A business management system based on SaaS

Abstract

The present invention belongs to the field of business management, and discloses a business management system based on SaaS, including a main terminal device, a slave terminal device and a SaaS business management server; the main terminal device sends a user's facial image to the SaaS business management server; the SaaS business management server generates an encrypted first token and a set of a preset number of identity identification codes after identity recognition, and then sends them to the main terminal device; before the terminal device establishes a communication connection with the SaaS business management server, it obtains the identity identification code from the main terminal device, and then sends the identity identification code to the SaaS business management server; the SaaS business management server generates an encrypted second token when the identity identification code is valid, and sends it to the slave terminal device. The present invention improves the convenience of verification when the business management system is used on different terminal devices at the same time.

Description

Technical Field

[0001] The present invention relates to the field of business management, and in particular to a business management system based on SaaS. Background Art

[0002] The existing business management system generally performs login verification based on account password, face, verification code, etc. If the business management system needs to be used on multiple terminal devices at the same time, multiple login verifications need to be repeated, which is obviously not convenient enough. Summary of the invention

[0003] The purpose of the present invention is to disclose a business management system based on SaaS to solve the problem of how to improve the convenience of verification of the business management system when logging in from multiple terminals.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The present invention provides a SaaS-based business management system, including a master terminal device, a slave terminal device and a SaaS business management server;

[0006] The main terminal device is used to obtain the user's facial image and send the facial image to the SaaS business management server;

[0007] The SaaS business management server is used to perform identity recognition on the face image sent by the main terminal device. If the identity recognition is successful, it generates a set of an encrypted first token and a preset number of identity identification codes, and sends the encrypted first token and the preset number of identity identification codes to the main terminal device;

[0008] The slave terminal device is used to establish an encrypted connection with the master terminal device before establishing a communication connection with the SaaS business management server;

[0009] The master terminal device is used to randomly select an identity identification code and transmit it to the slave terminal device through an encrypted connection, and delete the transmitted identity identification code from the set of identity identification codes;

[0010] The slave terminal device is also used to send the identity identification code to the SaaS business management server;

[0011] The SaaS business management server is also used to determine whether the identity identification code sent from the terminal device is valid. If it is valid, an encrypted second token is generated and sent to the terminal device.

[0012] Optionally, the number of master terminal devices is 1, and the number of slave terminal devices is multiple.

[0013] Optionally, identity recognition is performed on the face image sent by the main terminal device, including:

[0014] Obtain image feature A of the face image sent by the main terminal device;

[0015] The image feature A is compared with the image features of the pre-saved facial images of each person with the operation authority of the SaaS business management platform to determine whether the identity recognition is successful.

[0016] Optionally, obtaining an image feature A of a face image sent by the main terminal device includes:

[0017] Preprocess the face image sent by the main terminal device to obtain the image to be extracted;

[0018] Perform feature extraction on the image to be extracted to obtain image feature A.

[0019] Optionally, preprocessing the face image sent by the main terminal device to obtain the image to be extracted includes:

[0020] Filtering the face image sent by the main terminal device to obtain a filtered image;

[0021] Perform image segmentation processing on the filtered image to obtain the image to be extracted.

[0022] Optionally, filtering the face image sent by the main terminal device to obtain a filtered image includes:

[0023] Using a first filtering algorithm to filter the face image to obtain a first filtered image;

[0024] Using a second filtering algorithm to filter the face image to obtain a second filtered image;

[0025] The first filtered image and the second filtered image are merged to obtain a filtered image.

[0026] Optionally, the first filtering algorithm includes any one of a bilateral filtering algorithm, a non-local filtering algorithm, a Gaussian filtering algorithm, and an anisotropic diffusion filtering algorithm;

[0027] The second filtering algorithm includes any one of an ILPF algorithm, a BLPF algorithm, a BHPF algorithm, and a homomorphic filtering algorithm.

[0028] Optionally, merging the first filtered image and the second filtered image to obtain a filtered image includes:

[0029] Calculating a merging coefficient of the first filtered image and a merging coefficient of the second filtered image;

[0030] The first filtered image and the second filtered image are merged based on the merging coefficient of the first filtered image and the merging coefficient of the second filtered image to obtain a filtered image.

[0031] Optionally, performing image segmentation processing on the filtered image to obtain an image to be extracted includes:

[0032] Divide the filtered image into blocks, and divide the filtered image into a plurality of regions with the same area;

[0033] Calculate the face area coefficient of each area respectively;

[0034] Using an image segmentation algorithm to segment the area where the face area coefficient is greater than or equal to a preset face area coefficient threshold, to obtain the face area in the area where the face area coefficient is greater than or equal to the preset face area coefficient threshold;

[0035] Each area whose face area coefficient is less than a preset face area coefficient threshold is judged respectively, and the area whose face area coefficient is less than the preset face area coefficient threshold is divided into a valid area and an invalid area;

[0036] Only the face area and the effective area are retained in the filtered image to obtain the image to be extracted.

[0037] Optionally, before obtaining the facial image used, the main terminal device first performs a liveness detection on the user, and if the user passes the liveness detection, the facial image of the user is obtained.

[0038] Compared with the prior art, the beneficial effects of the present invention include:

[0039] The present invention first performs identity recognition through the main terminal device, and then the main terminal device saves the identity recognition code sent by the SaaS business management server; when a slave terminal device needs to communicate with the SaaS business management server, the slave terminal device directly obtains the identity recognition code from the main terminal device, and then the slave terminal device communicates with the SaaS business management server with the identity recognition code to obtain a second token for subsequent communication, so that the user does not need to perform repeated login verification on the slave terminal, thereby improving the convenience of verification when the business management system needs to be used on different terminal devices at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A schematic diagram of a SaaS-based business management system of the present invention.

[0042] Figure 2 The present invention is a schematic diagram of the process of performing image segmentation processing on a filtered image to obtain an image to be extracted. DETAILED DESCRIPTION

[0043] 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 parameters of the protection of the present invention.

[0044] like Figure 1 In one embodiment shown, the present invention provides a SaaS-based business management system, including a master terminal device, a slave terminal device and a SaaS business management server;

[0045] The main terminal device is used to obtain the user's facial image and send the facial image to the SaaS business management server;

[0046] The SaaS business management server is used to perform identity recognition on the face image sent by the main terminal device. If the identity recognition is successful, it generates a set of an encrypted first token and a preset number of identity identification codes, and sends the encrypted first token and the preset number of identity identification codes to the main terminal device;

[0047] The slave terminal device is used to establish an encrypted connection with the master terminal device before establishing a communication connection with the SaaS business management server;

[0048] The master terminal device is used to randomly select an identity identification code and transmit it to the slave terminal device through an encrypted connection, and delete the transmitted identity identification code from the set of identity identification codes;

[0049] The slave terminal device is also used to send the identity identification code to the SaaS business management server;

[0050] The SaaS business management server is also used to determine whether the identity identification code sent from the terminal device is valid. If it is valid, an encrypted second token is generated and sent to the terminal device.

[0051] The present invention first performs identity recognition through the main terminal device, and then the main terminal device saves the identity recognition code sent by the SaaS business management server; when a slave terminal device needs to communicate with the SaaS business management server, the slave terminal device directly obtains the identity recognition code from the main terminal device, and then the slave terminal device communicates with the SaaS business management server with the identity recognition code to obtain a second token for subsequent communication, so that the user does not need to perform repeated login verification on the slave terminal, thereby improving the convenience of verification when the business management system needs to be used on different terminal devices at the same time.

[0052] Token is a string of characters generated by the server, which is used as a token for client requests. After the first login, the server generates a token and returns it to the client. In the future, the client only needs to bring this token to request data, without having to bring the information for identity authentication again.

[0053] Optionally, the SaaS business management server is further used to periodically communicate with the main terminal device after the identity recognition is passed, and send a set of newly generated identity identification codes to the main terminal device;

[0054] After receiving the new set of identity identification codes, the master terminal device deletes the previously obtained set of identity identification codes, thereby realizing the update of the identity identification codes.

[0055] Regularly updating the identity identification code can improve the security of the present invention.

[0056] Specifically, each time the SaaS business management server generates a set of identity identification codes, it saves the generated set of identity identification codes and then starts a countdown of a preset duration. When the countdown ends, the previously generated set of identity identification codes is deleted, a new set of identity identification codes is generated, and then communication with the main terminal device is carried out again.

[0057] Specifically, if the master terminal device and / or the slave terminal device does not communicate with the SaaS business management server for more than a preset time period, the SaaS business management server deletes the first token and / or the second token.

[0058] If the connection fails during timeout, the token will be deleted to ensure the security of the system.

[0059] Optionally, the identification code is a random number in the range of 0-999999. For the same terminal device, if it still fails to pass the identity recognition after exceeding the verification times, the IP of the terminal device will be added to the blacklist.

[0060] Specifically, after being added to the blacklist, only the super administrator has the authority to modify and delete the IP from the blacklist.

[0061] Optionally, the master terminal device and the slave terminal device communicate with each other via encrypted Bluetooth.

[0062] Optionally, the SaaS business management server uses the public key of the main terminal device to encrypt the set of identity identification codes and sends it to the main terminal device. After receiving the encrypted set of identity identification codes, the main terminal device uses the private key to decrypt the encrypted set of identity identification codes.

[0063] Optionally, the SaaS business management server encrypts the first token and the second token using its own public key to obtain the encrypted first token and the second token;

[0064] After receiving a request containing an encrypted first token from the main terminal device or a request containing an encrypted second token from the terminal device, the encrypted first token and second token are decrypted using its own private key. If the decryption is successful, it indicates that the request is secure.

[0065] Optionally, the SaaS business management server encrypts the set of identity identification codes using the public key of the slave terminal device and sends it to the slave terminal device. After receiving the encrypted set of identity identification codes, the slave terminal device uses the private key to decrypt the encrypted set of identity identification codes.

[0066] Optionally, the master terminal device and the slave terminal device run service management software, which can send a request message for managing the service to the SaaS service management server, such as sending a query message to the SaaS service management server, the query message carrying attribute information of the order and the corresponding token.

[0067] Optionally, the number of master terminal devices is 1, and the number of slave terminal devices is multiple.

[0068] Specifically, the master terminal device is a device with a face shooting function. For example, the master terminal device may be a smart phone, and the slave terminal device may be a notebook, a tablet or other device.

[0069] Optionally, identity recognition is performed on the face image sent by the main terminal device, including:

[0070] Obtain image feature A of the face image sent by the main terminal device;

[0071] The image feature A is compared with the image features of the pre-saved facial images of each person with the operation authority of the SaaS business management platform to determine whether the identity recognition is successful.

[0072] Specifically, in the SaaS business management platform, the user's facial image can be entered when the user registers for the first time.

[0073] Optionally, obtaining an image feature A of a face image sent by the main terminal device includes:

[0074] Preprocess the face image sent by the main terminal device to obtain the image to be extracted;

[0075] Perform feature extraction on the image to be extracted to obtain image feature A.

[0076] Specifically, by performing preprocessing, the quality of the image can be improved so that more accurate image features can be obtained.

[0077] Optionally, preprocessing the face image sent by the main terminal device to obtain the image to be extracted includes:

[0078] Filtering the face image sent by the main terminal device to obtain a filtered image;

[0079] Perform image segmentation processing on the filtered image to obtain the image to be extracted.

[0080] Specifically, image filtering processing can reduce the noise in the face image, so that the signal-to-noise ratio of the filtered image is higher and the quality is better, which is conducive to the subsequent feature extraction process to obtain more accurate image features.

[0081] Optionally, filtering the face image sent by the main terminal device to obtain a filtered image includes:

[0082] Using a first filtering algorithm to filter the face image to obtain a first filtered image;

[0083] Using a second filtering algorithm to filter the face image to obtain a second filtered image;

[0084] The first filtered image and the second filtered image are merged to obtain a filtered image.

[0085] Specifically, by using two filtering algorithms to filter the face images respectively, the adaptability of the filtering process can be improved. Because the best applicable filtering algorithms for different images are different, the present invention uses different filtering algorithms to perform filtering and then merges the obtained filtered images, so that the filtering process of the present invention can be applied to more types of noisy images and has better applicability.

[0086] Optionally, the first filtering algorithm includes any one of a bilateral filtering algorithm, a non-local filtering algorithm, a Gaussian filtering algorithm, and an anisotropic diffusion filtering algorithm;

[0087] The second filtering algorithm includes any one of an ILPF algorithm, a BLPF algorithm, a BHPF algorithm, and a homomorphic filtering algorithm.

[0088] Specifically, the first filtering algorithm basically performs filtering in the spatial domain, while the second filtering algorithm basically performs filtering in the transform domain. Since the domains used for filtering are different, a better filtered image can be obtained when the filtering results are combined.

[0089] Optionally, merging the first filtered image and the second filtered image to obtain a filtered image includes:

[0090] Calculating a merging coefficient of the first filtered image and a merging coefficient of the second filtered image;

[0091] The first filtered image and the second filtered image are merged based on the merging coefficient of the first filtered image and the merging coefficient of the second filtered image to obtain a filtered image.

[0092] Optionally, the calculation formula of the merging coefficient of the first filtered image is:

[0093]

[0094] The calculation formula of the merging coefficient of the second filtering image is:

[0095]

[0096] fircef and seccef represent the merging coefficients of the first filtered image and the second filtered image, respectively. nfpx i Indicates the number of pixels with grayscale value i in the first filtered image, nfpx j It represents the number of pixels with gray value j in the second filtered image, and nfsm represents the total number of pixels in the face image sent by the main terminal device.

[0097] Specifically, in the process of calculating the first merging coefficient and the second merging coefficient, the present invention obtains the effective information content in the image by respectively calculating the logarithmic results of the proportions of pixel points with different grayscale values ​​in the first filtered processed image and the second filtered processed image. The larger the logarithmic result, the more effective information is in the image. Therefore, in the subsequent merging process, the greater the contribution to the final merging result, so that the merging result can integrate the filtering results of the two filtering algorithms while having a certain emphasis, so that the details in the filtered processed image with better filtering effect can be brought into the filtered image more, thereby ensuring the quality of the filtered image.

[0098] Optionally, merging the first filtered image and the second filtered image based on the merging coefficient of the first filtered image and the merging coefficient of the second filtered image to obtain a filtered image includes:

[0099] filimg(x,y)=firimg(x,y)+seccef×secimg(x,y)

[0100] filimg(x,y) represents the grayscale value of the pixel with coordinates (x,y) in the filtered image, firimg(x,y) represents the grayscale value of the pixel with coordinates (x,y) in the first filtered image, and secimg(x,y) represents the grayscale value of the pixel with coordinates (x,y) in the second filtered image.

[0101] Specifically, since the sizes of the first filtered image, the second filtered image and the filtered image are the same, the pixel points with the same coordinates can be merged to obtain a merged result.

[0102] Optionally, performing image segmentation processing on the filtered image to obtain an image to be extracted includes:

[0103] Divide the filtered image into blocks, and divide the filtered image into a plurality of regions with the same area;

[0104] Calculate the face area coefficient of each area respectively;

[0105] Using an image segmentation algorithm to segment the area where the face area coefficient is greater than or equal to a preset face area coefficient threshold, to obtain the face area in the area where the face area coefficient is greater than or equal to the preset face area coefficient threshold;

[0106] Each area whose face area coefficient is less than a preset face area coefficient threshold is judged respectively, and the area whose face area coefficient is less than the preset face area coefficient threshold is divided into a valid area and an invalid area;

[0107] Only the face area and the effective area are retained in the filtered image to obtain the image to be extracted.

[0108] Specifically, in the process of obtaining the image to be extracted, the present invention does not directly use image segmentation to segment the entire filtered image, because the larger the segmented area, the lower the segmentation accuracy, and face recognition requires a more accurate image. Therefore, the present invention divides the filtered image into blocks first, and then performs further segmentation processing in each area, thereby improving the segmentation efficiency and the segmentation accuracy.

[0109] Optionally, the filtered image is divided into blocks, and the filtered image is divided into a plurality of regions of equal area, including:

[0110] The filtered image is divided into M×M regions of the same area, where M is a preset number.

[0111] Optionally, M is 10.

[0112] Optionally, using an image segmentation algorithm to segment a region where the face region coefficient is greater than or equal to a preset face region coefficient threshold, and obtaining a face region in the region where the face region coefficient is greater than or equal to the preset face region coefficient threshold, comprises:

[0113] The image segmentation algorithm based on a single threshold is used to calculate the area where the face area coefficient is greater than or equal to the preset face area coefficient threshold to obtain the segmentation threshold.

[0114] The face region in the region where the face region coefficient is greater than or equal to the preset face region coefficient threshold is composed of pixel points whose gray value is greater than the segmentation threshold.

[0115] Optionally, the face area coefficient is calculated as:

[0116]

[0117] fcbkcef b represents the face area coefficient of area b, Nblpix represents the total number of edge pixels in area b, Npixal represents the total number of pixels in area b, η represents the first weight, pxfb represents the set of pixels in area b, gry k Represents the gray value of pixel k, gry max represents the median of the grayscale values ​​of the pixels in area b, and δ represents the second weight.

[0118] Specifically, the face region coefficient is mainly used to identify whether the region contains sufficient detail information and edge information. The face region coefficient is calculated from two angles: the total number of edge pixels and the variance of the grayscale values ​​of the pixels in the region. This allows the present invention to select the region containing the edge of the face, and for the region not containing the edge of the face, further judgment is made to take the region belonging to the skin part of the face as the valid region. Because if the edge information contained in the region is too small, such as the region of the cheek part of the face, it is easy to be segmented incorrectly by the image segmentation algorithm, thereby affecting the accuracy of the image to be extracted.

[0119] Optionally, the value of the first weight is 0.6, and the value of the second weight is 0.4.

[0120] Optionally, the preset face area coefficient threshold is 0.85.

[0121] Optionally, each area whose face area coefficient is less than a preset face area coefficient threshold is judged respectively, and the area whose face area coefficient is less than the preset face area coefficient threshold is divided into a valid area and an invalid area, including:

[0122] Obtaining the number U of pixel points conforming to the skin color model in an area whose face area coefficient is less than a preset face area coefficient threshold;

[0123] If the number U is greater than the set number threshold, it means that the area is a valid area. If the number U is less than or equal to the set number threshold, it means that the area is an invalid area.

[0124] Specifically, the preset quantity threshold is 10.

[0125] Optionally, the image feature A is compared with the image features of the face images of each person who has the operation authority of the SaaS business management platform that are pre-saved to determine whether the identity recognition is passed, including:

[0126] The image feature obtained by extracting the image feature of the face image of the person who has the operation authority of the SaaS business management platform saved in advance is recorded as the image feature B;

[0127] Calculate the similarity between image feature A and each image feature B respectively;

[0128] If the maximum similarity value is greater than the similarity threshold, it means that the identity recognition is successful.

[0129] Specifically, the same feature extraction process as that of image feature A is adopted to obtain the image features of the facial images of each person who has the operation authority of the SaaS business management platform.

[0130] Optionally, the similarity threshold is 0.96.

[0131] Optionally, before obtaining the facial image used, the main terminal device first performs a liveness detection on the user, and if the user passes the liveness detection, the facial image of the user is obtained.

[0132] Liveness detection can prevent users' facial images from being illegally used for identity recognition.

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope parameters of the technical solutions of the embodiments of the present invention.

Claims

1. A SaaS-based business management system, characterized in that: Including master terminal equipment, slave terminal equipment and SaaS business management server; The main terminal device is used to obtain the user's facial image and send the facial image to the SaaS business management server; The SaaS business management server is used to perform identity recognition on the face image sent by the main terminal device. If the identity recognition is successful, it generates a set of an encrypted first token and a preset number of identity identification codes, and sends the encrypted first token and the preset number of identity identification codes to the main terminal device; The slave terminal device is used to establish an encrypted connection with the master terminal device before establishing a communication connection with the SaaS business management server; The master terminal device is used to randomly select an identity identification code and transmit it to the slave terminal device through an encrypted connection, and delete the transmitted identity identification code from the set of identity identification codes; The slave terminal device is also used to send the identity identification code to the SaaS business management server; The SaaS business management server is also used to determine whether the identity identification code sent from the terminal device is valid. If it is valid, it generates an encrypted second token and sends the encrypted second token to the terminal device; Perform identity recognition on the face image sent by the main terminal device, including: Obtain image feature A of the face image sent by the main terminal device; Compare the image feature A with the image features of the face images of each person who has the operation authority of the SaaS business management platform that has been saved in advance to determine whether the identity recognition is successful; Obtain the image feature A of the face image sent by the main terminal device, including: Preprocess the face image sent by the main terminal device to obtain the image to be extracted; Perform feature extraction on the image to be extracted to obtain image feature A; Preprocess the face image sent by the main terminal device to obtain the image to be extracted, including: Filtering the face image sent by the main terminal device to obtain a filtered image; Performing image segmentation processing on the filtered image to obtain an image to be extracted; The face image sent by the main terminal device is filtered to obtain a filtered image, including: Using a first filtering algorithm to filter the face image to obtain a first filtered image; Using a second filtering algorithm to filter the face image to obtain a second filtered image; Merging the first filtered image and the second filtered image to obtain a filtered image; The first filtered image and the second filtered image are combined to obtain a filtered image, including: Calculating a merging coefficient of the first filtered image and a merging coefficient of the second filtered image; Merging the first filtered image and the second filtered image based on the merging coefficient of the first filtered image and the merging coefficient of the second filtered image to obtain a filtered image; The calculation formula of the merging coefficient of the first filtering processed image is: The calculation formula of the merging coefficient of the second filtering image is: fircef and seccef represent the merging coefficients of the first filtered image and the second filtered image, respectively. nfpx i Indicates the number of pixels with grayscale value i in the first filtered image, nfpx j represents the number of pixels with gray value j in the second filtered image, and nfsm represents the total number of pixels in the face image sent by the main terminal device; Perform image segmentation processing on the filtered image to obtain the image to be extracted, including: Divide the filtered image into blocks, and divide the filtered image into a plurality of regions with the same area; Calculate the face area coefficient of each area respectively; Using an image segmentation algorithm to segment the area where the face area coefficient is greater than or equal to a preset face area coefficient threshold, to obtain the face area in the area where the face area coefficient is greater than or equal to the preset face area coefficient threshold; Each area whose face area coefficient is less than a preset face area coefficient threshold is judged respectively, and the area whose face area coefficient is less than the preset face area coefficient threshold is divided into a valid area and an invalid area; Only the face area and the effective area are retained in the filtered image to obtain the image to be extracted; An image segmentation algorithm is used to segment an area where a face area coefficient is greater than or equal to a preset face area coefficient threshold, and a face area in an area where a face area coefficient is greater than or equal to the preset face area coefficient threshold is obtained, including: The image segmentation algorithm based on a single threshold is used to calculate the area where the face area coefficient is greater than or equal to the preset face area coefficient threshold to obtain the segmentation threshold. The face region in the region where the face region coefficient is greater than or equal to the preset face region coefficient threshold is formed by the pixel points whose gray value is greater than the segmentation threshold; The calculation formula of the face area coefficient is: fcbkcef b represents the face area coefficient of area b, Nblpix represents the total number of edge pixels in area b, Npixal represents the total number of pixels in area b, η represents the first weight, pxfb represents the set of pixels in area b, gry k Represents the gray value of pixel k, gry max represents the median of the grayscale values ​​of the pixels in area b, and δ represents the second weight.

2. A SaaS-based business management system according to claim 1, characterized in that: The number of master terminal devices is 1, and the number of slave terminal devices is multiple.

3. A SaaS-based business management system according to claim 1, characterized in that: The first filtering algorithm includes any one of a bilateral filtering algorithm, a non-local filtering algorithm, a Gaussian filtering algorithm, and an anisotropic diffusion filtering algorithm; The second filtering algorithm includes any one of an ILPF algorithm, a BLPF algorithm, a BHPF algorithm, and a homomorphic filtering algorithm.

4. A SaaS-based business management system according to claim 1, characterized in that: Before obtaining the facial image of the user, the main terminal device first performs a liveness detection on the user. If the user passes the liveness detection, the facial image of the user is obtained.

Images