Intelligent approval system and method for self-employed individuals based on the Internet of Things

Abstract

The present invention discloses an intelligent approval system and method for self-employed individuals based on the Internet of Things, belonging to the field of market supervision. The intelligent approval system includes a data acquisition module, a database, a data analysis module, and a data feedback module. The data acquisition module is used to collect basic data information and video material information. The database is used to encrypt and store the collected data information and analysis results. The data analysis module is used to analyze and process the collected video information. The data feedback module is used to automatically review and determine the information uploaded by the user based on the analysis results, and notify the user. The present invention changes the original uploaded picture as proof material to uploaded video by entering database keyword information and review standards, analyzes and processes the video to automatically capture clips in the video as proof material, calibrates it, and then performs intelligent review and sends notifications to the user, thereby improving the accuracy and security of the proof material.

Description

Technical Field

[0001] The present invention relates to the field of market supervision, and in particular to an intelligent approval system and method for self-employed individuals based on the Internet of Things. Background Art

[0002] In recent years, with the continuous development of the economy and advancements in technology, many new business models have emerged, and the scale of self-employed individuals has continued to grow, fully reflecting the vitality of the economy. Self-employed individuals, also known as individual industrial and commercial households, refer to natural persons or families that engage in industrial and commercial activities within the scope permitted by law and are approved and registered in accordance with the law. Self-employed individuals have played a significant role in the transformation of my country's economic and social structure over the past two decades. Their existence and development have attracted considerable social attention, and they have become one of China's ten major social classes today. Self-employed individuals in my country are characterized by rapid growth and significant economic and social benefits.

[0003] With the development of science and technology, the way for self-employed individuals to register and apply for business licenses has gradually become more convenient and quick. In view of the characteristics of self-employed individuals, such as single business model, little reporting information, and natural persons as operators, various places have gradually introduced online business. Users only need to fill in and submit supporting materials item by item according to the display page of the reporting system and wait for the review results. There is no need to go to the Industrial and Commercial Bureau for processing, realizing zero running around, zero face-to-face meetings and zero intervention in business processing.

[0004] However, currently when handling self-employed business online, materials are still uploaded by uploading photos. It is difficult to ensure that the uploaded personal information is consistent with the user who is actually handling the self-employed business. Even if the uploaded photo is of the user holding the identity document that needs to be uploaded, it is difficult to ensure that the photo is the photo needed to handle the self-employed business. There are cases where photos used to handle other businesses are misappropriated by others and false materials are uploaded, which threatens the economic and information security of users.

[0005] Therefore, it is necessary to make it easier for self-employed users to handle business and to ensure the authenticity of the self-employed ID card information used to handle business, so that it cannot be used by others. Therefore, a smart approval system and method for self-employed users based on the Internet of Things is needed. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent approval system and method for self-employed individuals based on the Internet of Things. By entering database keyword information and review standards, the original uploaded pictures as proof materials are changed to uploaded videos, the videos are analyzed and processed to automatically capture clips in the video according to keywords as proof materials, and the captured pictures are rotated and calibrated before being intelligently reviewed. A notification is sent to the user to inform the user whether the user has passed. If not, the user is informed of the problems and modification suggestions. Data encryption is performed throughout the process to solve the problems raised in the above background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart approval system for self-employed individuals based on the Internet of Things, characterized in that: the smart approval system includes a data acquisition module, a database, a data analysis module and a data feedback module;

[0008] The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the data feedback module; the data acquisition module is used to collect basic data information and video material information, the database is used to encrypt and store the collected data information and analysis results, the data analysis module is used to analyze and process the collected video information, and the data feedback module is used to automatically review and determine the information uploaded by the user based on the analysis results, and notify the user.

[0009] Furthermore, the data acquisition module includes a basic data acquisition unit and a video acquisition unit. The basic data acquisition unit is used to enter basic keyword information and judgment standard information, such as user name, business method and business scope, etc., which provides a basis for the system to perform intelligent analysis and review of information, thereby improving the accuracy of data review. The video acquisition unit is used to collect video material information uploaded by users through the Internet of Things, automatically identify the audio therein based on the video, and generate a text file. For example, by photographing the user holding the file to be uploaded and describing it, the user submits information by uploading a video, which can effectively solve the problem of not being able to determine whether the uploader is the person in the picture information when uploading pictures. Even if the user holds a photo of his or her ID card, it is difficult to ensure that the photo is the photo required for this business transaction. It can effectively improve the accuracy of information analysis and review, and avoid the situation where the user handling the business is inconsistent with the identity information. Even if the business is handled with the help of others, such as an elderly person applying with the help of his or her children, the user handling the business needs to record the video himself or herself, and no one else can replace him or her. This ensures that the uploaded data matches the user himself or herself. At the same time, since the video contains audio, it can effectively ensure that the video used is the video required for this business transaction, thereby avoiding the situation of information misappropriation.

[0010] Furthermore, the database includes a storage unit and an encryption unit. The storage unit is used to store entered keyword information, collected video and text information, and analysis results. The encryption unit encrypts the stored data information and the entire encryption process through the AES encryption algorithm. The AES encryption algorithm is an advanced encryption standard in cryptography. The encryption algorithm adopts a symmetric block cipher system. The minimum supported key length is 128 bits, 192 bits, and 256 bits, and the block length is 128 bits. The algorithm should be easy to implement in various hardware and software. The AES algorithm mainly has four operation processes, namely key addition layer, byte substitution layer, row shift layer, and column confusion layer. AES itself is to replace DES. AES has better security, efficiency and flexibility, and can effectively ensure the security of data when individual households handle business, protect the privacy information security of users, and prevent information leakage from posing a threat to the information security and personal property security of individual households.

[0011] Furthermore, the data analysis module includes a video extraction unit and an image calibration unit. The video extraction unit is used to analyze the video uploaded by the user, analyze and intercept the video according to the keyword information stored in the database, and use the intercepted image as the proof material for the self-employed to handle business, which can effectively ensure the accuracy of the proof material, ensure that it is the user who needs to handle the business who is performing the operation, and prevent the information from being used by others. The image calibration unit is used to calibrate the intercepted image, such as enlarging and correcting the document material held by the user, so that the system can better review and judge the image, improve the accuracy of the review, avoid the situation where the review fails due to improper holding posture of the user, reduce the number of modifications by the user, and improve the user experience of self-employed users in handling business online.

[0012] Furthermore, the data feedback module includes a data review unit and a user notification unit. The data review unit is used to review and determine the image proof materials that have been analyzed and intercepted based on the analysis results and the judgment standard information stored in the database. The user notification unit is used to send notifications to users who handle business. If the materials submitted by the user are accurate, a notification is sent to the user, such as sending a text message to remind the user that the review has passed. If the materials submitted by the user are missing or incorrect, a notification is sent to the user, such as informing of the existing problems and modification suggestions, so that the user can understand the progress of the business in a timely manner, and at the same time, the user can understand the specific material information that needs to be modified.

[0013] The smart approval method for self-employed individuals based on the Internet of Things includes the following steps:

[0014] S1. Input basic data information and review standards, collect video evidence uploaded by users, automatically convert the audio in the video into text information, and encrypt and store it in the database;

[0015] S2. Analyze and process the collected user-uploaded videos, and capture images as evidence based on keyword information stored in the database;

[0016] S3, calibrating the captured image;

[0017] S4. Based on the analysis results and the audit standards stored in the database, the captured image is audited and judged, and a notification is sent to the user.

[0018] Furthermore, in step S2, the text information automatically converted from the video uploaded by the user is analyzed based on the keyword information entered in the database;

[0019] In the automatically converted text, the time at which a sentence containing a keyword appears determines its importance. For example, a sentence containing a keyword that appears earlier is more important than a sentence containing a keyword that appears later. The following formula is used to analyze the importance of the keyword position F1:

[0020] F1 = log2(log2(2+Z));

[0021] Where Z is the median position of all sentences containing the keyword in the text;

[0022] The keyword frequency F2 is normalized using the following formula:

[0023]

[0024] Where T represents the number of times the keyword appears, A represents the mean frequency of the keyword, and σ is the standard deviation;

[0025] The number of related words that appear with a keyword determines the importance of the keyword. For example, the more different words a keyword appears with, the lower the importance of the keyword. The following formula is used to analyze the relationship between the keyword and the context F3:

[0026]

[0027] Where B represents the number of different words that appear with the keyword, C represents the maximum frequency of the keyword in the text, and k represents the number of different words that appear with the keyword in the kth order.

[0028] The number of sentences containing a keyword determines the importance of the keyword. For example, the more sentences a keyword appears in, the more important it is. The frequency F4 of the keyword in a sentence is analyzed using the following formula:

[0029]

[0030] Among them, Q represents the frequency of occurrence of sentences containing keywords, and S represents the number of all sentences in the text;

[0031] The score M of each keyword is calculated by the following formula:

[0032]

[0033] Set a threshold M for each keyword score 阈 , when M<M 阈 When M≥M, it means that the keyword is important. The position of the keyword in the text and the corresponding key frame of the video are extracted and the key frame is intercepted as the evidence. 阈 When , it means that the words that appear are not important and have nothing to do with the part that needs to be reviewed, and the system automatically filters them out.

[0034] By analyzing keywords to capture images, we can effectively avoid the failure of the review caused by capturing unnecessary pages, improve the accuracy and security of the supporting materials, and even if the user's ID card is lost, we can ensure that his or her identity information will not be used by others for self-employed registration or self-employed business license processing, and avoid the situation where others use the user's identity information to obtain loans, etc., thereby protecting the user's privacy information and personal property security, and improving the user's online business experience.

[0035] Furthermore, in step S3, the image captured as the proof material is binarized and then calibrated to establish a plane rectangular coordinate system, and the straight line f(x, y) in the image is detected and projected. The projection can be performed along any angle. For example, the user image captured as the proof material is enlarged and calibrated so that the proof material in the user's hand can be clearly and completely displayed, making the system review more accurate. The line integral P of the straight line f(x, y) is calculated using the following formula:

[0036]

[0037] in, θ is expressed as the tilt angle of the line perpendicular to the line in the original image;

[0038] According to the angle obtained by analysis, the original image is rotated and calibrated, and the calibration angle is 90-θ.

[0039] By calibrating the image, even if the user does not hold the proof documents correctly, it can be corrected automatically, effectively improving the accuracy and robustness of the intelligent review, avoiding the situation where the review fails due to the user not holding the proof documents correctly, reducing the number of times the user submits repeatedly, and improving the user experience of handling business online.

[0040] Furthermore, in step S4, the picture proof materials captured in the video are reviewed based on the analysis and processing results and the review standards entered into the database, and the user is notified. For example, when there is missing or erroneous proof material, the user is notified to modify and resubmit. If the user has any questions about the review, he or she can submit it for manual review. The system automatically learns and enters the information, thereby improving the accuracy and security of the review.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention changes the original uploaded images as proof materials to uploaded videos by entering database keyword information and audit standards, analyzes and processes the videos to automatically capture clips from the videos as proof materials, and calibrates the captured images. This effectively ensures the authenticity and security of the uploaded data, prevents the user's ID card information from being used by others, thereby threatening the user's economic and information security. Even if business is handled with the help of others, such as an elderly person applying with the help of their children, the user handling the business must record the video themselves, and no one else can do it on their behalf. This ensures that the uploaded data matches the user's own. At the same time, the present invention encrypts the entire process of the user handling the business, effectively ensuring user data security and preventing the leakage of user-filled information and video information, which could threaten the user's personal property and information security. Afterwards, the system performs intelligent auditing on the data information uploaded by the user and sends a notification to the user, such as informing the user of the reason for failure and how to modify the information. This facilitates user operation and eliminates the need for the user to repeatedly visit the Industrial and Commercial Bureau to modify the information, saving the user time and improving the user's online business experience. If the user has any questions about the audit results, they can request manual auditing, and the system automatically learns and continuously improves the system, thereby achieving audit accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 This is a schematic diagram of the module composition of the self-employed smart approval system based on the Internet of Things of the present invention;

[0045] Figure 2This is a schematic diagram of the steps of the smart approval method for self-employed individuals based on the Internet of Things of the present invention; DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0047] See also Figure 1-Figure 2 , the present invention provides a technical solution: a self-employed smart approval system based on the Internet of Things, characterized in that: the smart approval system includes a data acquisition module, a database, a data analysis module and a data feedback module;

[0048] The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the data feedback module;

[0049] The data acquisition module includes a basic data acquisition unit and a video acquisition unit. The basic data acquisition unit is used to input basic keyword information and judgment standard information, such as user name, business mode and business scope, etc., which provides a basis for the system to perform intelligent analysis and review of information, thereby improving the accuracy of data review. The video acquisition unit is used to collect video material information uploaded by users through the Internet of Things, automatically identify the audio in the video based on the video, and generate a text file. For example, by taking a photo of the user holding the file to be uploaded and describing it, the user submits information by uploading a video, which can effectively solve the problem of not being able to determine whether the uploader is the person in the picture information when uploading the picture. Even if the user holds a photo of his / her ID card, it is difficult to ensure that the photo is the photo required for the current business transaction. It can effectively improve the accuracy of information analysis and review, and avoid the situation where the user handling the business is inconsistent with the identity information. Even if the business is handled with the help of others, such as an elderly person applying with the help of their children, the user handling the business must record the video himself / herself, and no one else can replace him / her. This ensures that the uploaded data matches the user himself / herself. At the same time, because the video contains audio, it can effectively ensure that the video used is the video required for the current business transaction, thereby avoiding the situation of information misappropriation.

[0050] The database is used to encrypt and store the collected data information and analysis results. The database includes a storage unit and an encryption unit. The storage unit is used to store the entered keyword information, the collected video and text information and the analysis results. The encryption unit encrypts the stored data information and the entire encryption process through the AES encryption algorithm. The AES encryption algorithm is an advanced encryption standard in cryptography. The encryption algorithm adopts a symmetric block cipher system. The minimum supported key length is 128 bits, 192 bits, and 256 bits, and the block length is 128 bits. The algorithm should be easy to implement in various hardware and software. The AES algorithm mainly has four operation processes, namely, a key addition layer, a byte substitution layer, a row shift layer, and a column confusion layer. AES itself is intended to replace DES. AES has better security, efficiency and flexibility, and can effectively ensure the security of data when individual households handle business, protect the privacy information security of users, and prevent information leakage from posing a threat to the information security and personal property security of individual households.

[0051] The data analysis module is used to analyze and process the collected video information. The data analysis module includes a video extraction unit and an image calibration unit. The video extraction unit is used to analyze the video uploaded by the user, analyze and intercept the video according to the keyword information stored in the database, and use the intercepted image as the proof material for the self-employed to handle business. This can effectively ensure the accuracy of the proof material, ensure that it is the user who needs to handle the business who is performing the operation, and prevent the information from being used by others. The image calibration unit is used to calibrate the intercepted image, such as enlarging the document material held by the user, so that the system can better review and judge the image, improve the accuracy of the review, avoid the situation where the review fails due to improper holding posture of the user, reduce the number of modifications by the user, and improve the user experience of self-employed users in handling business online.

[0052] The data feedback module is used to automatically review and determine the information uploaded by the user based on the analysis results and notify the user. The data feedback module includes a data review unit and a user notification unit. The data review unit is used to review and determine the image evidence materials that have been analyzed and intercepted based on the analysis results and the judgment standard information stored in the database. The user notification unit is used to send a notification to the user who is handling the business. If the materials submitted by the user are accurate, a notification is sent to the user, such as a text message to remind the user that the review has passed. If the materials submitted by the user are missing or incorrect, a notification is sent to the user, such as informing the user of the existing problems and modification suggestions, so that the user can timely understand the progress of the business processing and at the same time understand the specific material information that needs to be modified.

[0053] The smart approval method for self-employed individuals based on the Internet of Things includes the following steps:

[0054] S1. Input basic data information and review standards, collect video evidence uploaded by users, automatically convert the audio in the video into text information, and encrypt and store it in the database;

[0055] S2. Analyze and process the collected user-uploaded videos, and capture images as evidence based on keyword information stored in the database;

[0056] In step S2, the text information automatically converted from the video uploaded by the user is analyzed based on the keyword information entered in the database;

[0057] In the automatically converted text, the time at which a sentence containing a keyword appears determines the importance of the sentence. For example, a sentence containing a keyword that appears earlier is more important than a sentence containing a keyword that appears later. The following formula is used to analyze the importance of the keyword position F1:

[0058] F1 = log2(log2(2+Z));

[0059] Where Z is the median position of all sentences containing the keyword in the text;

[0060] The keyword frequency F2 is normalized using the following formula:

[0061]

[0062] Where T represents the number of times the keyword appears, A represents the mean frequency of the keyword, and σ is the standard deviation;

[0063] The number of related words that appear with a keyword determines the importance of the keyword. For example, the more different words a keyword appears with, the lower the importance of the keyword. The following formula is used to analyze the relationship between the keyword and the context F3:

[0064]

[0065] Where B represents the number of different words that appear with the keyword, C represents the maximum frequency of the keyword in the text, and k represents the number of different words that appear with the keyword in the kth order.

[0066] The number of sentences containing a keyword determines the importance of the keyword. For example, the more sentences a keyword appears in, the more important it is. The frequency F4 of the keyword in a sentence is analyzed using the following formula:

[0067]

[0068] Among them, Q represents the frequency of occurrence of sentences containing keywords, and S represents the number of all sentences in the text;

[0069] The score M of each keyword is calculated by the following formula:

[0070]

[0071] Set a threshold M for each keyword score 阈 , when M<M 阈 When M≥M, it means that the keyword is important. The position of the keyword in the text and the corresponding key frame of the video are extracted and the key frame is intercepted as the evidence. 阈 When , it means that the words that appear are not important and have nothing to do with the part that needs to be reviewed, and the system automatically filters them out.

[0072] By analyzing keywords to capture images, we can effectively avoid the failure of the review caused by capturing unnecessary pages, improve the accuracy and security of the supporting materials, and even if the user's ID card is lost, we can ensure that his or her identity information will not be used by others for self-employed registration or self-employed business license processing, and avoid the situation where others use the user's identity information to obtain loans, etc., thereby protecting the user's privacy information and personal property security, and improving the user's online business experience.

[0073] S3, calibrating the captured image;

[0074] In step S3, the image captured as the evidence material is binarized and then calibrated to establish a plane rectangular coordinate system. The straight line f(x, y) in the image is detected and projected. The projection can be performed along any angle. For example, the user image captured as the evidence material is enlarged and calibrated so that the evidence material in the user's hand can be clearly and completely displayed, making the system review more accurate. The line integral P of the straight line f(x, y) is calculated using the following formula:

[0075]

[0076] in, θ is expressed as the tilt angle of the line perpendicular to the line in the original image;

[0077] According to the angle obtained by analysis, the original image is rotated and calibrated, and the calibration angle is 90-θ.

[0078] By calibrating the image, even if the user does not hold the proof documents correctly, it can be corrected automatically, effectively improving the accuracy and robustness of the intelligent review, avoiding the situation where the review fails due to the user not holding the proof documents correctly, reducing the number of times the user submits repeatedly, and improving the user experience of handling business online.

[0079] S4. Based on the analysis results and the audit standards stored in the database, the captured image is audited and judged, and a notification is sent to the user.

[0080] In step S4, the picture proof materials captured in the video are reviewed based on the analysis and processing results and the review standards entered in the database, and the user is notified. For example, when there are missing or incorrect proof materials, the user is notified to modify and resubmit. If the user has any questions about the review, he or she can submit it for manual review. The system automatically learns and enters the information, which improves the accuracy and security of the review.

[0081] Example 1:

[0082] If we analyze the videos uploaded by users and get the keyword score M of a certain keyword, it is:

[0083]

[0084] Set a threshold M for the keyword score 阈 =0.5; at this time, M<M 阈 , extract the location where the keyword appears in the text and the corresponding key frame of the video, and capture the key frame as evidence.

[0085] If the score M of a word is At this time, M≥M 阈 , indicating that the words that appear are unimportant and irrelevant to the part that needs to be reviewed. The system automatically filters them and does not intercept them.

[0086] If a keyword does not appear in the user's application, it means that there are missing materials in the submitted documents. The user's application will be deemed unsuccessful and a notification will be sent to the user to inform him of the missing materials and to remind him to reapply.

[0087] Example 2:

[0088] After analysis, the image is captured as evidence. If the line f(x, y) in the image is detected as one of the edges of the evidence held by the user in the image, the line integral P of the line f(x, y) is calculated using the following formula:

[0089]

[0090] If the angle θ=75° is obtained according to the analysis, the original image is rotated and calibrated with a calibration angle of 15°, and the rotated and calibrated image is audited according to the audit standards entered in the database, thereby improving the accuracy of the intelligent audit and avoiding the occurrence of different audits due to the user's holding posture.

[0091] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0092] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. The intelligent approval method for self-employed individuals based on the Internet of Things is characterized by: The following steps are involved: S1. Input basic data information and review standards, collect video evidence uploaded by users, automatically convert the audio in the video into text information, and encrypt and store it in the database; S2. Analyze and process the collected user-uploaded videos, and capture images as evidence based on keyword information stored in the database; S3, calibrating the captured image; S4. Based on the analysis results and the audit standards stored in the database, the captured image is audited and judged, and a notification is sent to the user; In step S2, the text information automatically converted from the video uploaded by the user is analyzed based on the keyword information entered in the database; In the automatically converted text, the time when a sentence containing a keyword appears determines the importance of the sentence. The following formula is used to analyze the importance of the keyword position F1: F1 = log2(log2(2+Z)); Where Z is the median position of all sentences containing the keyword in the text; The keyword frequency F2 is normalized using the following formula: Where T represents the number of times the keyword appears, A represents the mean frequency of the keyword, and σ is the standard deviation; The number of related words that appear with a keyword determines the importance of the keyword. The following formula is used to analyze the relationship between the keyword and the context F3: Where B represents the number of different words that appear with the keyword, C represents the maximum frequency of the keyword in the text, and k represents the number of different words that appear with the keyword in the kth order. The number of sentences containing a keyword determines the importance of the keyword. The frequency F4 of the keyword in the sentence is analyzed using the following formula: Among them, Q represents the frequency of occurrence of sentences containing keywords, and S represents the number of all sentences in the text; The score M of each keyword is calculated by the following formula: Set a threshold M for each keyword score 阈 , when M <M 阈 When M≥M, it means that the keyword is important. The position of the keyword in the text and the corresponding key frame of the video are extracted and the key frame is intercepted as the evidence. 阈 When , it means that the words appearing are not important and have nothing to do with the part that needs to be reviewed, and the system automatically filters them out; In step S3, the image captured as evidence is binarized and calibrated, a plane rectangular coordinate system is established, a straight line f(x, y) in the image is detected, the line is projected, and the line integral P of the line f(x, y) is calculated using the following formula: in, θ is expressed as the tilt angle of the line perpendicular to the line in the original image; According to the angle obtained by analysis, the original image is rotated and calibrated, and the calibration angle is 90-θ; In step S4, the image evidence material captured from the video is reviewed based on the analysis results and the review standards entered into the database, and the user is notified.

2. An intelligent approval system for self-employed individuals based on the Internet of Things, wherein the system is applied to the intelligent approval method for self-employed individuals based on the Internet of Things according to claim 1, and characterized by: The smart approval system includes: data collection module, database, data analysis module and data feedback module; The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the data feedback module; the data acquisition module is used to collect basic data information and video material information, the database is used to encrypt and store the collected data information and analysis results, the data analysis module is used to analyze and process the collected video information, and the data feedback module is used to automatically review and determine the information uploaded by the user based on the analysis results, and notify the user.

3. The IoT-based self-employed smart approval system according to claim 2 is characterized by: The data acquisition module includes a basic data acquisition unit and a video acquisition unit. The basic data acquisition unit is used to input basic keyword information and judgment standard information. The video acquisition unit is used to collect video material information uploaded by users, automatically identify the audio therein according to the video, and generate a text file.

4. The IoT-based self-employed smart approval system according to claim 3 is characterized by: The database includes a storage unit and an encryption unit. The storage unit is used to store input keyword information, collected video and text information and analysis results. The encryption unit encrypts the stored data information and the entire encryption process using the AES encryption algorithm.

5. The IoT-based self-employed smart approval system according to claim 4 is characterized by: The data analysis module includes a video extraction unit and an image calibration unit. The video extraction unit is used to analyze the video uploaded by the user, analyze and intercept the video according to the keyword information stored in the database, and use the intercepted image as proof of business operations for individual businesses. The image calibration unit is used to calibrate the intercepted image.

6. The IoT-based self-employed smart approval system according to claim 5 is characterized by: The data feedback module includes a data review unit and a user notification unit. The data review unit is used to review and judge the image proof materials that have been analyzed and intercepted based on the analysis results and the judgment standard information stored in the database. The user notification unit is used to send notifications to users who handle business.

Images