to fill in many forms. Another example is within a company, cross-departmental communication or transaction processing has gradually moved online, and when users handle company business, they also need to fill in various forms such as business approval documents and cross-departmental work orders.

[0003] Currently, the methods for intelligent form filling mostly use RPA (Robotic Process Automation) tools and NLP models. Among them, RPA tools use software robots to simulate human operations and automatically execute repetitive and rule-based business processes. The NLP model is a tool that uses deep learning technology to enable a computer to understand, analyze, generate, and process human language.

[0004] However, in the actual application process, both RPA tools and NLP models have different limitations and deficiencies. For example, the limitations of RPA tools: they can only process fixed template inputs (such as Excel tables) and cannot parse colloquial and multi-modal expressions (such as "Spent 5000 yuan on a business trip last week"). The deficiencies of general NLP models: For example, GPT-4 performs excellently in open-domain conversations but lacks the structured parsing ability in the enterprise form scenario (such as being unable to map "transportation expenses" to the specific subject code of the enterprise ERP).

[0005] In addition, using RPA tools or NLP models will also cause the problem of system islands: The data formats of ERP systems such as UFIDA and Kingdee are heterogeneous, and traditional middleware requires custom development and is difficult to quickly adapt. Summary of the Invention

[0006] In view of this, this application provides an intelligent form filling method and an intelligent form filling system, which solve or improve the problem that the existing method for filling intelligent forms is difficult to fill accurately and quickly adapt to the corresponding program.

[0007] As the first aspect of this application, this application provides an intelligent form filling method, including: Obtain the information of the form to be filled by the user; Based on a rule engine, identify the information of the form to be filled to obtain first identification information; Based on an AI identification model, identify the information of the form to be filled to obtain second identification information; Based on the target calling program, fuse the first identification information and the second identification information to obtain target form-filling information; Fill the target form based on the target form-filling information.

[0008] In an embodiment of the present application, the identifying the information to be filled in to obtain the second identification information based on the AI identification model includes: Based on the AI identification model, identify the information to be filled in to obtain initial identification information and a confidence level; When the confidence level is greater than a preset threshold, determine the initial identification information as the second identification information; When the confidence level is less than or equal to the preset threshold, generate feedback information for reminding the user to confirm the initial identification information.

[0009] In an embodiment of the present application, the filling the target form based on the target form-filling information includes: Based on a dynamic adaptation middleware, map the target form-filling information to generate at least one target filling item corresponding to the target form and target filling information corresponding to the target filling item; Call the target calling program based on the target form; When the target calling program is successfully called based on the target form, based on the target calling program, correspondingly fill the target filling information into the target filling item.

[0010] In an embodiment of the present application, the intelligent form filling method further includes: When the target calling program fails to be called based on the target form, fill the at least one target filling item into the target form corresponding to the target calling program through a preset database.

[0011] In an embodiment of the present application, the information to be filled in includes: Voice information; and / or Image information; and / or Text information.

[0012] In an embodiment of the present application, the information to be filled in includes voice information and image information; Among them, identifying the information to be filled in to obtain the first identification information based on a rule engine includes: identifying the voice information based on the rule engine to obtain the first identification information; Identifying the information to be filled in to obtain the first identification information based on the AI identification model includes: identifying the image information based on the AI identification model to obtain the second identification information.

[0013] In an embodiment of the present application, based on a target calling program, the first identification information and the second identification information are fused to obtain target form-filling information, including: Determine at least one target filling item based on the target calling program; According to each of the target filling items, respectively search for the first target information and the second target information corresponding to the target filling item in the first identification information and the second identification information; According to the target filling item, fuse the first target information and the second target information corresponding to the target filling item to obtain the target form-filling information corresponding to the target filling item.

[0014] In an embodiment of the present application, according to the target filling item, fuse the first target information and the second target information corresponding to the target filling item to obtain the target form-filling information corresponding to the target filling item, including: Calculate the similarity between the first target information and the second target information corresponding to the target filling item; When the similarity is greater than a preset similarity, determine the first target information or the second target information as the target form-filling information corresponding to the target filling item.

[0015] In an embodiment of the present application, the intelligent form-filling method further includes: When the similarity is less than or equal to the preset similarity, generate a warning message.

[0016] As a second aspect of the present application, the present application further provides an intelligent form-filling system, including: A data acquisition module, configured to acquire the information to be filled in the form by the user; An engine determination module, configured to identify the information to be filled in the form based on a rule engine to obtain first identification information; An identification module, configured to identify the information to be filled in the form based on an AI identification model to obtain second identification information; A fusion module, configured to fuse the first identification information and the second identification information based on a target calling program to obtain target form-filling information; A calling module, configured to call a target calling program and fill a target form based on the target form-filling information.

[0017] An intelligent form filling method provided by the present application first uses a rule engine to identify the first identification information from the information to be filled in the form, then uses an AI recognition model again to identify the second identification information from the information to be filled in the form, and according to the target calling program, fuses the first identification information and the second identification information to generate the target form filling information. Finally, the target form filling information is filled into the target form in the target calling program. During the entire form filling process, through dual recognition, the target form filling information can be identified more accurately. In addition, since two different recognition mechanisms are used to identify the information to be filled in the form, more scenarios can be used, improving the adaptation rate of the form filling method. Brief Description of the Drawings

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present application will become more obvious. The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 The figure shows a flowchart of an intelligent form filling method provided by an embodiment of the present application.

[0020] Figure 2 The figure shows a flowchart of an intelligent form filling method provided by another embodiment of the present application.

[0021] Figure 3 The figure shows a flowchart of an intelligent form filling method provided by another embodiment of the present application.

[0022] Figure 4 The figure shows a flowchart of an intelligent form filling method provided by another embodiment of the present application.

[0023] Figure 5 The figure shows a working block diagram of an intelligent form filling system provided by an embodiment of the present application.

[0024] Figure 6 The figure shows a working block diagram of an electronic device provided by an embodiment of the present application. Detailed Description of the Embodiments

[0025] In the description of this application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically defined. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0026] In addition, the mention of "embodiment" in this context means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The occurrence of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0027] As a first aspect of this application, this application provides an intelligent form filling method, an intelligent form filling method combining a rule engine, a fine-tuned large model, and cross-system dynamic mapping, which is applicable to enterprise office automation scenarios (such as financial reimbursement, HR attendance, supply chain management, etc.).

[0028] Figure 1 The following shows a schematic flowchart of an intelligent form filling method provided by an embodiment of this application, as Figure 1 shown, an intelligent form filling method specifically includes the following steps: S1: Obtain the information of the form to be filled in by the user; Specifically, the information of the form to be filled in by the user can be: (1) Voice information, which can be obtained by a recording device such as a recorder of the system to obtain the user's voice information; (2) Image information, which can be the image information captured by a camera device or the image information obtained by scanning a document, such as an invoice image; (3) Text information.

[0029] Specifically, the information of the form to be filled in can include any one form of the above-mentioned information of the form to be filled in, or can include multiple forms of the above-mentioned information of the form to be filled in. For example, the information of the form to be filled in includes voice information and image information, and the information of the form to be filled in can also only include voice information or only include image information.

[0030] S2: Based on the rule engine, identify the information of the form to be filled in to obtain the first identification information; Specifically, the rule engine is a component embedded in the application. Matching rules can be defined through the rule engine, and then the corresponding information can be identified from the information to be filled in the form according to the matching rules. For example, when the information to be filled in the form is voice information, the information included in the voice can be identified by keyword recognition or by semantic matching, etc.

[0031] For example, the information to be filled in the form input by the user includes the voice information "Reimburse the travel expenses for going to Beijing last week, high-speed rail ticket 500, accommodation 800, and the invoice is in the picture". Then the rule engine identifies from the voice information: travel expenses for Beijing, high-speed rail ticket 500, accommodation 800, and the date of last week is from March 10, 2024 to March 16, 2024.

[0032] S3: Based on the AI recognition model, identify the information to be filled in the form to obtain the second identification information; Specifically, the AI recognition model is an algorithm model in the field of artificial intelligence used to classify, detect, identify, or analyze input data (such as images, texts, audios, etc.).

[0033] Specifically, the AI recognition module can be the DeepSeek model.

[0034] For example, when the information to be filled in the form is invoice image information, then the AI recognition model identifies the invoice image information to obtain information such as the amount and invoice number.

[0035] Based on the AI recognition model, identify the information to be filled in the form again to generate the second identification information.

[0036] S4: Based on the target calling program, fuse the first identification information and the second identification information to obtain the target information to be filled in the form; Specifically, the target calling program refers to the program that needs to be filled in, such as UFIDA U8, Kingdee Cloud, DingTalk, etc.

[0037] After identifying the information to be filled in the form by using two recognition methods, based on the target calling program, fuse the first identification information and the second identification information to obtain the target information to be filled in the form. For example, according to DingTalk, the input rules required by DingTalk can be determined, and then according to the input rules, fuse the first identification information and the second identification information to obtain the target information to be filled in the form that matches the DingTalk input rules.

[0038] For example, the information to be filled in the form entered by the user includes the voice information "Reimburse the travel expenses for going to Beijing last week, high-speed rail ticket is 500 yuan, accommodation is 800 yuan, and the invoice is in the picture" and the image information (invoice image information). Then the corresponding first recognition information is: Travel expenses for Beijing, high-speed rail ticket is 500 yuan, accommodation is 800 yuan, and the date of last week is from 2024-03-10 to 2024-03-16. The second recognition information is: Amount 500 yuan, invoice number BJ20240315001; Then according to the target calling program, when fusing the first recognition information and the second recognition information: The specific fused target form-filling information is fused according to different target calling programs. For example: The fused target form-filling information can be: Destination: Beijing, Means of travel: High-speed rail, High-speed rail cost: 500 yuan, High-speed rail invoice number: BJ20240315001, Business trip time: from 2024-03-10 to 2024-03-16.

[0039] S5: Fill the target form based on the target form-filling information.

[0040] After determining the target form-filling information, it can be filled into the target form in the target calling program according to the target form-filling information.

[0041] An intelligent form-filling method provided by this application first uses a rule engine to identify the first recognition information from the information to be filled in the form, then uses an AI recognition model again to identify the second recognition information from the information to be filled in the form, and according to the target calling program, fuses the first recognition information and the second recognition information to generate the target form-filling information, and finally fills the target form-filling information into the target form in the target calling program. During the entire form-filling process, through double recognition, the target form-filling information can be recognized more accurately. In addition, because two different recognition mechanisms are used to recognize the information to be filled in the form, more scenarios can be used, improving the adaptation rate of the form-filling method.

[0042] In an embodiment of this application, as Figure 2 shown, S3 (Based on the AI recognition model, recognize the information to be filled in the form to obtain the second recognition information) further includes the following steps: S31: Based on the AI recognition model, recognize the information to be filled in the form to obtain the initial recognition information and the confidence level; S32: Determine whether the confidence level is greater than the preset threshold; Specifically, the preset threshold is related to the AI recognition model and is determined according to the specific type of the AI recognition model. For example, when the AI recognition model is the DeepSeek model, the preset threshold can be 0.7.

[0043] When the judgment result of S32 is yes, that is, when the confidence level is greater than the preset threshold, it indicates that the recognition accuracy is relatively high. Then, the initial recognition information is determined as the second recognition information, that is, S33 is executed.

[0044] When the judgment result of S32 is no, that is, when the confidence level is less than or equal to the preset threshold, it indicates that the recognition accuracy is relatively low. In this case, feedback information needs to be generated. Through the feedback information, the user can confirm the initial recognition information, that is, S34 is executed.

[0045] S33: Determine the initial recognition information as the second recognition information; S34: Generate feedback information, which is used to remind the user to confirm the initial recognition information.

[0046] After the feedback information is generated, the user can confirm the initial recognition information according to the feedback information. If the confirmation is incorrect, the user will input the correct information. After receiving the correct information input by the user, the content in the initial recognition information can be replaced with the correct information, and the modified information is used as the second recognition information. Additionally, if the manual confirmation is incorrect, the AI recognition model is fine-tuned, and then the fine-tuned AI recognition model is used to recognize the information to be filled in the form until the confidence level corresponding to the recognition result is greater than the preset threshold.

[0047] Specifically, the following method can be used to fine-tune the parameters of the AI recognition model: When the AI recognition model is the DeepSeek model, the DeepSeek model can be fine-tuned using the LORA technique, and the parameter settings can be "rank (rank) = 8, alpha (scaling factor) = 16".

[0048] In another embodiment of the present application, as Figure 3 shown, S5 (filling the target form based on the target information to be filled in the form) specifically includes the following steps: S51: Based on the dynamic adaptation middleware, map the target information to be filled in the form to generate at least one target filling item corresponding to the target form and target filling information corresponding to the target filling item; S52: Call the target calling program based on the target form; Different target forms correspond to different target calling programs. After the target form is determined, the target calling program is called.

[0049] S53: When the target calling program is successfully called based on the target form, fill the target filling information into the corresponding target filling item based on the target calling program.

[0050] S54: When the target calling program fails to be successfully called based on the target form, at least one target filling item is filled into the target form corresponding to the target calling program through a preset database.

[0051] That is, when the call to the target calling program fails, it automatically switches to the database direct connection mode (such as writing to the UFIDA background database through JDBC).

[0052] In another embodiment of the present application, as Figure 4 shown, the information to be filled in the form includes: voice information; and / or image information; and / or text information.

[0053] Then S2 (based on the rule engine, identifying the information to be filled in the form to obtain the first identification information) is specifically: based on the rule engine, identifying the voice information to obtain the first identification information; That is, the rule engine identifies the voice information.

[0054] S3 (based on the AI recognition model, identifying the information to be filled in the form to obtain the first identification information) is specifically: Based on the AI recognition model, identifying the image information to obtain the second identification information.

[0055] And the AI model identifies the image information.

[0056] At this time, S4 (based on the target calling program, fusing the first identification information and the second identification information to obtain the target form filling information) specifically includes the following steps: S41: Determine at least one target filling item based on the target calling program; Specifically, the target filling items corresponding to different target calling programs are different. For example, when the target calling program is DingTalk, for a leave application, the target filling items can be: start time of leave, end time of leave, type of leave, reason for leave, etc.

[0057] S42: According to each target filling item, respectively search for the first target information and the second target information corresponding to the target filling item in the first identification information and the second identification information; Based on the target filling item, search for the corresponding first target information and second target information in the first identification information and the second identification information. Since the information to be filled in the form input by the user includes voice information and image information, corresponding information can be obtained according to each piece of information to be filled in the form. For example, the start time of leave and the end time of leave may be identified from the voice information, and the reason for leave information can be obtained from the image information, etc.

[0058] S43: Based on the target filling item, fuse the first target information and the second target information corresponding to the target filling item to obtain the target filling form information corresponding to the target filling item.

[0059] After obtaining the first target information and the second target information corresponding to the target filling item from different to-be-filled form information respectively, fusion can be performed to obtain the target filling form information.

[0060] Optionally, S43: Based on the target filling item, fuse the first target information and the second target information corresponding to the target filling item to obtain the target filling form information corresponding to the target filling item, including: S44: Calculate the similarity between the first target information and the second target information corresponding to the target filling item; S45: When the similarity is greater than the preset similarity, determine the first target information or the second target information as the target filling form information corresponding to the target filling item.

[0061] For example: When the same target filling item corresponds to the first target information and the second target information, then similarity calculation needs to be performed to determine whether the first target information is the same as the second target information. For example, the to-be-filled form information input by the user includes voice information "Reimburse the travel expenses for going to Beijing last week, high-speed rail ticket 500, accommodation 800, the invoice is in the picture" and image information (invoice image information). Then the corresponding first recognition information is: Travel expenses for Beijing, high-speed rail ticket 550, accommodation 800, and the date of last week is from 2024-03-10 to 2024-03-16. The second recognition information is: Amount 500 yuan, invoice number BJ20240315001. Then the high-speed rail fee (target filling item) corresponds to the first target information (550 yuan) and the second target information (500 yuan), indicating that the first target information does not match the second target information.

[0062] S46: When the similarity is less than or equal to the preset similarity, generate a warning message.

[0063] The user determines the target filling item manually according to the warning message to make the target filling item accurate.

[0064] As the second aspect of the present application, the present application also provides an intelligent form filling system, as Figure 5 shown, the intelligent form filling system 100 includes: A data acquisition module 101, configured to acquire the to-be-filled form information of the user; Specifically, the data acquisition module 101 is configured to execute S1 (acquire the to-be-filled form information of the user) in the above-mentioned intelligent form filling method.

[0065] The engine determination module 102 is configured to identify the information to be filled in the form based on a rule engine to obtain first identification information; the engine determination module 102 is used to execute S2 (identifying the information to be filled in the form based on a rule engine to obtain first identification information) in the intelligent form filling method described above.

[0066] The identification module 103 is configured to identify the information to be filled in the form based on an AI identification model to obtain second identification information; Specifically, the identification module 103 is used to execute S3 (identifying the information to be filled in the form based on an AI identification model to obtain second identification information) in the intelligent form filling method described above.

[0067] Specifically, the identification module 103 can be a DeepSeek model.

[0068] The fusion module 104 is configured to fuse the first identification information and the second identification information based on a target calling program to obtain target form filling information; Specifically, the fusion module 104 is used to execute S4 (fusing the first identification information and the second identification information based on a target calling program to obtain target form filling information) in the intelligent form filling method described above.

[0069] The calling module 105 is configured to call a target calling program and fill a target form based on the target form filling information.

[0070] Specifically, the calling module 105 is used to execute S5 (calling a target calling program and filling a target form based on the target form filling information) in the intelligent form filling method described above.

[0071] An intelligent form filling system provided by the present application first uses a rule engine to identify first identification information from the information to be filled in the form, then uses an AI identification model again to identify second identification information from the information to be filled in the form, and fuses the first identification information and the second identification information according to a target calling program to generate target form filling information, and finally fills the target form filling information into the target form in the target calling program. During the entire form filling process, through double identification, the target form filling information can be identified more accurately. In addition, since two different identification mechanisms are used to identify the information to be filled in the form, more scenarios can be used, improving the adaptability rate of the form filling method.

[0072] Exemplary electronic device Next, with reference to Figure 6 to describe the electronic device according to an embodiment of the present application.

[0073] Figure 6 The block diagram of the electronic device according to an embodiment of the present application is illustrated.

[0074] As shown Figure 6 in FIG., the electronic device 20 includes one or more processors 200 and a memory 202.

[0075] The processor 200 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 20 to perform desired functions.

[0076] The memory 202 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 200 may run the program instructions to implement the intelligent form filling method of each embodiment of the present application above and / or other desired functions.

[0077] In one example, the electronic device 20 may further include: an input device 201 and an output device 203, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0078] When the electronic device is a stand-alone device, the input device 201 may be a communication network connector for receiving the collected input signals from the first device and the second device.

[0079] In addition, the input device 201 may further include, for example, a keyboard, a mouse, and so on.

[0080] The output device 203 may output various information to the outside, including the determined distance information, direction information, etc. The output device 203 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and so on.

[0081] Of course, for simplicity, Figure 6 only some of the components related to the present application in the electronic device 20 are shown in FIG., and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application scenarios, the electronic device 20 may further include any other appropriate components.

[0082] As a third aspect of the present application, the present application provides a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is used to perform the following steps: S1: Obtain the information to be filled in the form by the user; Specifically, the information to be filled in the form by the user can be any one or more of voice information, image information, and text information.

[0083] S2: Based on the rule engine, identify the information to be filled in the form to obtain the first identification information; Specifically, the rule engine is a component embedded in the application program. Matching rules can be defined through the rule engine, and then the corresponding information can be identified from the information to be filled in the form according to the matching rules. For example, when the information to be filled in the form is voice information, the information included in the voice can be identified through keywords, or the information included in the voice information can be identified according to semantic matching, etc.

[0084] S3: Based on the AI recognition model, identify the information to be filled in the form to obtain the second identification information; Specifically, the AI recognition model is an algorithm model in the field of artificial intelligence used to classify, detect, recognize, or analyze input data (such as images, texts, audio, etc.).

[0085] Specifically, the AI recognition module can be the DeepSeek model.

[0086] S4: Based on the target calling program, fuse the first identification information and the second identification information to obtain the target form-filling information; Specifically, the target calling program refers to the program that needs to be filled, such as UFIDA U8, Kingdee Cloud, DingTalk, etc.

[0087] S5: Fill the target form based on the target form-filling information.

[0088] After determining the target form-filling information, it can be filled into the target form in the target calling program according to the target form-filling information.

[0089] In addition to the above methods and devices, the embodiments of the present application can also be a computer program product, which includes computer program information. When the computer program information is run by a processor, the processor is caused to execute the steps in the intelligent form filling method according to various embodiments of the present application described in this specification.

[0090] The computer program product can be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0091] In addition, an embodiment of the present application may also be a computer-readable storage medium storing computer program information, which, when run by a processor, causes the processor to execute the steps in the intelligent form filling method according to various embodiments of the present application described in this specification.

[0092] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but not be limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0093] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present application. In addition, the above-disclosed specific details are only for illustrative and easy-to-understand purposes and not for limitation, and the present application is not limited to implementing with the above specific details.

[0094] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present application are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms meaning "including but not limited to" and can be used interchangeably with each other. The word "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with each other unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with each other.

[0095] It should also be noted that in the devices, equipment, and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present application.

Claims

1. An intelligent form filling method, characterized in that, Including: Obtain the information to be filled in the form by the user; Based on a rule engine, identify the information to be filled in the form to obtain first identification information; Based on an AI identification model, identify the information to be filled in the form to obtain second identification information; Based on a target calling program, fuse the first identification information and the second identification information to obtain target form-filling information; Fill the target form based on the target form-filling information.

2. The intelligent form filling method according to claim 1, wherein The step of, based on the AI identification model, identifying the information to be filled in the form to obtain second identification information includes: Based on the AI identification model, identify the information to be filled in the form to obtain initial identification information and a confidence level; When the confidence level is greater than a preset threshold, determine the initial identification information as the second identification information; When the confidence level is less than or equal to the preset threshold, generate feedback information for reminding the user to confirm the initial identification information.

3. The intelligent form filling method according to claim 2, wherein The step of filling the target form based on the target form-filling information includes: Based on a dynamic adaptation middleware, map the target form-filling information to generate at least one target filling item corresponding to the target form and target filling information corresponding to the target filling item; Call a target calling program based on the target form; When the target calling program is successfully called based on the target form, based on the target calling program, fill the target filling information into the target filling item correspondingly.

4. The intelligent form filling method according to claim 3, wherein The intelligent form filling method further includes: When the target calling program fails to be called successfully based on the target form, fill the at least one target filling item into the target form corresponding to the target calling program through a preset database.

5. The intelligent form filling method according to claim 1, wherein The information to be filled in the form includes: Voice information; and / or Image information; and / or Text information.

6. The intelligent form filling method according to claim 5, wherein The information to be filled in the form includes voice information and image information; Among them, the step of, based on a rule engine, identifying the information to be filled in the form to obtain first identification information includes: based on the rule engine, identify the voice information to obtain first identification information; The step of, based on an AI identification model, identifying the information to be filled in the form to obtain first identification information includes: based on the AI identification model, identify the image information to obtain second identification information.

7. The intelligent form filling method according to claim 6, wherein The step of, based on a target calling program, fusing the first identification information and the second identification information to obtain target form-filling information includes: Determine at least one target filling item based on the target calling program; According to each of the target filling items, respectively search for first target information and second target information corresponding to the target filling item in the first identification information and the second identification information; According to the target filling item, fuse the first target information and the second target information corresponding to the target filling item to obtain the target form-filling information corresponding to the target filling item.

8. The intelligent form filling method according to claim 7, wherein, According to the target filling item, fusing the first target information and the second target information corresponding to the target filling item to obtain the target form-filling information corresponding to the target filling item includes: Calculate the similarity between the first target information and the second target information corresponding to the target filling item; When the similarity is greater than a preset similarity, determine the first target information or the second target information as the target form-filling information corresponding to the target filling item.

9. The intelligent form filling method according to claim 8, wherein The intelligent form filling method further includes: When the similarity is less than or equal to the preset similarity, generate a warning message.

10. An intelligent form filling system, characterized in that, It includes: A data acquisition module, configured to acquire the information to be filled in by the user; An engine determination module, configured to identify the information to be filled in based on a rule engine to obtain first identification information; An identification module, configured to identify the information to be filled in based on an AI identification model to obtain second identification information; A fusion module, configured to fuse the first identification information and the second identification information based on a target calling program to obtain target form-filling information; A calling module, configured to call a target calling program and fill a target form based on the target form-filling information.

Images