WO2019056492A1

WO2019056492A1 - Contract investigation processing method, storage medium, and server

Info

Publication number: WO2019056492A1
Application number: PCT/CN2017/108371
Authority: WO
Inventors: 江倩
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-09-19
Filing date: 2017-10-30
Publication date: 2019-03-28
Also published as: CN107633458A

Abstract

A contract investigation processing method, configured to solve the problems of fraud risks and erroneous results when determining the identity of a person under investigation. The method comprises: upon initiation of a contract investigation process, acquiring a first face image of a current person under investigation; acquiring, according to identity information of a target person under investigation, a pre-recorded face image of the target person under investigation from a network-connected police database; performing face recognition on the first face image and the pre-recorded face image, and determining whether the first face image matches the pre-recorded face image; if not, then determining that the identity of the current person under investigation is different from the identity of the target person under investigation; and if so, then determining that the identity of the current person under investigation is the same as the identity of the target person under investigation, and performing subsequent procedures of the contract investigation process.

Description

Method for processing contract investigation, storage medium and server

[0001] The present application claims priority to the Chinese Patent Application No. 201710847319.1, entitled "Processing Method of a Contract Investigation, Storage Medium and Server", filed on September 19, 2017, the entire Chinese patent application The content is incorporated herein by reference.

Technical field

[0001] The present application relates to the field of image recognition technologies, and in particular, to a method for processing a contract investigation, a storage medium, and a server.

Background technique

[0003] Before an insurance company signs an insurance contract, it usually needs to conduct a contract investigation on the insured. In the process of contract investigation, the identity information of the respondent needs to be verified to ensure the authenticity of the information obtained by the investigation.

[0004] Currently, after conducting a contract investigation, it is generally determined by visual judgment whether the face of the respondent and the avatar on the identity document provided by the respondent correspond to each other, and the identity information of the respondent is confirmed. However, this approach has the potential for fraud and the possibility of misjudgment, leading to doubts about the information obtained from contract investigations.

technical problem

[0005] The embodiment of the present application provides a method for processing a contract investigation, a storage medium, and a server, which can complete the identity verification of the respondent, greatly reduce the risk of fraud and the possibility of misjudgment, and improve the contract investigation. The authenticity of the information obtained.

Problem solution

Technical solution

[0006] In a first aspect, a method for processing a contract investigation is provided, including:

[0007] after starting the contract investigation program, acquiring the first face image of the current respondent;

[0008] acquiring, according to the identity information of the target respondent, the reserved face image of the target respondent from the networked public security library;

[0009] performing face recognition on the first face image and the reserved face image, and determining whether the first face image matches the reserved face image; [0010] if the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent;

[0011] if the first face image matches the reserved face image, determining that the identity of the current respondent is the same as the identity of the target respondent, and performing the contract adjustment Check the follow-up process of the program.

[0012] In a second aspect, a computer readable storage medium is provided, the computer readable storage medium storing computer readable instructions, the computer readable instructions being executed by a processor to implement the processing of the contract investigation described above The steps of the method.

[0013] In a third aspect, a server is provided, comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing the computer readable The instruction 吋 implements the following steps:

[0014] after starting the contract investigation program, acquiring the first face image of the current respondent;

[0015] obtaining, according to the identity information of the target respondent, the reserved face image of the target respondent from the networked public security library;

[0016] performing face recognition on the first face image and the reserved face image, and determining whether the first face image matches the reserved face image;

[0017] if the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent;

[0018] if the first face image matches the reserved face image, determining that the identity of the current respondent is the same as the identity of the target respondent, and performing the contract adjustment Check the follow-up process of the program.

[0019] In a fourth aspect, a processing apparatus for a contract investigation is provided, including:

[0020] a first image obtaining module, configured to acquire a first face image of the current respondent after starting the contract investigation program;

[0021] a second image obtaining module, configured to acquire, from the networked public security library, the reserved face image of the target respondent according to the identity information of the target respondent;

[0022] an image matching determination module, configured to perform face recognition on the first face image and the reserved face image, and determine whether the first face image and the reserved face are Image matching

a first identity determining module, configured to determine, if the determination result of the image matching determination module is negative, that the identity of the current respondent is different from the identity of the target respondent; [0024] a second identity determining module, configured to: if the determination result of the image matching determination module is yes, determine that the identity of the current respondent is the same as the identity of the target respondent, and execute the The follow-up process of the contract investigation process.

Advantageous effects of the invention

Beneficial effect

[0025] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0026] In the embodiment of the present application, after the contract investigation procedure is started, the first face image of the current respondent is obtained; and then, according to the identity information of the target respondent, the obtained information is obtained from the networked public security library. Retaining a face image of the target respondent; then performing face recognition on the first face image and the reserved face image, and determining whether the first face image is related to the reserved person a face image matching; if the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent; The first face image is matched with the reserved face image, and then the identity of the current respondent is determined to be the same as the identity of the target respondent, and the subsequent process of the contract investigation procedure is executed. In this way, the face recognition technology can be used to determine whether the current respondent and the target respondent are the same person, thereby completing the identity verification of the respondent, greatly reducing the risk of fraud and the possibility of misjudgment. Improve the authenticity of the information obtained from the contract investigation.

Brief description of the drawing

DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are merely Some embodiments of the present application can also obtain other figures from those skilled in the art without departing from the drawings.

1 is a flow chart of an embodiment of a method for processing a contract investigation according to an embodiment of the present application;

[0029] FIG. 2 is a schematic flowchart of a process 101 of a contract investigation in an application scenario according to an embodiment of the present application;

3 is a schematic flowchart of preprocessing a reserved face image in an application scenario according to a method for processing a contract investigation in an embodiment of the present application;

[0031] FIG. 4 is a processing method of a contract investigation in an embodiment of the present application, and stitching images in an application scenario. A schematic diagram of the process of adding a watermark;

[0032] FIG. 5 is a structural diagram of an embodiment of a processing apparatus for contract investigation in an embodiment of the present application;

FIG. 6 is a schematic diagram of a server according to an embodiment of the present application.

Embodiments of the invention

[0034] The embodiment of the present application provides a method for processing a contract investigation, a storage medium, and a server for solving the problem that the identity of the respondent is subject to the risk of fraud and the possibility of misjudgment.

[0035] In order to make the object, the features and the advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present application. The embodiments described below are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

[0036] Please refer to FIG. 1. One embodiment of a method for processing a contract investigation in an embodiment of the present application includes:

[0037] 101. After starting the contract investigation procedure, acquiring a first face image of the current respondent;

[0038] In this embodiment, the contract investigation procedure can be initiated when a defect is required, such as after an insurance event occurs, before an insurance contract is signed, and the like. After starting the contract investigation procedure, in addition to designating the relevant contract investigator, one or more respondents need to be investigated during the contract investigation. Therefore, after the investigation, it is necessary to verify the current adjustment. Whether the inspector is the target investigator, that is, whether the person currently being investigated is the person who needs to investigate the contract investigation procedure.

[0039] To this end, the first face image of the current respondent may be acquired first. There are various ways to obtain the first face image, for example: The person in charge of the contract investigation takes pictures of the current respondent on the spot, and the current respondent uploads the law to the execution of the contract investigation through legal channels. The method of the server, the current surveyed person self-photographing the face image through the self-service terminal and uploading, and so on.

[0040] Further, in order to facilitate the acquisition of the first face image of the current respondent, and to ensure the authenticity of the acquired first face image, as shown in FIG. 2, the above step 101 may include:

[0041] 201. The actual geographic location where the current respondent is located is obtained.

[0042] 202. Control a designated drone to fly to the current geographic location;

[0043] 203. After the designated drone reaches the current address location, control the designated drone to shoot The first face image of the current respondent is taken and uploaded.

[0044] In step 201, a server (hereinafter referred to as a server) that executes the processing method of the contract investigation may obtain the current geographical location of the current respondent, and specifically, may be related to the current respondent. The communication of the mobile terminal determines its current geographic location. For example, the current respondent remotely communicates with the server through the mobile terminal to complete the contract investigation of the remote video. In this process, the mobile terminal can obtain the current geographic location through gps (Global Positioning System) and send it to the current location. server.

[0045] In step 202, after the server knows the current geographic location of the current respondent, the server can arrange the drone to go to the current respondent's location to perform a photographing operation. The server may search for the most recent executable mission drone based on the current geographic location as a "designated drone" and then control the designated drone to fly to the current geographic location.

[0046] It should be noted that, in the present application, multiple UAVs can be pre-configured to dispatch servers, and these UAVs can be evenly distributed in a certain area, so that as long as the current respondent is in the area, the server The drone can be arranged to perform the photographing task at the location of the current respondent.

[0047] For step 203, after the designated drone reaches the current address location, the server may control the designated drone to perform photographing, recording, and the like on the current respondent, thereby uploading the first face image to The server completes the acquisition of the first face image.

[0048] It can be understood that, after acquiring the first face image, if the person in charge of the contract investigation needs to face and photograph the first face image face-to-face with the current respondent, the cost burden of both parties is greatly increased. If the mobile terminal is remotely uploaded from the current investigator to the server, there may be a case where the first face image is forged. Therefore, in this embodiment, the server can transfer the unmanned aerial vehicle to the current location of the respondent, and then take the first face image through the drone, which not only greatly reduces the cost burden of both parties, but also ensures the first The reliability and authenticity of the face image.

[0049] Preferably, after the designated drone photographing reaches the current address location, the designated drone may first establish a near field communication connection with the mobile terminal carried by the current respondent, and then determine according to the signal of the near field communication. The spatial position of the mobile terminal, and taking a full-body image of the current respondent (photographing, may require the current respondent to cooperate to maintain the standing posture). The system of the designated drone analyzes the whole body image to confirm the position of the face in the whole body image, and then the system of the designated drone can be pushed accordingly Calculate the spatial orientation of the face of the current respondent. The designated drone moves according to the calculated spatial orientation of the face and adjusts the flight attitude, so that the designated drone can collect the face image of the current respondent. Finally, a frame image with the clearest facial features is taken from the captured face image as the first face image.

[0050] Further, after controlling the designated drone to capture the first face image of the current respondent, the designated drone may also be controlled to encrypt the first face image. , obtain an encrypted image, and upload the encrypted image to a designated third party notary server. It can be understood that the first face image captured by the designated drone is the original material of the survey, and the first face image is encrypted and uploaded to the third party notary server, which can be filed for the first time. In the original material, if a legal dispute arises (such as a claims dispute), the encrypted first face image may be extracted from the third party company as relevant evidence to solve the problem of criminal evidence such as insurance fraud. Preferably, in order to further improve the authenticity and legality of the image provided by the third party notary server, the system of the designated drone may be issued by a third party company, and the third party company is equivalent to the witness between the insurance company and the respondent. After the specified drone image is taken, it is automatically uploaded to the third party notary server. This process is not controlled and influenced by the server, thus further ensuring the authenticity and fairness of the original material.

[0051] 102. Obtain a reserved face image of the target respondent from the networked public security library according to the identity information of the target respondent;

[0052] It can be understood that, after conducting a contract investigation, the person who needs to be investigated, that is, the target respondent, is determined in advance. The identity information of these target respondents, such as name, ID number, and household registration, can be obtained in advance. Therefore, before the identity of the current respondent is checked, the reserved face image of the target respondent can be obtained from the networked public security library according to the identity information of the target respondent. Wherein, the reserved face image mentioned here may be the ID photo of the target respondent's identity document.

[0053] 103. Perform face recognition on the first face image and the reserved face image, determine whether the first face image matches the reserved face image, and if not, execute Step 104, if yes, proceed to step 105;

[0054] After acquiring the first face image and the reserved face image, face recognition may be performed on the two images separately, and the face feature information of the two faces is extracted and compared, if the comparison result is Match, then judge The first face image is matched with the reserved face image; otherwise, if the comparison result is not matched, it is determined that the first face image does not match the reserved face image.

[0055] Further, in order to improve the accuracy of the face recognition, as shown in FIG. 3, before step 103, the method may further include:

[0056] 301, determining that the obtained reserved face image is textured, and if yes, performing step 302, if no

, then step 303 is performed;

[0057] 302. Perform a descreening process on the reserved face image.

[0058] 303, respectively, detecting whether the clarity and contrast of the reserved face image meet the preset identification requirements, and if so, executing step 103, and if not, executing step 304;

[0059] 304, adjusting the sharpness and/or contrast of the reserved face image, so that the adjusted clarity and contrast of the reserved face image meet the recognition requirement, and then performing the steps 103.

[0060] For steps 301 and 302, it can be understood that the reserved face image obtained from the public security library, because most of the photos on the identity document, some of the documents are due to age, and there may be a net on the photo. Therefore, these reticulated face images are also provided with these textures. The presence of netting can interfere with face recognition and reduce the accuracy of face recognition. Therefore, if the obtained reserved face image is textured, the shell 1J performs the descreening process.

[0061] For step 303, whether the definition and the contrast of the reserved face image satisfy the recognition requirement may also affect the effect of the face recognition. Specifically, the standard range of the definition standard range and the contrast ratio may be pre-set, and if the resolution of the reserved face image is within the range of the definition standard, the resolution is considered to satisfy the preset recognition requirement; If the contrast of the face image is within the contrast standard range, the contrast is considered to meet the preset recognition requirements. It can be seen that, in order to ensure the accuracy of the face recognition, in this embodiment, after the face image is required to satisfy the requirements of the definition and the contrast, the step 103 is performed, so that any one of the definition and the contrast is not satisfied. If you require 吋, you need to adjust the sharpness or contrast of the reserved face image. ,

[0062] For the step 304, as described above, if the definition or the contrast of the reserved face image does not meet the preset recognition requirement, the definition and/or contrast of the reserved face image needs to be performed. After the adjustment, the clarity and contrast of the adjusted reserved face image satisfy the identification requirement, and then step 103 is performed.

[0063] It should be noted that, in this embodiment, a two-dimensional or three-dimensional face recognition algorithm may be used to reserve a face image. Perform face recognition. Among them, two-dimensional face recognition mainly uses 80 nodes or punctuation distributed from the low to the high on the human face, and the identity is authenticated by measuring the distance between the eyes, the cheekbones, the chin, and the like. For example, it may include: an algorithm based on singular value feature method, subspace analysis method, local hold projection, artificial neural network method, support vector machine method and the like. In appropriate cases, 3D face recognition algorithm can also be used for face recognition. The 3D face recognition algorithm can make up for the shortcomings of 2D face algorithm in face posture, different lighting conditions, expression changes and facial makeup. Improve the accuracy of face recognition. Specifically, the following two types of three-dimensional face recognition algorithms can be adopted in this embodiment:

[0064] 1) Image feature based method: An algorithm for separating the pose from the 3D structure is adopted. First, the size contour and the three-dimensional direction of the entire face are matched; then, in the case where the posture is fixed, the local matching of different feature points of the face (these feature points are manually identified) is performed.

[0065] 2) Model-based variable parameter method: Combine the 3D deformation of the universal face model with the matrix iteration based on the distance map to restore the head pose and the 3D face. As the relationship of the model deformation changes continuously, the attitude parameters are updated, and the process is repeated until the minimum scale meets the requirements. The biggest difference between the model-based variable parameter method and the image feature-based method is that the latter needs to re-search the coordinates of the feature point after each change of the face pose, and the former only needs to adjust the parameters of the 3D deformation model.

[0066] 104. Determine that the identity of the current respondent is different from the identity of the target respondent;

[0067] if the first face image does not match the reserved face image, it may be determined that the identity of the current respondent is different from the identity of the target respondent, and is currently adjusted. The investigator is not the same person as the target respondent.

[0068] 105. Determine that the identity of the current respondent is the same as the identity of the target respondent, and execute a subsequent process of the contract investigation procedure.

[0069] if the first face image matches the reserved face image, it may be determined that the identity of the current respondent is the same as the identity of the target respondent, and the current respondent The same person as the target respondent. After confirming that the current respondent's identity is ok, the subsequent process of the contract investigation procedure can be performed.

[0070] It should be noted that in the subsequent process, the investigation record or report can be submitted by the person in the contract investigation.

, and upload the first face image and/or the reserved face image to the specified image library for file retention.

[0071] Further, as shown in FIG. 4, in step 105, determining the identity of the current respondent and the target After the identity of the respondents is the same, it also includes:

[0072] 401: splicing the first face image and the reserved face image to obtain a spliced image; [0073] 402, adding watermark information to the spliced image, the watermark information including the The name, survey date and face matching result of the target respondent;

[0074] 403. Encrypt the spliced image after adding the watermark information and upload the spliced image to a designated third party notary server.

[0075] For the above steps 401~403, it can be understood that after the first face image is uploaded to the server, the server compares it with the reserved face graphic, regardless of the comparison result, when a legal dispute occurs, Insurance companies may be required to provide relevant materials in the contract investigation process. Therefore, the server may splicing the first face image and the reserved face image to obtain a spliced image, and adding watermark information to the spliced image, where the watermark information includes but is not limited to the name of the target respondent, Investigate date and face matching results. Finally, the stitched image is encrypted and uploaded to a third party notary server. It can be seen that when a legal dispute really occurs and the materials in the contract investigation process need to be provided, the third-party company can extract the corresponding encrypted stitched image from its third-party notary server as electronic evidence, which greatly reduces the legal dispute process. Difficulties in obtaining evidence.

[0076] In particular, the stitched image with the watermark information added in 402 may be first cached in the nas (Network Attached Storage) space, and when the person in charge of the contract investigation submits the survey record or report, the stitched image is The nas space is uploaded to the specified image library as a file of the insurance company.

[0077] In this embodiment, after the contract investigation procedure is started, the first face image of the current respondent is obtained; and then, the target is obtained from the networked public security library according to the identity information of the target respondent. Retaining a face image of the respondent; then performing face recognition on the first face image and the reserved face image, and determining whether the first face image and the reserved face are Image matching; if the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent; A face image is matched with the reserved face image, and then the identity of the current respondent is determined to be the same as the identity of the target respondent, and the subsequent process of the contract investigation procedure is executed. In this way, the face recognition technology can be used to determine whether the current respondent and the target respondent are the same person, thereby completing the identity verification of the respondent, greatly reducing the risk of fraud and the possibility of misjudgment. Improve the authenticity of the information obtained from the contract investigation. It should be understood that the size of the serial number of each step in the foregoing embodiment does not mean the order of execution sequence, and the execution order of each process should be determined by its function and internal logic, and should not be implemented in the implementation process of the embodiment of the present application. Any restrictions.

[0079] The above mainly describes a processing method of a contract investigation, and a processing apparatus for a contract investigation will be described in detail below.

[0080] FIG. 5 is a structural diagram showing an embodiment of a processing apparatus for contract investigation in the embodiment of the present application.

[0081] In this embodiment, a processing device for a contract investigation includes:

[0082] The first image obtaining module 501 is configured to acquire a first face image of the current respondent after starting the contract investigation program;

[0083] The second image obtaining module 502 is configured to obtain, according to the identity information of the target respondent, the reserved face image of the target respondent from the networked public security library;

[0084] The image matching determining module 503 is configured to perform face recognition on the first face image and the reserved face image, and determine whether the first face image matches the reserved face image ;

[0085] The first identity determining module 504 is configured to: if the determination result of the image matching determining module 503 is negative, determine that the identity of the current respondent is different from the identity of the target respondent;

[0086] The second identity determining module 505 is configured to: if the determination result of the image matching determining module 503 is yes, determine that the identity of the current respondent is the same as the identity of the target respondent, and Perform the follow-up process of the contract investigation process.

[0087] Further, the processing device of the contract investigation may further include:

[0088] a descreening processing module, configured to perform a descreening process on the reserved face image if the obtained reserved face image is textured;

[0089] an identification request detection module, configured to separately detect whether the definition and the contrast of the reserved face image meet the preset recognition requirement;

[0090] The first triggering module is configured to trigger the image matching determining module if the detection result of the identification request detecting module is YES;

[0091] a second triggering module, configured to: if the detection result of the identification request detecting module is negative, adjust the sharpness and/or contrast of the reserved face image, so that the adjusted The sharpness and contrast of the face image are satisfied to meet the recognition requirement, and then the image matching judgment module is triggered. [0092] Further, the first image obtaining module may include:

[0093] a geographic location obtaining unit, configured to obtain a current geographic location where the current respondent is located;

[0094] a flight control unit, configured to control a designated drone to fly to the current geographic location;

And a photographing uploading unit, configured to control the designated drone to capture and upload the first face image of the current respondent after the designated drone reaches the current address location.

[0096] Further, the processing device of the contract investigation may further include:

[0097] an encryption uploading module, configured to control the specified drone to encrypt the first facial image after controlling the designated drone to capture the first face image of the current respondent , obtain an encrypted image, and upload the encrypted image to a designated third party notary server.

[0098] Further, the processing device of the contract investigation may further include:

[0099] an image splicing module, configured to splicing the first face image and the reserved face image to obtain a spliced image;

[0100] a watermark adding module, configured to add watermark information on the stitched image, where the watermark information includes a name, an investigation date, and a face matching result of the target respondent;

[0101] The spliced image uploading module is configured to encrypt and upload the spliced image after adding the watermark information to a designated third party notary server.

6 is a schematic diagram of a server according to an embodiment of the present application. As shown in FIG. 6, the server 6 of this embodiment includes: a processor 60, a memory 61, and computer readable instructions 62 stored in the memory 61 and operable on the processor 60, for example, executing the contract described above. The procedure for investigating the method of investigation. The processor 60 executes the computer readable instructions 62 to implement the steps in the processing method embodiments of the various contract investigations described above, such as steps 101 through 105 shown in FIG. Alternatively, the processor 60 executes the computer readable instructions 62 to implement the functions of the modules/units in the various apparatus embodiments described above, such as the functions of the modules 501 through 505 shown in FIG.

[0103] Illustratively, the computer readable instructions 62 may be partitioned into one or more modules/units, the one or more modules/units being stored in the memory 61, and by the processor 60 is performed to complete the application. The one or more modules/units may be a series of computer readable instruction instruction segments capable of performing a particular function for describing the execution of the computer readable instructions 62 in the server 6. [0104] The server 6 may be a computing device such as a local server or a cloud server. The server may include, but is not limited to, processor 60, memory 61. It will be understood by those skilled in the art that FIG. 6 is merely an example of the server 6, and does not constitute a limitation to the server 6, and may include more or less components than those illustrated, or some components may be combined, or different components, such as The server may also include an input output device, a network access device, a bus, and the like.

[0105] The processor 60 may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-to-use programmable gate array

(Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

[0106] The memory 61 may be an internal storage unit of the server 6, such as a hard disk or a memory of the server 6. The memory 61 may also be an external storage device of the server 6, such as a plug-in hard disk provided on the server 6, a smart memory card (SMC), and a Secure Digital (SD) card. Flash card, etc. Further, the memory 61 may also include both an internal storage unit of the server 6 and an external storage device. The memory 61 is for storing the computer readable instructions and other programs and data required by the server. The memory 61 can also be used to temporarily store data that has been output or is about to be output.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0108] The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage The media includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

The above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that The technical solutions described in the embodiments are modified, or some of the technical features are equivalently replaced; and the modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

Claim

[Claim 1] A method for processing a contract investigation, comprising:

After starting the contract investigation program, acquiring the first face image of the current respondent; obtaining the reserved face image of the target respondent from the networked public security library according to the identity information of the target respondent ;

Performing face recognition on the first face image and the reserved face image, and determining whether the first face image matches the reserved face image;

If the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent; if the first face is And matching the image with the reserved face image, determining that the identity of the current respondent is the same as the identity of the target respondent, and performing a subsequent process of the contract investigation procedure.

[Claim 2] The method for processing a contract investigation according to claim 1, wherein the first face image and the reserved face image are subjected to face recognition, and the first is determined Before the face image is matched with the reserved face image, the method further includes: if the obtained reserved face image is textured, performing the descreening process on the reserved face image;

Detecting respectively whether the definition and the contrast of the reserved face image meet the preset identification requirements;

Performing the face recognition on the first face image and the reserved face image by performing the face recognition on the first face image and the reserved face image, if the resolution and the contrast of the reserved face image meet the preset recognition requirements. a step of matching a face image with the reserved face image;

If the definition or the contrast of the reserved face image does not meet the preset recognition requirement, the sharpness and/or contrast of the reserved face image is adjusted to make the adjusted reserved person Determining the resolution and the contrast of the face image, and performing the face recognition on the first face image and the reserved face image, and determining whether the first face image is The step of reserving the face image matching.

[Claim 3] The method for processing a contract investigation according to claim 1, wherein the acquisition The first face image of the current respondent includes:

Obtaining a current geographic location where the current respondent is located; controlling a designated drone to fly to the current geographic location;

After the designated drone reaches the current address location, the designated drone is controlled to capture and upload a first face image of the current respondent.

[Claim 4] The processing method of the contract investigation according to claim 3, wherein the processing method of the contract investigation further comprises:

After controlling the designated drone to capture the first face image of the current respondent, controlling the designated drone to encrypt the first face image to obtain an encrypted image, and The encrypted image is uploaded to the designated third-party notary server.

[Claim 5] The method of processing a contract investigation according to any one of claims 1 to 4, characterized in that

After determining that the identity of the current respondent is the same as the identity of the target respondent, the method further includes:

And splicing the first face image and the reserved face image to obtain a spliced image; adding watermark information to the spliced image, the watermark information including a name, an investigation of the target respondent Date and face matching results;

The spliced image after adding the watermark information is encrypted and uploaded to a designated third party notary server.

[Claim 6] A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions are executed by a processor to implement the following steps:

If the first face image does not match the reserved face image, determining that the identity of the current respondent is different from the identity of the target respondent; If the first face image matches the reserved face image, determining that the identity of the current respondent is the same as the identity of the target respondent, and executing the contract investigation procedure Follow-up process.

[Claim 7] The computer readable storage medium according to claim 6, wherein the first person is determined by performing face recognition on the first face image and the reserved face image Before the matching of the face image with the reserved face image, the method further includes: if the acquired reserved face image is textured, performing the descreening process on the reserved face image;

[Claim 8] The computer readable storage medium according to claim 6, wherein the acquiring the first face image of the current respondent comprises:

[Claim 9] The computer readable storage medium of claim 8, wherein the computer readable instructions are executed by a processor, further comprising:

After controlling the designated drone to capture the first face image of the current respondent, controlling the designated drone to encrypt the first face image to obtain an encrypted image, And uploading the encrypted image to a designated third party notary server.

[Claim 10] The computer readable storage medium according to any one of claims 6 to 9, wherein the identity of the current respondent is determined to be the same as the identity of the target respondent After that, it also includes:

[Claim 11] A server comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer readable The instruction 吋 implements the following steps:

[Claim 12] The server according to claim 11, wherein the face recognition is performed on the first face image and the reserved face image, and it is determined whether the first face image is Before the reserved face image is matched, the method further includes:

If the obtained reserved face image is textured, the reserved face image is subjected to a descreening process;

Detecting respectively whether the definition and the contrast of the reserved face image satisfy the preset identification begging;

[Claim 13] The server according to claim 11, wherein the acquiring the first face image of the current respondent comprises:

[Claim 14] The server according to claim 13, further comprising:

[Claim 15] The server according to any one of claims 11 to 14, wherein after determining that the identity of the current respondent is the same as the identity of the target respondent, And splicing the first face image and the reserved face image to obtain a spliced image; adding watermark information to the spliced image, the watermark information including a name, an investigation of the target respondent Date and face matching results;

[Claim 16] A processing apparatus for a contract investigation, comprising: a first image obtaining module, configured to acquire a first face image of the current respondent after starting the contract investigation program;

a second image obtaining module, configured to acquire, from the networked public security library, the reserved face image of the target respondent according to the identity information of the target respondent;

An image matching judging module, configured to perform face recognition on the first face image and the reserved face image, and determine whether the first face image matches the reserved face image; a determining module, configured to determine, if the determination result of the image matching determination module is negative, that the identity of the current respondent is different from the identity of the target respondent; the second identity determining module is configured to: If the judgment result of the image matching judgment module is YES, it is determined that the identity of the current respondent is the same as the identity of the target respondent, and the subsequent flow of the contract investigation procedure is executed.

The processing device for the contract investigation according to claim 16, wherein the processing device for the contract investigation further comprises:

a texture processing module, configured to perform a descreening process on the reserved face image if the obtained reserved face image is textured;

The identification request detection module is configured to separately detect whether the definition and contrast of the reserved face image meet the preset recognition requirement;

a first triggering module, configured to trigger the image matching determining module if the detection result of the identification request detecting module is YES;

a second triggering module, configured to adjust a sharpness and/or a contrast of the reserved face image if the detection result of the identification request detecting module is negative, so that the adjusted reserved face The sharpness and contrast of the image both satisfy the recognition requirement, and then the image matching judgment module is triggered.

[Claim 18] The processing apparatus of the contract investigation according to claim 16, wherein the first image acquisition module comprises:

a geographic location obtaining unit, configured to obtain a current geographic location where the current respondent is located;

a flight control unit, configured to control a designated drone to fly to the current geographic location; The photographing uploading unit is configured to control the designated drone to capture and upload the first face image of the current respondent after the designated drone reaches the current address location.

The processing device of the contract investigation according to claim 18, wherein the processing device for the contract investigation further comprises:

An encryption uploading module, configured to control the specified drone to encrypt the first facial image after the first drape image of the current respondent is controlled, and obtain the encryption Image, and upload the encrypted image to a designated third party notary server.

[Claim 20] The processing device of the contract investigation according to any one of claims 16 to 19, wherein the processing device of the contract investigation further comprises:

An image splicing module, configured to splicing the first face image and the reserved face image to obtain a spliced image;

a watermark adding module, configured to add watermark information on the mosaic image, the watermark information including a name, an investigation date, and a face matching result of the target respondent; a mosaic image uploading module, configured to add The stitched image after the watermark information is encrypted and uploaded to a designated third party notary server.