A rental management method and system
Through the online rental platform, the key point detection of tenant images is obtained to obtain the integration of facial and non-face features, forming a reliability evaluation coefficient, solving the problem of tenant identity authentication in the traditional rental model, improving the security and trust of rental management, and suitable Short-term rental housing management.
Patent Information
- Application Number
- CN202110018643.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-01-07
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the traditional rental model, tenants and rental managers are complicated to connect, and the rental file information of the public security management department is incomplete and inaccurate, which makes it difficult to authenticate tenants' identity information, and lacks means to identify and judge bad habits and violent behaviors of renters.
The online rental platform collects tenant images, performs key point detection to obtain facial and non-face features, and integrates them to form a reliability evaluation coefficient. Rental managers provide corresponding service scope based on this.
It improves the trust and security of rental management, reduces anonymity, increases the sense of presence, prevents the entry of people with bad tendencies, and provides early warnings for management, which is especially suitable for short-term rental housing management.
Smart Images

Figure CN112749657B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information processing technology, and in particular to a rental management method and system. Background Art
[0002] With the development of social economy, more and more people are flowing from underdeveloped areas to developed areas. Housing prices in developed areas are high, and many migrants choose to rent houses in developed areas to solve temporary accommodation problems. However, the traditional rental model is inconvenient for tenants and rental managers to connect. Tenants need to connect with rental managers face to face. After signing the contract and paying the rent, the rental manager gives the door lock key or IC door card to the tenant, and the tenant uses the door key or IC door card to open the door. The docking process between tenants and rental managers is cumbersome. In addition, the public security management department’s rental house file information is incomplete, incomplete, and inaccurate, and the information changes are delayed, the data is outdated and invalid, and the information on rent cancellation is not updated in time, and there are too many blind spots in rental house management. For example: no registration when checking in, no cancellation when leaving the rent; different living patterns, high difficulty in face-to-face verification, and many problems in monitoring mobile personnel, especially the lack of identification and judgment methods for whether the tenants have bad habits and violent behavior tendencies. Summary of the invention
[0003] Therefore, the present invention provides a rental management method and system, and the technical problem to be solved is to overcome the defect in the prior art that it is not easy to authenticate the reliability of tenants' identity information in rental management, thereby promoting tenants' trust in rental managers and effectively managing rentals.
[0004] In order to achieve the above object, the present invention provides the following technical solutions:
[0005] In a first aspect, an embodiment of the present invention provides a rental management method, comprising the following steps:
[0006] Collect tenants’ images based on online rental platforms;
[0007] Perform key point detection on the image to obtain facial features and non-facial features, and fuse the facial features and non-facial features to obtain the tenant's identity authentication information;
[0008] A reliability evaluation coefficient of the tenant is formed based on the identity authentication information, and the rental manager provides a corresponding service range to the tenant based on the reliability evaluation coefficient.
[0009] In one embodiment, a first feature vector representing identity information and a second feature vector representing expression information are generated based on facial features;
[0010] Generating a third feature vector representing the wearing information and a fourth feature vector representing the behavior information based on the non-facial features;
[0011] Fusing the first feature vector, the second feature vector, the third feature vector and the fourth feature information to obtain an identity feature vector representing identity authentication information;
[0012] Based on the preset mapping relationship between the identity feature vector and the reliability evaluation, the corresponding reliability evaluation coefficient is obtained.
[0013] In one embodiment, face detection and key point recognition are performed on the image through a multi-task convolutional neural network to obtain facial features;
[0014] The identity information and facial expression corresponding to the face are obtained based on the facial features, a preset identity information library and a facial expression library, and the first feature vector and the second feature vector are generated based on the identity information and the facial expression information.
[0015] In one embodiment, after the face is detected, background difference is used to extract the non-facial contour, each area is determined according to each key point on the contour, and a contour polygon approximation algorithm is used to remove redundant vertices of the contour, and the tenant's wearing information is obtained based on the contour information, and the third eigenvector is obtained based on the wearing information.
[0016] In one embodiment, based on the data of each key point on the contour, the geometric relationship and geometric changes between key points of the same type are calculated, the behavior information is extracted, and the fourth eigenvector is obtained based on the behavior information.
[0017] In one embodiment, the wearing information includes: hairstyle, earrings, sunglasses, masks, hats, scarves, and ties.
[0018] In one embodiment, the rental manager provides a corresponding service range to the tenant based on the reliability evaluation coefficient, including: setting the reliability evaluation coefficient to multiple levels, and the rental manager implements corresponding management measures for different levels.
[0019] In a second aspect, an embodiment of the present invention provides a rental management system, including:
[0020] A tenant image acquisition module is used to collect tenant images based on the online rental platform;
[0021] The identity authentication information acquisition module is used to detect key points of the image, obtain facial features and non-facial features, and fuse the facial features and non-facial features to obtain the tenant's identity authentication information;
[0022] The service scope determination module is used to form a reliability evaluation coefficient of the tenant based on the identity authentication information, and the rental manager provides the tenant with a corresponding service scope based on the reliability evaluation coefficient.
[0023] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the rental management method of the first aspect of the embodiment of the present invention.
[0024] In a fourth aspect, an embodiment of the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the rental management method of the first aspect of the embodiment of the present invention by executing the computer instructions.
[0025] The technical solution of the present invention has the following advantages:
[0026] The present invention provides a rental management method and system, which detects key points of tenant images on an online rental platform, obtains facial and non-facial features and performs feature fusion to obtain tenant identity authentication information; forms a tenant reliability evaluation coefficient based on the information, and the rental manager provides a corresponding service range to the tenant based on the reliability evaluation coefficient. The present invention recognizes the tenant's photo, extracts facial and non-facial reference information, increases the visual perception trust reflected by the rental manager in the process of tenant photo recognition, helps to reduce the anonymity of the website and increase the sense of presence, and promotes trust between tenants and landlords. The tenant's various features can also reflect the precursor of his bad tendencies. Based on the identity authentication information fused with multiple features, the tenant's reliability evaluation coefficient is formed to provide the tenant with a corresponding service range, which is conducive to the effective management of rental housing, especially the management of short-term rental housing with frequent tenant changes. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0028] Figure 1 A flowchart of an example of a rental housing management method provided in an embodiment of the present invention;
[0029] Figure 2 A module composition diagram of a specific example of a rental house management system provided in an embodiment of the present invention;
[0030] Figure 3 A composition diagram of a specific example of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0031] The technical solution of the present invention will be described clearly and completely below 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 creative work are within the scope of protection of the present invention.
[0032] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0033] Example 1
[0034] The embodiment of the present invention provides a rental management method, such as Figure 1 As shown, the method comprises the following steps:
[0035] Step S1: Collect images of tenants based on the online rental platform.
[0036] Step S2: Detect key points of the image, obtain facial features and non-facial features, fuse the facial features and non-facial features, and obtain the tenant's identity authentication information.
[0037] Step S3: A reliability evaluation coefficient of the tenant is formed based on the identity authentication information, and the rental manager provides a corresponding service scope to the tenant based on the reliability evaluation coefficient.
[0038] The rental management method provided by the embodiment of the present invention collects the image of the tenant before the tenant wants to enter the house each time or within a preset time period through the online rental platform, and extracts the facial and reference information other than facial features based on the photo recognition of the tenant in the online rental platform, thereby increasing the visual perception trust and attractiveness reflected by the rental manager (including landlords, properties, trustees or other rental management personnel, and the landlord is taken as an example below) in the process of identifying the tenant's photo, and discovering the tenant's bad tendencies as early as possible, which helps to reduce the anonymity of the website and increase the sense of presence, and promote the tenant's trust in the landlord. The various characteristics of the tenant can also reflect the precursor of the tenant's bad behavior, and based on this, the tenant's reliability evaluation coefficient is formed, and the corresponding service scope is provided to the tenant using the reliability evaluation coefficient, which is conducive to the effective management of rental housing, especially the management of short-term rental housing with frequent tenant changes.
[0039] In an embodiment of the present invention, a first feature vector representing identity information and a second feature vector representing expression information are generated based on facial features; a third feature vector representing wear information and a fourth feature vector representing behavior information are generated based on non-facial features; the first feature vector, the second feature vector, the third feature vector and the fourth feature information are fused to obtain an identity feature vector representing identity authentication information; based on a preset mapping relationship between the identity feature vector and the reliability evaluation, a corresponding reliability evaluation coefficient is obtained.
[0040] In a specific embodiment, a multi-task convolutional neural network (MTCNN algorithm) is used to perform face detection and key point recognition on an image to obtain facial features; based on the facial features, a preset identity information library and a facial expression library, identity information and facial expressions corresponding to the face are obtained, and a first feature vector and a second feature vector are generated based on the identity information and facial expression information. In actual applications, key point information of the facial features of the image is extracted, and after obtaining facial features related to face recognition, the facial features are matched with the face data set in the ID card database to identify and obtain the identity information; after obtaining the facial features related to the facial expression, the facial expression library is input for matching to obtain the corresponding expression.
[0041] In a specific embodiment, after detecting the face, background difference is used to extract the non-face contour, each area is determined according to each key point on the contour, and the contour polygon approximation algorithm is used to remove the redundant vertices of the contour, and the wear information of the tenant is obtained based on the contour information, and the third feature vector is obtained based on the wear information. The wear information includes: hairstyle, earrings, whether to wear sunglasses, masks, and ties.
[0042] In the embodiment of the present invention, the contour polygon approximation algorithm is mainly used to process the contour. The background difference is to extract a clear human body contour from the background image. According to the relationship between the camera and the moving target, the background difference method based on the static background is used to extract the contour. In order to overcome the influence of sudden changes in illumination, each frame of the video image is subjected to image preprocessing by median filtering and histogram normalization. The processing results are averaged to obtain the initial background image of the algorithm. The pixel values of the corresponding pixels of the background image and the current image are differentially calculated. The differential image is binarized and morphologically processed to highlight the target area, thereby obtaining a relatively complete target contour. Take the extraction of the contour of a tie as an example:
[0043] The outline of a tie is approximately a straight line. Each outline contains points sufficient to describe the characteristics of this curve. According to the contour feature points of the tie and body parts, a tie contour polygon approximation algorithm is proposed to locate the tie. The approximate area of the tie is below the neck and the arm is connected to the torso. The contour curve C of the tie is shown by the following formula:
[0044] C={Pc=(xc,yc)|c=1,2,…,q}
[0045] Among them, q is the total number of points of the contour, Pc is the coordinate of each point, and the lines composed of the points of the contour are thinned. After the processing is completed, the broken lines formed by each segmentation point are connected in sequence to obtain the thinned tie contour curve. The tie has a certain tilt angle ranging from 70° to 90°. The tie is close to the head, and the approximate straight line that meets these two conditions is fine-tuned, and the midpoint of the straight line is the tie position.
[0046] In a specific embodiment, based on the data of each key point on the contour, the geometric relationship and geometric changes between similar key points are calculated, the behavior information is extracted, and the fourth eigenvector is obtained based on the behavior information. In practical applications, the behavior information of the tenant can be obtained to judge his psychological state, for example, by obtaining the twitching frequency of the nose, the flickering action of the eyes, the scratching of the back of the head and other actions to judge whether the person is lying.
[0047] The embodiment of the present invention obtains local features at different scales by performing multi-scale sampling around a single key point of non-facial feature points, thereby increasing the dimension of the features, especially for non-facial local features. The different scales enable the extracted features to contain both details and relatively overall structural information, so that the details of the tenant's identity authentication information can be more comprehensively obtained, and a reliability evaluation coefficient can be formed based on this. For example, when taking photos, people who often wear sunglasses, masks, and have strange hairstyles are unwilling to show too much facial information. Combinations such as strange hairstyles, unnatural facial expressions, and behavioral information representing abnormal psychological states will be considered to have a low reliability evaluation coefficient. In practical applications, the identity authentication information can be established The various combinations of features are mapped with reliability evaluation, so that the corresponding reliability evaluation coefficient is obtained by extracting and fusing the features of the acquired image, and the reliability evaluation coefficient is divided into multiple threshold ranges and corresponding services are provided. For example, different thresholds are set for the reliability evaluation coefficient, and the reliability evaluation coefficient is divided into low, medium and high levels. If it is high, it indicates the highest reliability, allowing the tenant to safely pass through the detection point and enter the rental house; if it is medium, it is necessary to adjust the image content in the photo to display more identity information, or set restrictions on the tenant to enter the rental house; if the reliability evaluation coefficient is displayed as low, the rental manager is reminded to contact the tenant in real time or to conduct face-to-face identity verification of the person taking the photo.
[0048] The rental management method provided by the present invention can effectively improve the recognition of the credibility of identity authentication by identifying the reliability of tenants, thereby improving the security of rental activities, preventing the entry of people with unsafe tendencies and providing relevant warnings for management personnel.
[0049] Example 2
[0050] The embodiment of the present invention provides a rental management system, such as Figure 2 As shown, including:
[0051] The tenant image acquisition module 1 is used to collect tenant images based on the online rental platform; this module executes the method described in step S1 of embodiment 1, which will not be repeated here.
[0052] The identity authentication information acquisition module 2 is used to detect key points of the image, obtain facial features and non-facial features, and fuse the facial features and non-facial features to obtain the tenant's identity authentication information. This module executes the method described in step S2 of embodiment 1, which will not be repeated here.
[0053] The service scope determination module 3 is used to form a reliability evaluation coefficient of the tenant based on the identity authentication information, and the rental manager provides the tenant with a corresponding service scope based on the reliability evaluation coefficient. This module executes the method described in step S3 of embodiment 1, which will not be repeated here.
[0054] The rental management system provided by the embodiment of the present invention is based on the recognition of tenants' photos in the online rental platform, discovers reference information of the face and other than facial features, increases the visual perception trust reflected by the rental manager in the process of tenant photo recognition, and discovers the tenant's bad tendencies as early as possible, which helps to reduce the anonymity of the website and increase the sense of presence, and promotes the tenant's trust in the landlord. The various characteristics of the tenant can also reflect the precursors of the tenant's bad behavior and form the tenant's reliability evaluation coefficient based on this, and use the reliability evaluation coefficient to provide the tenant with a corresponding service range, which is conducive to the effective management of rental houses, especially the management of short-term rental houses with frequent tenant changes.
[0055] Example 3
[0056] An embodiment of the present invention provides a computer device, such as Figure 3 As shown, the device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected via a bus or other means. Figure 3 Take the example of connecting via a bus.
[0057] The memory 52 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as the corresponding program instructions / modules in the embodiments of the present invention. The processor 51 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 52, that is, the rental management method in the above method embodiment 1 is implemented.
[0058] The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created by the processor 51, etc. In addition, the memory 52 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 52 may optionally include a memory remotely arranged relative to the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, an intranet, a mobile communication network, and combinations thereof.
[0059] One or more modules are stored in the memory 52, and when executed by the processor 51, the rental management method in Example 1 is executed.
[0060] The specific details of the above-mentioned computer device can be understood by referring to the corresponding related descriptions and effects in Example 1, and will not be repeated here.
[0061] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.
[0062] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the scope of protection of the invention.
Claims
1. A rental management method, characterized in that: The steps include: Collect tenants’ images based on online rental platforms; Detect key points of the image to obtain facial features and non-facial features; The facial features and non-facial features are integrated to obtain the tenant's identity authentication information, including: generating a first feature vector representing identity information and a second feature vector representing expression information based on the facial features; generating a third feature vector representing wear information and a fourth feature vector representing behavior information based on the non-facial features; fusing the first feature vector, the second feature vector, the third feature vector and the fourth feature information to obtain an identity feature vector representing identity authentication information; The reliability evaluation coefficient of the tenant is formed based on the identity authentication information, including: obtaining the corresponding reliability evaluation coefficient based on a preset identity feature vector and reliability evaluation mapping relationship; and the rental manager provides the tenant with a corresponding service scope based on the reliability evaluation coefficient.
2. The rental management method according to claim 1, characterized in that: Use multi-task convolutional neural network to detect faces and identify key points in images to obtain facial features; The identity information and facial expression corresponding to the face are obtained based on the facial features, a preset identity information library and a facial expression library, and the first feature vector and the second feature vector are generated based on the identity information and the facial expression information.
3. The rental management method according to claim 1, characterized in that: After detecting the face, background difference is used to extract the non-facial contour, and each area is determined according to the key points on the contour. The contour polygon approximation algorithm is used to remove redundant vertices of the contour. The tenant's wearing information is obtained based on the contour information, and the third eigenvector is obtained based on the wearing information.
4. The rental management method according to claim 3, characterized in that: Based on the data of each key point on the contour, the geometric relationship and geometric changes between key points of the same type are calculated, the behavior information is extracted, and the fourth eigenvector is obtained based on the behavior information.
5. The rental management method according to claim 3, characterized in that: The wearing information includes: hairstyle, earrings, sunglasses, masks, hats, scarves, and ties.
6. The rental management method according to claim 1, characterized in that: The rental manager provides a corresponding range of services to the tenant based on the reliability evaluation coefficient, including: setting the reliability evaluation coefficient to multiple levels, and the rental manager implements corresponding management measures for different levels.
7. A rental house management system, characterized in that: include: A tenant image acquisition module is used to collect tenant images based on the online rental platform; The identity authentication information acquisition module is used to detect key points of the image and obtain facial features and non-facial features; The facial features and non-facial features are integrated to obtain the tenant's identity authentication information, including: generating a first feature vector representing identity information and a second feature vector representing expression information based on the facial features; generating a third feature vector representing wear information and a fourth feature vector representing behavior information based on the non-facial features; fusing the first feature vector, the second feature vector, the third feature vector and the fourth feature information to obtain an identity feature vector representing identity authentication information; The service scope determination module is used to form a reliability evaluation coefficient of the tenant based on the identity authentication information, including: obtaining a corresponding reliability evaluation coefficient based on a preset identity feature vector and reliability evaluation mapping relationship; and the rental manager provides the tenant with a corresponding service scope based on the reliability evaluation coefficient.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the rental management method according to any one of claims 1 to 6.
9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the rental management method as described in any one of claims 1 to 6 by executing the computer instructions.
