WO2022134584A1

WO2022134584A1 - Real estate picture verification method and apparatus, computer device and storage medium

Info

Publication number: WO2022134584A1
Application number: PCT/CN2021/109507
Authority: WO
Inventors: 宋文琳
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-12-22
Filing date: 2021-07-30
Publication date: 2022-06-30
Also published as: CN112650875A

Abstract

Provided are a real estate picture verification method and apparatus, a computer device, and a storage medium. The method comprises: receiving a real estate picture verification request, wherein the real estate picture verification request comprises a real estate picture to be verified and real estate information to be verified, said real estate picture comprises a digital watermark, and the digital watermark comprises position information of said real estate picture when being photographed (S201); retrieving a preset database according to said real estate information to obtain the actual position of a real estate to be verified; extracting the position information in the digital watermark (S203); comparing whether the position information is consistent with the actual position or not (S204); and if the position information is consistent with the actual position, determining that the real estate picture passes verification (S205). The auditing efficiency of the real estate picture is improved, and the fraud loss caused by photo counterfeiting is reduced.

Description

Real estate picture verification method, device, computer equipment and storage medium

This application is required to be submitted to the China Patent Office on December 22, 2020, the application number is 202011528048.1, the invention The priority of the Chinese patent application titled "Method, Apparatus, Computer Equipment and Storage Medium for Real Estate Picture Verification", The entire contents of which are incorporated herein by reference.

technical field

The present application relates to the field of artificial intelligence technology, and in particular, to a method, device, computer equipment and storage medium for real estate picture verification.

Background technique

In the loan business - real estate mortgage loan scenario, business personnel need to go to the scene to take real estate information, such as interior pictures, elevator pictures, and residential environment pictures, to verify the authenticity of the real estate and conduct real estate valuation. The inventor realizes that in the case of a large order quantity, more labor costs will be incurred.

With the development of Internet technology, users can upload real estate pictures for real estate evaluation, which is convenient for users, allowing users to apply for loan business by themselves without the presence of salespersons according to their needs, and saves the labor cost of salespersons. But at the same time, there may be cases where users fake real estate pictures.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a real estate picture verification method, device, computer equipment and storage medium, so as to solve the problem of real estate picture authenticity verification.

In order to solve the above-mentioned technical problems, the embodiment of the present application provides a real estate picture verification method, which adopts the following technical solutions:

Receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the real estate to be verified Location information when the picture was taken;

Retrieves a preset database according to the real estate information to be verified, and obtains the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

extracting the location information in the digital watermark;

comparing whether the location information is consistent with the actual location;

When the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification.

In order to solve the above technical problems, the embodiment of the present application also provides a real estate picture verification device, which adopts the following technical solutions:

The receiving module is used to receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains all the real estate images to be verified. Describe the location information of the property to be verified when the picture was taken;

a retrieval module, used for retrieving a preset database according to the real estate information to be verified, to obtain the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

an extraction module for extracting the location information in the digital watermark;

a comparison module for comparing whether the position information is consistent with the actual position;

A determination module, configured to determine that the real estate picture has passed the verification when the location information is consistent with the actual location.

In order to solve the above-mentioned technical problems, the embodiment of the present application also provides a computer device, which adopts the following technical solutions:

A computer device includes a memory and a processor, wherein computer-readable instructions are stored in the memory, and the processor implements the following steps when executing the computer-readable instructions:

extracting the location information in the digital watermark;

In order to solve the above technical problems, the embodiments of the present application also provide a computer-readable storage medium, which adopts the following technical solutions:

A computer device includes a memory and a processor, the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the processor further performs the following steps:

extracting the location information in the digital watermark;

Compared with the prior art, the embodiment of the present application mainly has the following beneficial effects: by receiving a real estate image verification request, the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image verification request to be verified The real estate picture contains a digital watermark, and the digital watermark includes the location information when the real estate picture to be verified is taken; according to the real estate information to be verified, a preset database is retrieved, and the actual location of the real estate to be verified is obtained, The preset database at least pre-stores the actual location of the property; extracts the location information in the digital watermark; compares whether the location information is consistent with the actual location; when the location information is consistent with the actual location, determine The property pictures are verified. Improve the efficiency of real estate image review. By comparing latitude and longitude, altitude and re-taking identification, reduce fraud losses caused by fake photos.

Description of drawings

In order to illustrate the solutions in the present application more clearly, the following will briefly introduce the accompanying drawings used in the description of the embodiments of the present application. For those of ordinary skill, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;

2 is a flow chart of an embodiment of a real estate picture verification method according to the present application;

Fig. 3 is a flow chart of a specific embodiment of obtaining a picture of the real estate to be verified in Fig. 2;

4 is a schematic structural diagram of an embodiment of a real estate picture verification device according to the present application;

FIG. 5 is a schematic structural diagram of an embodiment of a computer device according to the present application.

Detailed ways

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field of this application; the terms used herein in the specification of the application are for the purpose of describing specific embodiments only It is not intended to limit the application; the terms "comprising" and "having" and any variations thereof in the description and claims of this application and the above description of the drawings are intended to cover non-exclusive inclusion. The terms "first", "second" and the like in the description and claims of the present application or the above drawings are used to distinguish different objects, rather than to describe a specific order.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings.

As shown in FIG. 1 , the system architecture 100 may include

terminal devices

101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the

terminal devices

101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the

terminal devices

101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. Various communication client applications may be installed on the

terminal devices

101 , 102 and 103 , such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, and the like.

The

terminal devices

101, 102, and 103 can be various electronic devices that have a display screen and support web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic Picture Experts Compression Standard Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) Players, Laptops and Desktops, etc.

The server 105 may be a server that provides various services, such as a background server that provides support for the pages displayed on the

terminal devices

101 , 102 , and 103 .

It should be noted that the real estate image verification method provided by the embodiments of the present application is generally performed by a server/terminal device , and accordingly, the real estate image verification apparatus is generally set in the server/terminal device .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

Continuing to refer to FIG. 2 , a flowchart of one embodiment of a method for real estate picture verification according to the present application is shown. The described real estate image verification method includes the following steps:

Step S201: Receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the real estate image to be verified. Verified location information at the time the property image was taken.

In this embodiment, the electronic device (such as the server/ terminal device shown in FIG. 1 ) on which the real estate picture verification method operates can receive the real estate picture verification request through a wired connection or a wireless connection, and the real estate picture verification The request contains the image of the property to be verified and the property information to be verified. It should be pointed out that the above wireless connection methods may include but are not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future .

The user inputs the information of the property to be verified and the picture of the property to be verified on the interactive interface, and the information of the property to be verified can be one of the property number, the name of the property owner, and the ID.

The real estate picture to be verified can be a picture saved on a storage medium in advance, or a picture taken in real time by a device with a camera. The user imports the pre-saved pictures through the interactive interface, or obtains the pictures of the real estate to be verified in real time by invoking the computer-readable instructions for shooting.

Step S202: Retrieve a preset database according to the real estate information to be verified to obtain the actual position of the real estate to be verified, and the preset database at least pre-stores the actual position of the real estate.

In this embodiment, the preset database pre-stores the actual location of the real estate, and the preset database is retrieved through the information of the real estate to be verified. one of them. The actual location of the pre-stored property contains at least the location or latitude, longitude and altitude of the property on the preset map.

Step S203, extracting the location information in the digital watermark.

The process of extracting digital watermark is the reverse process of adding digital watermark. For example, the position information is stored by using the last bit of the RGB value of each pixel of the image. The process of extracting a digital watermark is the inverse of the above process: extract the pixel value, select the last bit, and spell out the information. Similarly, using the digital watermark added by other algorithms, the digital watermark is extracted through the reverse process of adding, and the location information of the real estate picture to be verified when the picture is taken is obtained.

Step S204, comparing whether the location information is consistent with the actual location;

Compare the actual location with the location information in the digital watermark by character string.

Step S205, when the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification.

Compare the actual location and the location information in the digital watermark, and when the two are consistent, it is determined that the real estate image to be verified has passed the verification. When the location information in the digital watermark includes latitude and longitude and altitude, the latitude and longitude are compared first, and then the altitude is compared. Through the comparison of latitude and longitude and altitude, it can be accurate to the specific floor and specific room of a specific building, which improves the accuracy of real estate picture verification.

By receiving a real estate image verification request, the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the to-be-verified real estate image. The location information when the real estate picture was taken; retrieve the preset database according to the real estate information to be verified to obtain the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate; extract the digital The location information in the watermark; compare whether the location information is consistent with the actual location; when the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification. Improve the efficiency of real estate image review. By comparing latitude and longitude, altitude and re-taking identification, reduce fraud losses caused by fake photos.

In some optional implementations of this embodiment, before step S201, the above electronic device may further perform the following steps:

Get real-time shooting requests;

According to the real-time shooting request, call the preset picture shooting module and the preset positioning module to obtain the real-time shooting picture and the location information of the real-time shooting;

Converting the location information into a digital watermark and adding it to the picture; obtaining a picture of the real estate to be verified to which the digital watermark has been added.

When the user wants to use the real-time shooting picture for verification, he can send a real-time shooting request by clicking the real-time shooting option on the interactive interface, receive the real-time shooting request, call the preset picture shooting module and the preset positioning module, the The shooting module and the positioning module are embedded in the same electronic device. At present, electronic devices with cameras are embedded with a picture shooting module. The picture shooting module takes pictures by turning on the camera, and the positioning module simultaneously locates the position information at the time of shooting. The positioning module is based on GPS system, the location information includes latitude, longitude and altitude, and can also be a location mapped to a preset map.

The photographed picture and the location information of the positioning are input into the preset digital watermark addition, the location information is added to the photographed picture, and the digital watermarked real estate picture to be verified is obtained.

A digital watermark is to embed a specific digital signal into a digital product. The addition of a digital watermark can be based on the following principles: each pixel in an image is usually represented by three RGB values from 0 to 255, and converted to binary, it is 00000000 to 11111111. Set the last digit of each value to all zeros, this change is invisible to the human eye. The last bit freed up in this way can be used to store information. The process of extracting information is the inverse of the above process: extract the pixel value, select the last bit, and spell out the information.

Digital watermarking can also be based on spatial domain dark watermarking algorithm, such as Patchwork algorithm, arbitrarily select N pairs of image points, increase the brightness of one point, and correspondingly reduce the brightness value of another point; through this adjustment process, the embedding of the watermark is completed. The algorithm is imperceptible and resistant to lossy compression encoding (JPEG) and some malicious attack processing.

Digital watermarking can also be based on transform-domain dark watermarking algorithms, such as the block-based DCT-based digital watermarking technology scheme. Some blocks of the image are randomly selected by a key, and a triplet is slightly changed at the intermediate frequency of the frequency domain to hide the binary. sequence information. The encoding in the intermediate frequency component is chosen because the encoding in the high frequency is easy to be corrupted by various signal processing methods, while the encoding in the low frequency is easy to detect the change of the low frequency component because the human vision is very sensitive to the low frequency component. The digital watermarking algorithm is robust to lossy compression and low-pass filtering.

Digital watermarks are not intuitively visible to human vision. By adding a digital watermark of location information to the real estate image to be verified to verify whether the location information is consistent with the actual location, the authenticity of the real estate image can be effectively verified.

In some optional implementations, before step S204, the above electronic device may perform the following steps:

Obtain the property owner information to be verified;

Retrieve a preset database according to the real estate information to be verified, and obtain the actual holder information corresponding to the real estate information;

comparing said property owner information to be verified with said actual owner information;

When the location information is consistent with the actual location, the step of determining that the real estate picture has passed the verification includes:

When the property owner information to be verified is consistent with the actual owner information, and the location information is consistent with the actual location, it is determined that the property image to be verified passes the verification.

The real estate information to be verified can be the real estate code, the house number, and the preset database is retrieved through the real estate information. The preset database can be the real estate management database preset by the real estate management agency, which at least includes the actual location of the real estate and the actual owner. Information, the actual location at least includes the latitude, longitude and altitude of the property, and the actual holder information at least includes the holder's name and ID.

After the location information extracted from the digital watermark is compared with the actual location, the property holder information to be verified and the actual holder information are compared, when the property holder information to be verified and the actual holder information are compared. When the location information is consistent with the actual location, it is determined that the real estate picture to be verified has passed the verification.

It is also possible to compare the information of the property holder to be verified with the information of the actual holder, and when the two are inconsistent, end the verification process to prevent users from using properties that do not belong to them for verification.

In some optional implementation manners, when the actual holder information includes the facial features of the actual holder, in the step of comparing the property holder information to be verified and the actual holder information, Also includes:

Perform feature extraction on the face image of the property holder to be verified to obtain the face feature to be verified;

Calculate the similarity between the face feature to be verified and the face feature of the actual holder;

When the similarity is greater than a set threshold, it is determined that the property owner information to be verified is consistent with the actual owner information.

When the actual holder information in the database contains the facial features of the actual holder, receive the facial image of the property holder to be verified, perform feature extraction on the facial image, compare the similarity between the two, and set a threshold , when the similarity is greater than the set threshold, it is considered that the real estate holder to be verified is the actual holder, and the real estate image verification is continued, otherwise the verification is ended. Identity verification can be performed more effectively through face recognition, preventing users from using real estate that does not actually belong to them for verification.

In some optional implementations, before step S202, the method further includes:

Inputting the real estate picture to be verified into a pre-trained neural network model, and obtaining a classification result output by the pre-trained neural network model in response to the real estate picture, and the classification result is a remake picture or a non-remake picture;

When the classification result is a retaken picture, it is determined that the verification of the real estate picture to be verified fails.

In order to avoid the situation that the real estate picture provided by the user may be a remake, when verifying, first determine whether it is a remake, and if it is a remake, end the image verification. For the human eye, it is difficult to distinguish reposted pictures, and the pre-trained neural network model is used to judge.

The training steps for a pre-trained neural network model include:

Prepare training samples, the samples are real estate pictures marked with picture categories;

Input the training sample into the neural network model, and obtain the predicted category of the training sample;

Compare whether the prediction categories of different samples in the training sample are consistent with the picture categories through a loss function, where the loss function is:

Among them, N is the number of training samples, the corresponding mark for the i-th sample is Yi is the marked result, h=(h1,h2,...,hc) is the prediction result of sample i, where C is all classified quantity;

When the predicted category is inconsistent with the labeled category, the weight of each node in the neural network model is updated repeatedly and iteratively, until the loss function reaches a minimum value.

The categories of the marked pictures are remake pictures and non-remake pictures. It is difficult for the human eye to identify whether they are remake pictures, but the texture features of the remake pictures and non-remake pictures are different. The neural network model is used to learn the texture features of different categories of pictures, and the real estate pictures are processed. Classify and identify the remade real estate pictures, which can prevent users from using the remade real estate pictures for image verification.

In some optional implementations, the above electronic device may perform the following steps:

Store the received real estate image verification request in the blockchain

It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned real estate image verification request information, the above-mentioned real estate image verification request information may also be stored in a node of a blockchain.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

The present application may be used in numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, including A distributed computing environment for any of the above systems or devices, and the like. This application may be described in the general context of computer-executable instructions, such as computer-readable instruction modules, being executed by a computer. Generally, modules of computer-readable instructions include routines, computer-readable instructions, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, modules of computer readable instructions may be located in both local and remote computer storage media including storage devices.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. , the computer-readable instructions, when executed, may include the processes of the above-mentioned method embodiments. Wherein, the aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only storage memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM) or the like.

It should be understood that although the various steps in the flowchart of the accompanying drawings are sequentially shown in the order indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order and may be performed in other orders. Moreover, at least a part of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution sequence is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of sub-steps or stages of other steps.

Further referring to FIG. 4 , as an implementation of the method shown in FIG. 2 above, the present application provides an embodiment of a real estate picture verification device, and the device embodiment corresponds to the method embodiment shown in FIG. 2 . Can be used in various electronic devices.

As shown in FIG. 4 , the real estate picture verification device 400 in this embodiment includes: a receiving module 401 , a retrieval module 402 , an extraction module 403 , a comparison module 404 and a determination module 405 . in:

The receiving module 401 is configured to receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark includes The location information when the picture of the property to be verified is taken;

The retrieval module 402 is used for retrieving a preset database according to the real estate information to be verified, to obtain the actual position of the real estate to be verified, and the preset database at least pre-stores the actual position of the real estate;

Extraction module 403, for extracting the location information in the digital watermark;

a comparison module 404, configured to compare whether the location information is consistent with the actual location;

The determining module 405 is configured to determine that the real estate picture has passed the verification when the location information is consistent with the actual location.

In this embodiment, by receiving a real estate image verification request, the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark Contains the location information of the real estate to be verified when the picture is taken; searches a preset database according to the real estate information to be verified, and obtains the actual location of the real estate to be verified, and the preset database at least pre-stores the actual position of the real estate position; extract the position information in the digital watermark; compare whether the position information is consistent with the actual position; when the position information is consistent with the actual position, it is determined that the real estate picture has passed the verification. Improve the efficiency of real estate image review. By comparing latitude and longitude, altitude and re-taking identification, reduce fraud losses caused by fake photos.

In some optional implementations of this embodiment, the receiving module 401 includes:

a first obtaining submodule, used for obtaining a real-time shooting request;

The first processing sub-module is configured to call the preset picture shooting module and the preset positioning module according to the real-time shooting request, and obtain the real-time shooting picture and the location information of the real-time shooting location;

The first adding submodule is used to convert the location information into a digital watermark and add it to the picture; obtain the real estate picture to be verified with the digital watermark added.

When the actual locations are consistent, it is determined that the real estate picture has passed the verification.

In some optional implementations of this embodiment, the real estate picture verification device further includes:

The first receiving sub-module is used to obtain the property holder information to be verified;

a first retrieval submodule, used for retrieving a preset database according to the real estate information to be verified, and obtaining the actual holder information corresponding to the real estate information;

a first comparison sub-module for comparing the property owner information to be verified with the actual owner information;

The first judging submodule is used to determine the picture of the property to be verified when the information of the property owner to be verified is consistent with the actual owner information, and the location information is consistent with the actual location approved.

In some optional implementations of this embodiment, when the property owner information to be verified received by the first receiving submodule is a face image, the first comparing submodule includes:

The first extraction subunit is used for feature extraction of the face image of the property owner to be verified to obtain the face feature to be verified;

a first comparison subunit, used to calculate the similarity between the face feature to be verified and the face feature of the actual holder;

A first judging subunit, configured to determine that the information of the property owner to be verified is consistent with the information of the actual owner when the similarity is greater than a set threshold.

The first processing submodule is used to input the real estate picture to be verified into a pre-trained neural network model, and obtain a classification result output by the pre-trained neural network model in response to the real estate picture, the classification result be a remake or a non-remake;

The second judging submodule is configured to determine that the verification of the real estate picture to be verified fails when the classification result is a retaken picture.

The second acquisition sub-module is used for acquiring training samples, where the training samples are N real estate pictures marked as remake pictures, and N is a positive integer greater than 0;

a second processing submodule, configured to input the training samples into the neural network model, and obtain N prediction results output by the neural network model in response to the N real estate pictures;

The first comparison sub-module is used to compare whether the N prediction results are consistent with the label through a loss function, wherein the loss function is:

Among them, N is the number of training samples, Yi is the labeling result for the ith sample, h=(h1, h2,...,hc) is the prediction result of sample i, where C is the number of all categories;

The first adjustment sub-module is used to adjust the parameters of each node in the neural network model, and ends when the loss function reaches a minimum value to obtain the pre-trained neural network model.

The storage module is used to store the received real estate picture verification request in the blockchain.

To solve the above technical problems, the embodiments of the present application also provide computer equipment. Please refer to FIG. 5 for details. FIG. 5 is a block diagram of a basic structure of a computer device according to this embodiment.

The computer device 5 includes a memory 51 , a processor 52 , and a network interface 53 that communicate with each other through a system bus. It should be pointed out that only the computer device 5 with components 51-53 is shown in the figure, but it should be understood that it is not required to implement all of the shown components, and more or less components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculation and/or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, special-purpose Integrated circuit (Application Specific Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processor (Digital Signal Processor, DSP), embedded equipment, etc.

The computer equipment may be a desktop computer, a notebook computer, a palmtop computer, a cloud server and other computing equipment. The computer device can perform human-computer interaction with the user through a keyboard, a mouse, a remote control, a touch pad or a voice control device.

The memory 51 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), Magnetic Memory, Magnetic Disk, Optical Disk, etc. The computer-readable storage medium may be non-volatile or volatile. In some embodiments, the memory 51 may be an internal storage unit of the computer device 5 , such as a hard disk or a memory of the computer device 5 . In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), etc. Of course, the memory 51 may also include both the internal storage unit of the computer device 5 and its external storage device. In this embodiment, the memory 51 is generally used to store the operating system and various application software installed on the computer device 5 , such as computer-readable instructions for a real estate image verification method. In addition, the memory 51 can also be used to temporarily store various types of data that have been output or will be output.

In some embodiments, the processor 52 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. This processor 52 is typically used to control the overall operation of the computer device 5 . In this embodiment, the processor 52 is configured to execute computer-readable instructions stored in the memory 51 or process data, for example, computer-readable instructions for executing the method for verifying a real estate picture.

The network interface 53 may include a wireless network interface or a wired network interface, and the network interface 53 is generally used to establish a communication connection between the computer device 5 and other electronic devices.

The present application also provides another embodiment, that is, to provide a computer-readable storage medium, where the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to The at least one processor is caused to perform the steps of the above-mentioned real estate picture verification method.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or in a part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of this application.

Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The accompanying drawings show the preferred embodiments of the present application, but do not limit the scope of the patent of the present application. This application may be embodied in many different forms, rather these embodiments are provided so that a thorough and complete understanding of the disclosure of this application is provided. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. . Any equivalent structure made by using the contents of the description and drawings of the present application, which is directly or indirectly used in other related technical fields, is also within the scope of protection of the patent of the present application.

Claims

A real estate image verification method, comprising the following steps:

Receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the real estate to be verified Location information when the picture was taken;

Retrieves a preset database according to the real estate information to be verified, and obtains the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

extracting the location information in the digital watermark;

comparing whether the location information is consistent with the actual location;

When the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification.
The real estate image verification method according to claim 1, wherein, in the receiving real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the real estate image verification request to be verified The real estate picture contains a digital watermark, and the digital watermark includes the location information of the real estate picture to be verified before the steps, including:

Get real-time shooting requests;

According to the real-time shooting request, call the preset picture shooting module and the preset positioning module to obtain the real-time shooting picture and the location information of the real-time shooting;

The location information is converted into a digital watermark and added to the picture to obtain a picture of the real estate to be verified to which the digital watermark has been added.
The real estate picture verification method according to claim 1, wherein the preset database contains real estate owner information, and when the position information is consistent with the actual position, it is determined that the real estate picture passes the verification The steps also include:

Obtain the property owner information to be verified;

Retrieve a preset database according to the real estate information to be verified, and obtain the actual holder information corresponding to the real estate information;

comparing said property owner information to be verified with said actual owner information;

When the location information is consistent with the actual location, the step of determining that the real estate picture has passed the verification includes:

When the property owner information to be verified is consistent with the actual owner information, and the location information is consistent with the actual location, it is determined that the property image to be verified passes the verification.
The real estate picture verification method according to claim 3, wherein the actual holder information includes the facial features of the actual holder, and the comparison between the real estate holder information to be verified and the actual holder Steps to personal information, including:

Perform feature extraction on the face image of the property holder to be verified to obtain the face feature to be verified;

Calculate the similarity between the face feature to be verified and the face feature of the actual holder;

When the similarity is greater than a set threshold, it is determined that the property owner information to be verified is consistent with the actual owner information.
The real estate image verification method according to claim 1, wherein, in the receiving real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the real estate image verification request to be verified The real estate picture includes a digital watermark, and the digital watermark includes the location information of the real estate picture to be verified after the step of taking the photo, and further includes:

Inputting the real estate picture to be verified into a pre-trained neural network model, and obtaining a classification result output by the pre-trained neural network model in response to the real estate picture, and the classification result is a remake picture or a non-remake picture;

When the classification result is a retaken picture, it is determined that the verification of the real estate picture to be verified fails.
The real estate picture verification method according to claim 5, wherein the training of the neural network model comprises:

Acquiring training samples, where the training samples are N real estate pictures marked as remade pictures, and N is a positive integer greater than 0;

Inputting the training sample into the neural network model to obtain N prediction results output by the neural network model in response to the N real estate pictures;

Compare the N prediction results and the annotations through a loss function, where the loss function is:

Among them, N is the number of training samples, Yi is the labeling result for the ith sample, h=(h1, h2,...,hc) is the prediction result of sample i, where C is the number of all categories;

The parameters of each node in the neural network model are adjusted until the loss function reaches a minimum value, and the pre-trained neural network model is obtained.
The real estate picture verification method according to claim 1, wherein, further comprising:

The received real estate picture verification request is stored in the blockchain.
A real estate picture verification device, comprising:

The receiving module is used to receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains all the real estate images to be verified. Describe the location information of the property to be verified when the picture was taken;

a retrieval module, used for retrieving a preset database according to the real estate information to be verified, to obtain the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

an extraction module for extracting the location information in the digital watermark;

a comparison module for comparing whether the position information is consistent with the actual position;

A determination module, configured to determine that the real estate picture has passed the verification when the location information is consistent with the actual location.
A computer device, comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and the processor implements the following steps when executing the computer-readable instructions:

Receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the real estate to be verified Location information when the picture was taken;

Retrieves a preset database according to the real estate information to be verified, and obtains the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

extracting the location information in the digital watermark;

comparing whether the location information is consistent with the actual location;

When the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification.
The computer device according to claim 9, wherein in the receiving a real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the real estate image to be verified Before the step of containing the digital watermark, the digital watermark includes the location information of the real estate picture to be verified when the picture is taken, including:

Get real-time shooting requests;

According to the real-time shooting request, call the preset picture shooting module and the preset positioning module to obtain the real-time shooting picture and the location information of the real-time shooting;

The location information is converted into a digital watermark and added to the picture to obtain a picture of the real estate to be verified to which the digital watermark has been added.
The computer device according to claim 9, wherein the preset database contains real estate owner information, and when the position information is consistent with the actual position, the step of determining that the real estate picture passes the verification Also included before:

Obtain the property owner information to be verified;

Retrieve a preset database according to the real estate information to be verified, and obtain the actual holder information corresponding to the real estate information;

comparing said property owner information to be verified with said actual owner information;

When the location information is consistent with the actual location, the step of determining that the real estate picture has passed the verification includes:

When the property owner information to be verified is consistent with the actual owner information, and the location information is consistent with the actual location, it is determined that the property image to be verified passes the verification.
11. The computer device of claim 11, wherein the actual owner information includes facial features of the actual owner, and the comparing the property owner information to be verified with the actual owner information steps, including:

Perform feature extraction on the face image of the property holder to be verified to obtain the face feature to be verified;

Calculate the similarity between the face feature to be verified and the face feature of the actual holder;

When the similarity is greater than a set threshold, it is determined that the property owner information to be verified is consistent with the actual owner information.
The computer device according to claim 9, wherein in the receiving a real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the real estate image to be verified After the step of containing a digital watermark, the digital watermark includes the location information of the real estate picture to be verified when the picture is taken:

Inputting the real estate picture to be verified into a pre-trained neural network model, and obtaining a classification result output by the pre-trained neural network model in response to the real estate picture, and the classification result is a remake picture or a non-remake picture;

When the classification result is a retaken picture, it is determined that the verification of the real estate picture to be verified fails.
The computer device of claim 13, wherein the training of the neural network model comprises:

Acquiring training samples, where the training samples are N real estate pictures marked as remade pictures, and N is a positive integer greater than 0;

Inputting the training sample into the neural network model to obtain N prediction results output by the neural network model in response to the N real estate pictures;

Compare the N prediction results and the annotations through a loss function, where the loss function is:

Among them, N is the number of training samples, Yi is the labeling result for the ith sample, h=(h1, h2,...,hc) is the prediction result of sample i, where C is the number of all categories;

The parameters of each node in the neural network model are adjusted until the loss function reaches a minimum value, and the pre-trained neural network model is obtained.
The computer device of claim 9, wherein the processor further implements the following steps when executing the computer-readable instructions:

The received real estate picture verification request is stored in the blockchain.
A computer-readable storage medium, where computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the processor further performs the following steps:

Receive a real estate image verification request, where the real estate image verification request includes the real estate image to be verified and the real estate information to be verified, wherein the real estate image to be verified contains a digital watermark, and the digital watermark contains the real estate to be verified Location information when the picture was taken;

Retrieves a preset database according to the real estate information to be verified, and obtains the actual location of the real estate to be verified, and the preset database at least pre-stores the actual location of the real estate;

extracting the location information in the digital watermark;

comparing whether the location information is consistent with the actual location;

When the location information is consistent with the actual location, it is determined that the real estate picture has passed the verification.
The computer-readable storage medium according to claim 16, wherein, in the receiving a real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the to-be-verified real estate image is included in the real estate image verification request. The real estate picture contains a digital watermark, and the digital watermark contains the location information of the real estate picture to be verified before the steps, including:

Get real-time shooting requests;

According to the real-time shooting request, call the preset picture shooting module and the preset positioning module to obtain the real-time shooting picture and the location information of the real-time shooting;

The location information is converted into a digital watermark and added to the picture to obtain a picture of the real estate to be verified to which the digital watermark has been added.
The computer-readable storage medium according to claim 16, wherein the preset database contains real estate owner information, and when the location information is consistent with the actual location, it is determined that the real estate picture passes The verification steps also include:

Obtain the property owner information to be verified;

Retrieve a preset database according to the real estate information to be verified, and obtain the actual holder information corresponding to the real estate information;

comparing said property owner information to be verified with said actual owner information;

When the location information is consistent with the actual location, the step of determining that the real estate picture has passed the verification includes:

When the property owner information to be verified is consistent with the actual owner information, and the location information is consistent with the actual location, it is determined that the property image to be verified passes the verification.
19. The computer-readable storage medium of claim 18, wherein the actual holder information includes facial features of the actual holder, and the comparing the property holder information to be verified with the actual holder Steps to have someone information, including:

Perform feature extraction on the face image of the property holder to be verified to obtain the face feature to be verified;

Calculate the similarity between the face feature to be verified and the face feature of the actual holder;

When the similarity is greater than a set threshold, it is determined that the property owner information to be verified is consistent with the actual owner information.
The computer-readable storage medium according to claim 16, wherein, in the receiving a real estate image verification request, the real estate image verification request includes a real estate image to be verified and real estate information to be verified, wherein the to-be-verified real estate image is included in the real estate image verification request. The real estate picture contains a digital watermark, and the digital watermark further includes after the steps of the digital watermark containing the location information of the real estate picture to be verified when shooting:

Inputting the real estate picture to be verified into a pre-trained neural network model, and obtaining a classification result output by the pre-trained neural network model in response to the real estate picture, and the classification result is a remake picture or a non-remake picture;

When the classification result is a retaken picture, it is determined that the verification of the real estate picture to be verified fails.