Website record auditing method and system based on AI and RPA

Abstract

The invention belongs to the technical field of website record auditing, and particularly relates to a website record auditing method and system based on AI and RPA, and the method comprises the following steps: S1, an RPA robot calls corresponding data information of a work order to be recorded and audited based on a data calling module; s2, the RPA robot intelligently obtains text information in the to-be-recorded auditing data information through a data acquisition module; s3, the RPA robot intelligently processes the text information through a text information processing module, key fields in the text information and keyword information corresponding to the key fields are obtained, the auditing work orders which do not meet the auditing requirements can be rejected in time, the risks of missed judgment and erroneous judgment existing in manual judgment are effectively avoided, RPA configuration is flexible and convenient, and the efficiency is high. Iterative updating is convenient and fast, the resource utilization rate of an original auditing system is high, destructiveness is small, an existing system does not need to be changed during deployment, and stability of the original system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of website filing and review, and specifically to a website filing and review method and system based on AI and RPA. Background Art

[0002] In order to regulate the healthy development of the Internet industry and further improve the management of mobile Internet information services, we will conduct supervision and inspection on website filing and deal with websites that have not yet completed filing procedures in accordance with the law. At present, with the surge in the number of filing applications, the workload of staff has increased sharply, and human review is stretched to its limits.

[0003] Since the filing system has been in stable operation for many years, the system is fully functional and has all the basic functions required for filing and review. Avoiding its modification can greatly reduce costs. However, how to reduce the workload of staff during website filing and review is a problem to be solved in this field. Therefore, the present invention provides a website filing and review method and system based on AI and RPA. Summary of the invention

[0004] The purpose of the present invention is to provide a website filing and review method and system based on AI and RPA to solve the above problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an automated website filing review method based on AI and RPA, comprising the following steps:

[0006] S1: The RPA robot retrieves the corresponding data information of the work order to be filed and reviewed based on the data retrieval module;

[0007] S2: The RPA robot intelligently obtains text information in the data information to be filed and reviewed through the data collection module;

[0008] S3: The RPA robot intelligently processes the text information through the text information processing module to obtain key fields in the text information and keyword information corresponding to the key fields, where the keyword information includes telephone number information, email address information, and domain name address information;

[0009] S4: The RPA robot reviews the data information to be filed through the telephone conflict review unit, the email conflict review unit, the domain name conflict review unit, and the website domain name access review unit. Based on the relevant information of the websites that have completed the filing review stored in the data storage module, it determines whether there is a telephone conflict, an email conflict, a domain name conflict, or an abnormal website domain name access in the data information to be filed;

[0010] S5: Based on the rejection module, the RPA robot registers and records the review work orders corresponding to the pending review data information that has not passed the review of the telephone conflict review unit, the email conflict review unit, the domain name conflict review unit, and the website domain name access review unit, executes the rejection, and records the reason for failure in the rejection form and sends it to the applicant of this review work order.

[0011] Preferably, in step S2, the data acquisition module identifies the data information to be filed and reviewed based on optical character recognition (OCR) technology to obtain text information in the data information to be filed and reviewed.

[0012] Preferably, in step S3, the text information processing module extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology, and the keyword information includes telephone number information, email address information and domain name address information.

[0013] Preferably, the text information processing module pre-sets key fields and stores the pre-set information in the text information processing module. When the pre-set key field information appears in the text information, the keyword information at the corresponding position is extracted.

[0014] Preferably, in step S4, the telephone conflict review unit, the email conflict review unit, the domain name conflict review unit, and the website domain name access review unit review the review data information to be filed in sequence. When any one or more of the telephone conflict review unit, the email conflict review unit, the domain name conflict review unit, and the website domain name access review unit detect that the review data information to be filed is unqualified, it means that the review work order corresponding to the review data information to be filed is unqualified.

[0015] Preferably, when the suffix "gov" exists in the domain name address in the data information to be filed for review, the review work order corresponding to the data information to be filed for review will be marked and transferred to manual review, and a manual determination will be made whether the government certification materials submitted by the applicant are qualified. If unqualified, after confirmation by the staff, the RPA robot will directly reject the review work order through the rejection module and record the rejection reason in the rejection form and send it to the applicant of this review work order.

[0016] Preferably, the website-related information that has completed the filing review and is stored in the data storage module includes personal website domain name-related filing information and corporate website domain name-related filing information, the personal website domain name-related filing information includes a telephone number, an email address, and a domain name address, and the corporate website domain name-related filing information includes a telephone number, an email address, and a domain name address;

[0017] The telephone conflict review unit compares the telephone number of the data information to be filed and reviewed with the telephone number stored in the data storage module. When the same number exists, it means that there is a telephone conflict in the data information to be filed and reviewed;

[0018] The email conflict review unit compares the email address of the data information to be filed and reviewed with the email address stored in the data storage module. When the same email address exists, it means that the data information to be filed and reviewed exists.

[0019] The domain name conflict review unit compares the domain name address of the data information to be filed and reviewed with the domain name address stored in the data storage module. If the domain name address is the same, it means that there is a domain name conflict in the data information to be filed and reviewed;

[0020] The website domain name access review unit accesses the domain name address of the data information to be filed for review to detect whether it is accessible. When the domain name address is accessible, it indicates that there is an abnormality that an unfiled domain name can be accessed.

[0021] Preferably, the personal website domain name related registration information also includes a scanned copy of the front and back of the personal ID card and an upper body photo of the individual, and the corporate website domain name related registration information also includes a scanned copy of the company's business license, a scanned copy of the corporate legal person's ID card, and an upper body photo of the corporate legal person.

[0022] An AI and RPA-based website filing automated review system comprises a data retrieval module, a data collection module, a text information processing module, a data storage module, a telephone conflict review unit, an email conflict review unit, a domain name conflict review unit, a website domain name access review unit and a rejection module, wherein the data retrieval module, the data collection module, the text information processing module, the telephone conflict review unit, the email conflict review unit, the domain name conflict review unit, the website domain name access review unit and the rejection module are executed by an RPA robot;

[0023] The data retrieval module is used to retrieve the data information to be filed and reviewed;

[0024] The data acquisition module recognizes the data information to be filed and reviewed based on optical character recognition (OCR) technology to obtain text information in the data information to be filed and reviewed;

[0025] The text information processing module extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology, wherein the keyword information includes telephone number information, email address information and domain name address information;

[0026] The data storage module stores information about websites that have completed filing and review, the information about the websites includes filing information about personal website domain names and filing information about corporate website domain names, the filing information about personal website domain names includes telephone numbers, email addresses, and domain name addresses, and the filing information about corporate website domain names includes telephone numbers, email addresses, and domain name addresses;

[0027] The telephone conflict review unit is used to review whether the telephone number information obtained in the text information processing module conflicts;

[0028] The mailbox conflict review unit is used to review whether the mailbox address information obtained in the text information processing module conflicts;

[0029] The domain name conflict review unit is used to review whether the domain name address information obtained in the text information processing module conflicts;

[0030] The website domain name access review unit is used to detect whether the website information obtained in the text information processing module is registered;

[0031] The rejection module is used to register and reject unqualified data information to be filed for review.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1) The present invention can immediately reject audit work orders that do not meet audit requirements, effectively avoiding the risk of missed or misjudgment caused by human judgment. RPA configuration is flexible and convenient, and iterative updates are convenient and fast. It has high resource utilization and low destructiveness for the original audit system. There is no need to change the existing system during deployment, thus ensuring the stability of the original system.

[0034] 2) Newly submitted work orders can be quickly reviewed, and abnormal problems such as telephone conflicts, email conflicts, domain name conflicts, and unregistered domain names that can be accessed can be found in time, and rejected immediately, making it easier for users to modify and resubmit, avoiding the situation where users have to wait for manual review for a long time before being rejected due to such simple reasons, which can greatly improve user perception;

[0035] 3) Problems such as telephone conflicts, email conflicts, domain name conflicts, and unregistered domain names being accessible usually account for about 90% to 95% of the total number of rejected work orders. Through preliminary review by this system, the above-mentioned problem work orders are eliminated and automatically rejected, which can achieve the greatest benefit with minimal development costs, save most of the human resources occupied by rejected work orders, and reduce the workload of manual review. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the process of the present invention;

[0037] Figure 2 This is a logic block diagram of the system of the present invention.

[0038] In the figure: 1. Data retrieval module; 2. Data collection module; 3. Text information processing module; 4. Telephone conflict review unit; 5. Email conflict review unit; 6. Domain name conflict review unit; 7. Website domain name access review unit; 8. Data storage module; 9. Rejection module. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "top / bottom" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "mounted / connected", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] Example:

[0043] See also Figure 1-2 The present invention provides a technical solution: an automated review method for website filing based on AI and RPA, comprising the following steps:

[0044] S1: The RPA robot is connected to the review system. The RPA robot retrieves the corresponding data information of the work order to be filed for review based on the data retrieval module 1, and retrieves the data in the order of work order application.

[0045] S2: The RPA robot intelligently obtains text information in the data information to be filed and reviewed through data collection module 2;

[0046] S3: The RPA robot intelligently processes the text information through the text information processing module 3 to obtain key fields in the text information and keyword information corresponding to the key fields. The keyword information includes telephone number information, email address information, and domain name address information.

[0047] S4: The RPA robot reviews the data information to be filed through the telephone conflict review unit 4, the mailbox conflict review unit 5, the domain name conflict review unit 6, and the website domain name access review unit 7, and determines whether there is a telephone conflict (the same telephone number cannot be bound to multiple sponsors), a mailbox conflict (the same mailbox cannot be bound to multiple sponsors), a domain name conflict (the domain name has been registered and occupied by other applications and cannot be registered repeatedly), and a website domain name access anomaly (when an unregistered website is not allowed to be accessed, the access link page should display "This website cannot be accessed");

[0048] S5: Based on the rejection module 9, the RPA robot registers and records the review work orders corresponding to the pending review data information that have not passed the review of the telephone conflict review unit 4, the email conflict review unit 5, the domain name conflict review unit 6, and the website domain name access review unit 7, executes the rejection, and records the reason for failure in the rejection form and sends it to the applicant of this review work order. When the review fails, it is rejected immediately, which is convenient for users to modify in time and improve efficiency.

[0049] In step S2, the data acquisition module 2 optimizes the data information to be filed and reviewed based on the optical character recognition (OCR) technology, and then recognizes the data information to be filed and reviewed to obtain text information in the data information to be filed and reviewed.

[0050] In step S3, the text information processing module 3 extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology. The keyword information includes telephone number information, email address information and domain name address information.

[0051] The text information processing module 3 pre-sets the key fields and stores the pre-set information in the text information processing module 3. For example, if the pre-set information is a number, email address, domain name, etc., when the pre-set key field information appears in the text information, the keyword information at the corresponding position is extracted.

[0052] In step S4, the telephone conflict review unit 4, the email conflict review unit 5, the domain name conflict review unit 6, and the website domain name access review unit 7 review the data information to be filed for review in turn. When any one or more of the telephone conflict review unit 4, the email conflict review unit 5, the domain name conflict review unit 6, and the website domain name access review unit 7 detects that the data information to be filed for review is unqualified, it means that the review work order corresponding to the data information to be filed for review is unqualified.

[0053] When the suffix "gov" is included in the domain name address in the data information to be filed for review, the review work order corresponding to the data information to be filed for review will be marked and transferred to manual review, and a manual review will be conducted to determine whether the government certification materials submitted by the applicant are qualified. If unqualified, after confirmation by the staff, the RPA robot will directly reject the review work order through the rejection module 9 and record the rejection reason in the rejection form and send it to the applicant of the review work order.

[0054] The website related information that has completed the filing review and is stored in the data storage module 8 includes the filing information related to the personal website domain name and the filing information related to the corporate website domain name. The filing information related to the personal website domain name includes the telephone number, email address and domain name address, and the filing information related to the corporate website domain name includes the telephone number, email address and domain name address;

[0055] The telephone conflict review unit 4 compares the telephone number of the data information to be filed and reviewed with the telephone number stored in the data storage module 8. When the same number exists, it means that there is a telephone conflict in the data information to be filed and reviewed;

[0056] The email conflict review unit 5 compares the email address of the data information to be filed and reviewed with the email address stored in the data storage module 8. When the same email address exists, it means that the data information to be filed and reviewed exists.

[0057] The domain name conflict review unit 6 compares the domain name address of the data information to be filed and reviewed with the domain name address stored in the data storage module 8. When the same domain name address exists, it means that the data information to be filed and reviewed has a domain name conflict.

[0058] The website domain name access audit unit 7 accesses the domain name address of the data information to be filed for audit to detect whether it is accessible. When the domain name address is accessible, it means that there is an abnormality that the unfiled domain name can be accessed.

[0059] The registration information related to personal website domain names also includes scanned copies of the front and back of the individual's ID card, and an upper body photo of the individual. The registration information related to corporate website domain names also includes a scanned copy of the company's business license, a scanned copy of the corporate legal person's ID card, and an upper body photo of the corporate legal person.

[0060] An AI and RPA-based website filing automated review system comprises a data retrieval module 1, a data collection module 2, a text information processing module 3, a data storage module 8, a telephone conflict review unit 4, an email conflict review unit 5, a domain name conflict review unit 6, a website domain name access review unit 7 and a rejection module 9, wherein the data retrieval module 1, the data collection module 2, the text information processing module 3, the telephone conflict review unit 4, the email conflict review unit 5, the domain name conflict review unit 6, the website domain name access review unit 7 and the rejection module 9 are executed by an RPA robot;

[0061] The data retrieval module 1 is used to retrieve the data information to be filed and reviewed;

[0062] The data acquisition module 2 recognizes the data information to be filed and reviewed based on the optical character recognition (OCR) technology to obtain the text information in the data information to be filed and reviewed;

[0063] The text information processing module 3 extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology. The keyword information includes telephone number information, email address information, and domain name address information.

[0064] The data storage module 8 stores information about websites that have completed filing and review, including filing information about personal website domain names and filing information about corporate website domain names, including telephone numbers, email addresses, and domain name addresses, and filing information about corporate website domain names includes telephone numbers, email addresses, and domain name addresses;

[0065] The telephone conflict review unit 4 is used to review whether the telephone number information obtained in the text information processing module 3 conflicts;

[0066] The mailbox conflict review unit 5 is used to review whether the mailbox address information obtained in the text information processing module 3 conflicts;

[0067] The domain name conflict review unit 6 is used to review whether the domain name address information obtained in the text information processing module 3 conflicts;

[0068] The website domain name access review unit 7 is used to detect whether the website information obtained in the text information processing module 3 is registered;

[0069] The rejection module 9 is used to register and reject the unqualified data information to be filed for review.

[0070] RPA robot pre-examination can reject more than 90% of rejected work orders in advance, greatly reducing the workload of manual rejection. The number of work orders per day is calculated as 500. Each rejected work order needs to manually input the rejection reason and feedback to the user, and register the relevant information of the rejection. It is estimated that each work order that needs to be rejected takes 3 minutes of manual work. According to the work order rejection rate of about 5%, the manpower saved every day is ≈500*5%*90%*3=1.13 hours.

[0071] Website filing review requires access verification for each URL registered in each work order (i.e., to detect whether there are abnormalities that can be accessed by unregistered domain names) to verify whether it can be accessed. If it can be accessed, it is an unregistered accessible website and needs to be rejected. After being replaced by RPA robots, preliminary estimates show that manual review of each website filing work order takes about 30 seconds, and eliminating the website access verification link can save 5 seconds, and the efficiency is improved by nearly 20%.

[0072] The present invention reduces simple, boring and repetitive labor that requires manual intervention, releases human resources, and enables human resources to review other information more accurately and efficiently, objectively improving the work quality of filing and review.

[0073] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention; therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the attached claims rather than the above description. Therefore, it is intended to include all changes within the meaning and scope of the equivalent elements of the claims in the present invention, and any figure marks in the claims should not be regarded as limiting the claims involved.

[0074] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automated website filing review method based on AI and RPA, characterized by: The following steps are involved: S1: The RPA robot retrieves the corresponding data information of the work order to be filed and reviewed based on the data retrieval module (1); S2: The RPA robot intelligently obtains text information in the data information to be filed and reviewed through the data collection module (2); S3: The RPA robot performs intelligent processing on the text information through the text information processing module (3) to obtain key fields in the text information and keyword information corresponding to the key fields, wherein the keyword information includes telephone number information, email address information, and domain name address information; S4: The RPA robot reviews the data information to be filed through the telephone conflict review unit (4), the email conflict review unit (5), the domain name conflict review unit (6), and the website domain name access review unit (7), and determines whether there is a telephone conflict, an email conflict, a domain name conflict, or a website domain name access anomaly in the data information to be filed based on the relevant information of the website that has completed the filing review stored in the data storage module (8); S5: Based on the rejection module (9), the RPA robot registers and records the review work orders corresponding to the pending review data information that has not passed the review of the telephone conflict review unit (4), the email conflict review unit (5), the domain name conflict review unit (6), and the website domain name access review unit (7), executes the rejection, and records the reason for failure in the rejection form and sends it to the applicant of this review work order.

2. According to claim 1, the method for automated website filing review based on AI and RPA is characterized in that: In the step S2, the data acquisition module (2) identifies the data information to be filed and reviewed based on the optical character recognition (OCR) technology to obtain text information in the data information to be filed and reviewed.

3. According to claim 1, the method for automated website filing review based on AI and RPA is characterized in that: In step S3, the text information processing module (3) extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology, wherein the keyword information includes telephone number information, email address information and domain name address information.

4. According to claim 3, the method for automated website filing review based on AI and RPA is characterized in that: The text information processing module (3) pre-sets the key fields and stores the pre-set information in the text information processing module (3). When the pre-set key field information appears in the text information, the keyword information at the corresponding position is extracted.

5. According to claim 1, the method for automated website filing review based on AI and RPA is characterized in that: In the step S4, the telephone conflict review unit (4), the mailbox conflict review unit (5), the domain name conflict review unit (6), and the website domain name access review unit (7) review the data information to be filed for review in sequence. When any one or more of the telephone conflict review unit (4), the mailbox conflict review unit (5), the domain name conflict review unit (6), and the website domain name access review unit (7) detect that the data information to be filed for review is unqualified, it means that the review work order corresponding to the data information to be filed for review is unqualified.

6. According to claim 1, the method for automated website filing review based on AI and RPA is characterized in that: When the domain name in the data to be filed contains the suffix "gov", the audit work order corresponding to the data to be filed will be marked and transferred to manual review, where a person will manually determine whether the government certification materials submitted by the applicant are qualified. If they are unqualified, after the staff confirms that they are unqualified, the RPA robot will directly reject the audit work order through the rejection module (9) and record the rejection reason in the rejection form and send it to the applicant of the audit work order.

7. According to claim 1, the method for automated website filing review based on AI and RPA is characterized in that: The website-related information that has completed the filing review and is stored in the data storage module (8) includes personal website domain name-related filing information and corporate website domain name-related filing information, wherein the personal website domain name-related filing information includes a telephone number, an email address, and a domain name address, and the corporate website domain name-related filing information includes a telephone number, an email address, and a domain name address; The telephone conflict review unit (4) compares the telephone number of the data information to be filed and reviewed with the telephone number stored in the data storage module (8). When the same number exists, it means that the data information to be filed and reviewed has a telephone conflict. The email conflict review unit (5) compares the email address of the data information to be filed and reviewed with the email address stored in the data storage module (8). When the same email address exists, it means that the data information to be filed and reviewed exists. The domain name conflict review unit (6) compares the domain name address of the data information to be filed and reviewed with the domain name address stored in the data storage module (8). When the domain name address is the same, it means that the data information to be filed and reviewed has a domain name conflict. The website domain name access review unit (7) detects whether the domain name address of the data information to be filed and reviewed is accessible by accessing the domain name address. When the domain name address is accessible, it indicates that there is an abnormality that the unfiled domain name can be accessed.

8. According to claim 7, the method for automated website filing review based on AI and RPA is characterized in that: The registration information related to the personal website domain name also includes a scanned copy of the front and back of the personal ID card and an upper body photo of the individual. The registration information related to the corporate website domain name also includes a scanned copy of the company's business license, a scanned copy of the corporate legal person's ID card, and an upper body photo of the corporate legal person.

9. An automated website filing review system based on AI and RPA, characterized by: The system comprises a data retrieval module (1), a data collection module (2), a text information processing module (3), a data storage module (8), a telephone conflict review unit (4), an email conflict review unit (5), a domain name conflict review unit (6), a website domain name access review unit (7) and a rejection module (9), wherein the data retrieval module (1), the data collection module (2), the text information processing module (3), the telephone conflict review unit (4), the email conflict review unit (5), the domain name conflict review unit (6), the website domain name access review unit (7) and the rejection module (9) are executed by an RPA robot; The data retrieval module (1) is used to retrieve data information to be filed and reviewed; The data acquisition module (2) recognizes the data information to be filed and reviewed based on optical character recognition (OCR) technology to obtain text information in the data information to be filed and reviewed; The text information processing module (3) extracts key fields and keyword information corresponding to the key fields from the text information based on natural language processing (NLP) technology, wherein the keyword information includes telephone number information, email address information and domain name address information; The data storage module (8) stores information related to websites that have completed filing and review, the information related to the websites including filing information related to personal website domain names and filing information related to corporate website domain names, the personal website domain name filing information including telephone numbers, email addresses and domain name addresses, and the corporate website domain name filing information including telephone numbers, email addresses and domain name addresses; The telephone conflict review unit (4) is used to review whether the telephone number information obtained in the text information processing module (3) conflicts; The mailbox conflict review unit (5) is used to review whether the mailbox address information obtained in the text information processing module (3) conflicts; The domain name conflict review unit (6) is used to review whether the domain name address information obtained in the text information processing module (3) conflicts; The website domain name access review unit (7) is used to detect whether the website information obtained in the text information processing module (3) is registered; The rejection module (9) is used to register and record the unqualified data information to be filed for review and reject it.

Images