CN110942069A - Method, device, storage medium and equipment for extracting key information of vehicle insurance policy - Google Patents
Method, device, storage medium and equipment for extracting key information of vehicle insurance policy Download PDFInfo
- Publication number
- CN110942069A CN110942069A CN201911003015.2A CN201911003015A CN110942069A CN 110942069 A CN110942069 A CN 110942069A CN 201911003015 A CN201911003015 A CN 201911003015A CN 110942069 A CN110942069 A CN 110942069A
- Authority
- CN
- China
- Prior art keywords
- insurance policy
- vehicle insurance
- image
- identified
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000000605 extraction Methods 0.000 claims description 23
- 238000001514 detection method Methods 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a method, a device, a storage medium and equipment for extracting key information of a vehicle insurance policy, wherein the method comprises the following steps: acquiring an insurance policy image of the vehicle insurance to be identified; determining the key position of the vehicle insurance policy image to be identified; and extracting key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy. The key information of the vehicle insurance policy is extracted by determining the key position of the image of the vehicle insurance policy to be identified, wherein the key information is the information capable of revealing the validity of the vehicle insurance policy. Therefore, the time spent by the staff for searching the key information in the vehicle insurance policy can be reduced as much as possible, and the extracted information is convenient to enter, so that the time for checking the vehicle insurance policy can be saved, and the vehicle detection efficiency is improved.
Description
Technical Field
The application relates to the field of image processing, in particular to a method, a device, a storage medium and equipment for extracting key information of a vehicle insurance policy.
Background
In the process of detecting various vehicles (whether the light and the exhaust emission reach the standard or not) by the vehicle inspection station, whether the vehicle owner handles related vehicle insurance matters or not needs to be checked, such as the conditions of strong insurance and business insurance. Since the majority of the car owners provide the original or copy of the insurance policy of the car insurance, the conventional method is to manually check the information of the insurance policy, and the checked information includes: whether the vehicle to be detected belongs to insurance of the vehicle to be detected, whether the vehicle to be detected belongs to the insurance of the vehicle to be detected, the name of an insurance company, the number of a policy, the amount of the policy and the like in the validity period.
Because a large number of vehicles need to be detected every day at the vehicle inspection station, and the types, styles, insurance companies and the like of the vehicle insurance policies are various, the positions of various key information need to be searched for verification by a manual detection mode, and then the information is recorded. Generally, the process of checking a car insurance policy and entering key information takes more than 5 minutes, resulting in inefficient detection.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, a storage medium, and a device for extracting key information of a vehicle insurance policy, so as to save time for checking the vehicle insurance policy, thereby improving vehicle detection efficiency.
In order to achieve the above object, embodiments of the present application are implemented as follows:
in a first aspect, an embodiment of the present application provides a method for extracting key information of a vehicle insurance policy, where the method includes: acquiring an insurance policy image of the vehicle insurance to be identified; determining the key position of the vehicle insurance policy image to be identified; and extracting key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy.
The key information of the vehicle insurance policy is extracted by determining the key position of the image of the vehicle insurance policy to be identified, wherein the key information is the information capable of revealing the validity of the vehicle insurance policy. Therefore, the time spent by the staff for searching the key information in the vehicle insurance policy can be reduced as much as possible, and the extracted information is convenient to enter, so that the time for checking the vehicle insurance policy can be saved, and the vehicle detection efficiency is improved.
With reference to the first aspect, in a first possible implementation manner of the first aspect, determining a key location of the to-be-identified vehicle insurance policy image includes: determining an insurance company corresponding to the vehicle insurance policy from the image of the vehicle insurance policy to be identified; determining a car insurance policy sample of the insurance company; and determining the key position of the to-be-identified vehicle insurance policy image according to the sample position of the recorded key information in the vehicle insurance policy sample.
The corresponding car insurance policy sample is determined by determining the insurance company corresponding to the car insurance policy, and the key position of the car insurance policy image to be identified can be rapidly and accurately determined based on the sample position of the car insurance policy sample, so that the efficiency of the key information extraction method of the car insurance policy is improved.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, determining an insurance company corresponding to the vehicle insurance policy from the image of the vehicle insurance policy to be identified includes: obtaining seal information from the vehicle insurance policy image to be identified, wherein the seal information comprises the name of the insurance company; and extracting characters in the seal information to determine the insurance company.
Because the seal information comprises the name of the insurance company, the corresponding insurance company can be quickly and accurately determined by determining the seal information in the image of the vehicle insurance policy to be identified, and therefore, the efficiency of the key information extraction method of the vehicle insurance policy can be improved.
With reference to the first possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the determining, from the image of the to-be-identified vehicle insurance policy, an insurance company corresponding to the vehicle insurance policy includes: determining insurance person information of the vehicle insurance policy from the image of the vehicle insurance policy to be identified, wherein the insurance person information comprises the name of the insurance company; and extracting characters in the information of the insurer to determine the insurance company.
Because the insurance person information comprises the name of the insurance company, the corresponding insurance company can be quickly and accurately determined by determining the insurance person information in the image of the vehicle insurance policy to be identified, and therefore, the efficiency of the key information extraction method of the vehicle insurance policy can be improved.
With reference to the second possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, the obtaining seal information from the to-be-identified vehicle insurance policy image includes: determining a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified; determining a seal area containing the seal information according to the form line; and acquiring the seal information from the seal area.
By determining the table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified, the seal area containing the seal information can be determined accurately, and therefore the efficiency is improved.
With reference to the first aspect or any one of the first to the fourth possible implementation manners of the first aspect, in a fifth possible implementation manner of the first aspect, the extracting key information of the insurance policy in the image of the insurance policy to be identified according to the key position includes: determining a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified; cutting the insurance policy image to be identified according to the key position and the table line, and acquiring a cut text image, wherein the text image comprises the key information; and extracting characters in the text image to acquire the key information.
The to-be-identified car insurance policy image is cut based on the table lines and the key positions of the car insurance policy in the to-be-identified car insurance policy image, so that the cut text image is obtained, the key information of the car insurance policy can be accurately extracted, and the accuracy of the determined key information can be ensured.
With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the acquiring an image of a to-be-identified car insurance policy includes: acquiring an original image for shooting the vehicle insurance policy; determining the outline of the vehicle insurance policy in the original image; and cutting the original image according to the outline of the vehicle insurance policy to obtain the image of the vehicle insurance policy to be identified.
The original image of the vehicle insurance policy is processed, the original image is cut based on the outline of the vehicle insurance policy, noise in the original image can be eliminated, and the image of the vehicle insurance policy to be identified is obtained, so that the accuracy of the key information extraction method of the vehicle insurance policy can be improved as much as possible.
In a second aspect, an embodiment of the present application provides an apparatus for extracting key information of a vehicle insurance policy, where the apparatus includes: the image acquisition module is used for acquiring an insurance policy image of the vehicle insurance to be identified; the key position determining module is used for determining the key position of the to-be-identified vehicle insurance policy image; and the key information extraction module is used for extracting the key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy.
In a third aspect, an embodiment of the present application provides a storage medium, where one or more programs are stored, and the one or more programs are executable by one or more processors to implement the method for extracting key information of a vehicle insurance policy according to any one of the first aspect or possible implementation manners of the first aspect.
In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, where the memory is configured to store information including program instructions, and the processor is configured to control execution of the program instructions, where the program instructions are loaded and executed by the processor to implement the method for extracting key information of a vehicle insurance policy according to the first aspect or any one of possible implementation manners of the first aspect.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a method for extracting key information of a vehicle insurance policy according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an original image of a car insurance policy provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of an image of a to-be-identified insurance policy obtained by processing an original image according to an embodiment of the present application.
Fig. 4 is a block diagram of a structure of a key information extraction device of a vehicle insurance policy according to an embodiment of the present application.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Icon: 10-key information extraction device of the vehicle insurance policy; 11-an image acquisition module; 12-a key location determination module; 13-key information extraction module; 20-an electronic device; 21-a memory; 22-a communication module; 23-a bus; 24-a processor; 25-camera device.
Detailed Description
In the process of detecting various vehicles (whether the light and the exhaust emission reach the standard or not) by the vehicle inspection station, whether the vehicle owner handles related vehicle insurance matters or not needs to be checked, such as the conditions of strong insurance and business insurance. Since the majority of the car owners provide the original or copy of the insurance policy of the car insurance, the conventional method is to manually check the information of the insurance policy, and the checked information includes: whether the vehicle to be detected belongs to insurance of the vehicle to be detected, whether the vehicle to be detected belongs to the insurance of the vehicle to be detected, the name of an insurance company, the number of a policy, the amount of the policy and the like in the validity period.
Because a large number of vehicles need to be detected every day at the vehicle inspection station, and the types, styles, insurance companies and the like of the vehicle insurance policies are various, the positions of various key information need to be searched for verification by a manual detection mode, and then the information is recorded. Generally, the process of checking a car insurance policy and entering key information takes more than 5 minutes, resulting in inefficient detection.
The inventors of the present application analyzed the above-described processing procedure to find that: in the checking process of the vehicle insurance policy, the worker takes a picture of the vehicle insurance policy for a certain time, and if the worker introduces a corresponding computer system or device to process part or all steps in the checking process of the vehicle insurance policy, the checking efficiency of the vehicle insurance policy of the vehicle inspection station can be greatly improved.
Based on this, the inventor of the present application provides a method, an apparatus, a storage medium and a device for extracting key information of a vehicle insurance policy, so as to save time for checking the vehicle insurance policy, thereby improving vehicle detection efficiency.
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for extracting key information of a car insurance policy according to an embodiment of the present disclosure. In the present embodiment, the method for extracting key information of the vehicle insurance policy may include step S10, step S20, and step S30.
In the present embodiment, the step S10 may be performed when the vehicle insurance policy is verified.
Step S10: and acquiring an insurance policy image to be identified.
In this embodiment, when the vehicle insurance policy is checked, the original image can be obtained by shooting the vehicle insurance policy. The shooting device for shooting the car insurance policy can be terminal equipment with a shooting function, such as a camera, a video camera, a smart phone, a tablet personal computer and the like, and also can be electronic equipment for executing a key information extraction method of the car insurance policy.
Since the distance or angle between the car insurance policy and the shooting device is not absolutely fixed when the car insurance policy is shot, the shot original image usually has rotational distortion, noise and uneven illumination, and an irrelevant background image may exist in the original image (i.e. a partial image in the original image may be redundant).
In order to ensure the accuracy of the image of the vehicle insurance policy and reduce the interference factors as much as possible, in the embodiment, the original image of the vehicle insurance policy can be processed to eliminate the noise in the original image of the vehicle insurance policy, so that the image of the vehicle insurance policy to be identified is obtained. In this embodiment, Hough transform (a method for detecting a curve in which shapes such as a straight line, a circle, a parabola, and an ellipse in an image can be described by a certain functional relationship) may be employed to extract straight line information in an original image, a contour of a car insurance policy (here, the contour may be a contour of the entire car insurance policy, or a contour of a table of the car insurance policy) may be determined, and rotation correction may be performed on the original image based on the contour, so that the car insurance policy in the original image is vertically (or horizontally) placed for subsequent processing. After the original image is corrected, the corrected original image may be processed by an image preprocessing method, for example, noise removal, sharpening, histogram equalization, and non-uniform illumination. Then, the image can be cut according to the outline of the vehicle insurance policy so as to obtain the image of the vehicle insurance policy to be identified.
As shown in fig. 2, fig. 2 shows an original image of a car insurance policy provided in an embodiment of the present application. In the original image, the car insurance policy has some tilt, uneven light, and some unwanted background parts. After the original image is processed, the obtained insurance policy image to be identified is shown in fig. 3.
The original image of the vehicle insurance policy is processed, the original image is cut based on the outline of the vehicle insurance policy, noise in the original image can be eliminated, and the image of the vehicle insurance policy to be identified is obtained, so that the accuracy of the key information extraction method of the vehicle insurance policy can be improved as much as possible.
It should be noted that, in the process of processing the original image to obtain the insurance policy image to be identified described in this embodiment, the sequence of steps may be different, and is not limited to the above exemplary processing sequence. For example, the processing of the original image may be to perform denoising, sharpening, histogram equalization processing on the phenomena of noise and uneven illumination, identify the outline of the insurance policy, perform rotation correction on the original image, and then perform cutting; the contour of the insurance policy may be recognized, cut, denoised, sharpened, histogram equalized, etc., and therefore, the present application should not be considered as limited herein. The method of specifying the contour of the vehicle insurance policy is not limited to the Hough transform method.
As the insurance companies are numerous, the policy types of each insurance company are different, the tables are different greatly, and the positions of the key information of the policies on the policies of different companies are different. In order to effectively extract the key information of the vehicle insurance policy, reduce the difficulty of subsequent identification and facilitate the checking of the vehicle insurance policy by the staff, the step S20 can be executed after the image of the vehicle insurance policy to be identified is obtained.
Step S20: and determining the key position of the vehicle insurance policy image to be identified.
In the process of checking the vehicle insurance policy, the staff only needs to check some specific information of the vehicle insurance policy (such as whether the information belongs to the insurance of the vehicle to be detected, whether the information is in the valid period, the vehicle license plate, the name of an insurance company, the policy number, the policy amount, the policy period, the insurance person and the like) to determine the validity of the vehicle insurance policy, and the determination of the key position for recording the specific information is favorable for accelerating the checking of the vehicle insurance policy by the staff.
In order to quickly and accurately determine the key position of the to-be-identified vehicle insurance policy image, in this embodiment, an insurance company corresponding to the vehicle insurance policy can be determined from the to-be-identified vehicle insurance policy image, a vehicle insurance policy sample of the insurance company is further determined, and the key position of the to-be-identified vehicle insurance policy image is determined based on the sample position of the recorded key information in the vehicle insurance policy sample.
Because the stamp information comprises the name of the insurance company, the insurance company corresponding to the vehicle insurance policy can be determined by determining the stamp information. Since the stamp information is generally below the vehicle insurance policy (including lower left, lower right, center below, etc., which are generally more on the lower right), for example, the table line of the vehicle insurance policy can be determined from the image of the vehicle insurance policy to be recognized. The identified form lines, in combination, may be based on the identification of color components (in the case of the original of the insurance policy, the stamp is typically red or blue, so that a range of color values may be identified). The stamp region where the stamp information is located may also be identified in a bottom-up manner (the stamp is generally present mostly under the vehicle insurance policy). The method can also be based on shape identification (the shape of the stamp area can be generally rectangular, circular, oval and the like), and the method for identifying the stamp area where the stamp information is located is not limited, and only the stamp area needs to be determined.
After the seal area is determined, the seal information contained in the seal area can be obtained, characters in the seal information are further extracted, and the corresponding insurance company is determined. By determining the seal information in the image of the vehicle insurance policy to be identified, the corresponding insurance company can be quickly and accurately determined, so that the efficiency of the key information extraction method of the vehicle insurance policy can be improved.
Since the name of the insurance company is necessarily included in the insurance person information, the insurance company corresponding to the vehicle insurance policy can be determined by determining the insurance person information. Since the insurance person information generally appears below the vehicle insurance policy (the bottom of the vehicle insurance policy is most), the insurance person information can be identified in a bottom-up manner in the present embodiment. The identification method can be to extract and identify the words to determine the 'XX insurance company' word, so as to determine the corresponding insurance company. By determining the information of the insurers in the image of the vehicle insurance policy to be identified, the corresponding insurance company can be determined quickly and accurately, so that the efficiency of the key information extraction method of the vehicle insurance policy can be improved.
It should be noted that the method for determining the insurance company corresponding to the vehicle insurance policy is not limited to the two methods, and the method may also be implemented by performing text extraction and recognition on the entire vehicle insurance policy, and recognizing the "XX insurance company" in the vehicle insurance policy, so as to determine the insurance company corresponding to the vehicle insurance policy. Therefore, the present application should not be considered as limited herein.
After the corresponding insurance company is determined, a sample of the vehicle insurance policy used by the insurance company can be obtained. In this embodiment, the manner of obtaining the car insurance policy sample may be determined from a preset data set (i.e., the established insurance company name and the corresponding car insurance policy sample data set, including the insurance company name and the corresponding car insurance policy sample, and the car insurance policy sample corresponding to the insurance company name may be output by inputting the insurance company name), or may be queried by searching a keyword through a network, which is not limited herein. Therefore, the vehicle insurance policy sample corresponding to the insurance company can be determined quickly and accurately.
Since in an actual vehicle insurance policy, insurance companies usually adopt certain table systems (i.e., the vehicle insurance policy of an insurance company adopts the same table system). In this embodiment, the manner of determining the sample position of the car insurance policy sample may be: and determining the table system of the vehicle insurance policy sample of the insurance company through the name of the insurance company, and determining the sample position for recording the key information based on the table system of the type.
Of course, some insurance companies may have more than two table systems, for example, the insurance companies may modify the table system of the vehicle insurance policy in the near future, so that more than two table systems exist. For the situation, corresponding vehicle insurance policy samples can be established corresponding to the vehicle insurance policies of different table systems of the insurance company, and before the sample position of the vehicle insurance policy sample is determined, an accurate vehicle insurance policy sample can be determined by performing a vehicle insurance policy sample matching process according to the distribution situation of the table lines.
Therefore, the key position of the to-be-identified car insurance policy image can be determined according to the sample position of the key information recorded in the car insurance policy sample. In this embodiment, the sample position of the car insurance policy sample may be preset in advance, or may be determined by querying the sample position of the car insurance policy sample of the insurance company, which is not limited herein. As for the mode of determining the key position of the to-be-identified car insurance policy image based on the sample position of the car insurance policy sample, because the form patterns of the car insurance policy sample and the car insurance policy are consistent, the position of the corresponding form in the to-be-identified car insurance policy image can be determined as the key position through the position of the form of the sample position in the car insurance policy sample, and the accuracy of determining the key position can be ensured.
The corresponding car insurance policy sample is determined by determining the insurance company corresponding to the car insurance policy, and the key position of the car insurance policy image to be identified can be rapidly and accurately determined based on the sample position of the car insurance policy sample, so that the efficiency of the key information extraction method of the car insurance policy is improved.
In addition, the number of the key positions of the insurance policy image to be identified may be one or multiple, and should not be considered as a limitation of the present application.
After the key positions of the insurance policy image to be recognized are determined, step S30 may be performed.
Step S30: and extracting key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy.
In this embodiment, the key information of the insurance policy can be extracted through the key position, so that the worker can check the insurance policy. For example, a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified can be determined. And cutting the image of the insurance policy to be identified by adopting a projection method through the table determined by the table lines and the key positions to obtain a cut text image, wherein the text image comprises key information of the insurance policy. The characters in the text image can be further extracted, and the key information of the vehicle insurance policy can be determined according to the extracted characters. For example, the extracted characters may be recognized by using an OCR (Optical Character Recognition) technology or a deep learning method, so as to determine the key information.
The to-be-identified car insurance policy image is cut based on the table lines and the key positions of the car insurance policy in the to-be-identified car insurance policy image, so that the cut text image is obtained, the key information of the car insurance policy can be accurately extracted, and the accuracy of the determined key information can be ensured.
In the embodiment, for the extracted key information, the staff can selectively input the key information after checking the key information, and the key information is not required to be input in a word-by-word input mode, so that a large amount of information input time can be saved.
Referring to fig. 4, based on the same inventive concept, an embodiment of the present application further provides a device 10 for extracting key information of a car insurance policy, where the device includes: the image acquisition module 11 is used for acquiring an insurance policy image of the vehicle insurance to be identified; a key position determining module 12, configured to determine a key position of the to-be-identified vehicle insurance policy image; and the key information extraction module 13 is configured to extract key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, where the key information is information capable of revealing the validity of the vehicle insurance policy.
In this embodiment, the key position determining module 12 is further configured to determine, from the image of the to-be-identified vehicle insurance policy, an insurance company corresponding to the vehicle insurance policy; determining a car insurance policy sample of the insurance company; and determining the key position of the to-be-identified vehicle insurance policy image according to the sample position of the recorded key information in the vehicle insurance policy sample.
In this embodiment, the key position determining module 12 is further configured to obtain seal information from the to-be-identified vehicle insurance policy image, where the seal information includes a name of the insurance company; and extracting characters in the seal information to determine the insurance company.
In this embodiment, the key position determining module 12 is further configured to determine, from the image of the to-be-identified car insurance policy, insurance person information of the car insurance policy, where the insurance person information includes a name of the insurance company; and extracting characters in the information of the insurer to determine the insurance company.
In this embodiment, the key position determining module 12 is further configured to determine a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified; determining a seal area containing the seal information according to the form line; and acquiring the seal information from the seal area.
In this embodiment, the key information extraction module 13 is further configured to determine a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified; cutting the insurance policy image to be identified according to the key position and the table line, and acquiring a cut text image, wherein the text image comprises the key information; and extracting characters in the text image to acquire the key information.
In this embodiment, the image obtaining module 11 is further configured to obtain an original image of the car insurance policy; determining the outline of the vehicle insurance policy in the original image; and cutting the original image according to the outline of the vehicle insurance policy to obtain the image of the vehicle insurance policy to be identified.
The embodiment of the present application further provides a storage medium, where one or more programs are stored, and the one or more programs may be executed by one or more processors to implement the method for extracting key information of a vehicle insurance policy as described in this embodiment.
Referring to fig. 5, fig. 5 is a block diagram illustrating an electronic device according to an embodiment of the present disclosure. In this embodiment, the electronic device 20 for executing the key information extraction method for the vehicle insurance policy provided in the embodiment of the present application may be a terminal, such as a smart phone, a tablet computer, a personal digital assistant, and the like; the electronic device 20 may also be a server, such as a network server, a cloud server, a server cluster, a data server, etc., and is not limited herein.
Illustratively, the electronic device 20 may include: a communication module 22 connected to the outside world via a network, one or more processors 24 for executing program instructions, a bus 23, a different form of memory 21, and a camera 25 (in some alternative implementations, the electronic device 20 may not include the camera 25). Such as a disk, ROM (Read-only Memory), or RAM (Random Access Memory), or any combination thereof.
Illustratively, the memory 21 has stored therein a program. The processor 24 can call and run these programs from the memory 21 and control the image pickup device 25 to pick up the original image of the vehicle insurance policy, so that the key information extraction method of the vehicle insurance policy can be performed by running the programs.
In summary, the embodiment of the present application provides a method, an apparatus, a storage medium, and a device for extracting key information of a vehicle insurance policy, which extract key information of the vehicle insurance policy by determining a key position of an image of the vehicle insurance policy to be identified, where the key information is information capable of disclosing validity of the vehicle insurance policy. Therefore, the time spent by the staff for searching the key information in the vehicle insurance policy can be reduced as much as possible, and the extracted information can be conveniently input by the staff, so that the time for checking the vehicle insurance policy can be saved, and the vehicle detection efficiency can be improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A key information extraction method of a vehicle insurance policy is characterized by comprising the following steps:
acquiring an insurance policy image of the vehicle insurance to be identified;
determining the key position of the vehicle insurance policy image to be identified;
and extracting key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy.
2. The method for extracting the key information of the vehicle insurance policy according to claim 1, wherein the step of determining the key position of the image of the vehicle insurance policy to be identified comprises the following steps:
determining an insurance company corresponding to the vehicle insurance policy from the image of the vehicle insurance policy to be identified;
determining a car insurance policy sample of the insurance company;
and determining the key position of the to-be-identified vehicle insurance policy image according to the sample position of the recorded key information in the vehicle insurance policy sample.
3. The method for extracting the key information of the vehicle insurance policy according to claim 2, wherein the step of determining the insurance company corresponding to the vehicle insurance policy from the image of the vehicle insurance policy to be identified comprises the following steps:
obtaining seal information from the vehicle insurance policy image to be identified, wherein the seal information comprises the name of the insurance company;
and extracting characters in the seal information to determine the insurance company.
4. The method for extracting the key information of the vehicle insurance policy according to claim 2, wherein the step of determining the insurance company corresponding to the vehicle insurance policy from the image of the vehicle insurance policy to be identified comprises the following steps:
determining insurance person information of the vehicle insurance policy from the image of the vehicle insurance policy to be identified, wherein the insurance person information comprises the name of the insurance company;
and extracting characters in the information of the insurer to determine the insurance company.
5. The method for extracting key information of the vehicle insurance policy according to claim 3, wherein obtaining seal information from the image of the vehicle insurance policy to be identified comprises:
determining a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified;
determining a seal area containing the seal information according to the form line;
and acquiring the seal information from the seal area.
6. The method for extracting key information of the vehicle insurance policy according to any one of claims 1 to 5, wherein extracting the key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position comprises:
determining a table line of the vehicle insurance policy in the image of the vehicle insurance policy to be identified;
cutting the insurance policy image to be identified according to the key position and the table line, and acquiring a cut text image, wherein the text image comprises the key information;
and extracting characters in the text image to acquire the key information.
7. The method for extracting the key information of the vehicle insurance policy according to claim 6, wherein the step of acquiring the image of the vehicle insurance policy to be identified comprises the following steps:
acquiring an original image for shooting the vehicle insurance policy;
determining the outline of the vehicle insurance policy in the original image;
and cutting the original image according to the outline of the vehicle insurance policy to obtain the image of the vehicle insurance policy to be identified.
8. A key information extraction device of a vehicle insurance policy, characterized by comprising:
the image acquisition module is used for acquiring an insurance policy image of the vehicle insurance to be identified;
the key position determining module is used for determining the key position of the to-be-identified vehicle insurance policy image;
and the key information extraction module is used for extracting the key information of the vehicle insurance policy in the image of the vehicle insurance policy to be identified according to the key position, wherein the key information is information capable of revealing the validity of the vehicle insurance policy.
9. A storage medium storing one or more programs executable by one or more processors to implement a critical information extraction method for a vehicle insurance policy according to any one of claims 1 to 7.
10. An electronic device comprising a memory for storing information comprising program instructions and a processor for controlling the execution of the program instructions, wherein the program instructions are loaded and executed by the processor to implement a critical information extraction method for a vehicle insurance policy according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003015.2A CN110942069A (en) | 2019-10-22 | 2019-10-22 | Method, device, storage medium and equipment for extracting key information of vehicle insurance policy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003015.2A CN110942069A (en) | 2019-10-22 | 2019-10-22 | Method, device, storage medium and equipment for extracting key information of vehicle insurance policy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110942069A true CN110942069A (en) | 2020-03-31 |
Family
ID=69906052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911003015.2A Pending CN110942069A (en) | 2019-10-22 | 2019-10-22 | Method, device, storage medium and equipment for extracting key information of vehicle insurance policy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110942069A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107688805A (en) * | 2017-07-25 | 2018-02-13 | 平安科技（深圳）有限公司 | The method, apparatus and relevant device positioned according to image file in single mode plate is recorded |
| CN107688772A (en) * | 2017-06-23 | 2018-02-13 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of policy information typing |
| CN107958201A (en) * | 2017-10-13 | 2018-04-24 | 上海眼控科技股份有限公司 | A kind of intelligent checking system and method for vehicle annual test insurance policy form |
| CN108132926A (en) * | 2018-02-05 | 2018-06-08 | 北京公共交通控股（集团）有限公司 | Contract generating means and system |
| CN109783781A (en) * | 2018-12-13 | 2019-05-21 | 中国平安财产保险股份有限公司 | Declaration form input method and relevant apparatus based on image recognition |
| CN109840469A (en) * | 2018-12-13 | 2019-06-04 | 中国平安财产保险股份有限公司 | Declaration form input method and relevant apparatus based on image recognition |
| CN109918984A (en) * | 2018-12-15 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Insurance policy number identification method, device, electronic equipment and storage medium |
| CN109918679A (en) * | 2019-03-22 | 2019-06-21 | 成都晟堃科技有限责任公司 | A method of parsing papery declaration form data |
-
2019
- 2019-10-22 CN CN201911003015.2A patent/CN110942069A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107688772A (en) * | 2017-06-23 | 2018-02-13 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of policy information typing |
| CN107688805A (en) * | 2017-07-25 | 2018-02-13 | 平安科技（深圳）有限公司 | The method, apparatus and relevant device positioned according to image file in single mode plate is recorded |
| WO2019019446A1 (en) * | 2017-07-25 | 2019-01-31 | 平安科技（深圳）有限公司 | Method and apparatus for performing locating in file input template according to image file, and related device |
| CN107958201A (en) * | 2017-10-13 | 2018-04-24 | 上海眼控科技股份有限公司 | A kind of intelligent checking system and method for vehicle annual test insurance policy form |
| CN108132926A (en) * | 2018-02-05 | 2018-06-08 | 北京公共交通控股（集团）有限公司 | Contract generating means and system |
| CN109783781A (en) * | 2018-12-13 | 2019-05-21 | 中国平安财产保险股份有限公司 | Declaration form input method and relevant apparatus based on image recognition |
| CN109840469A (en) * | 2018-12-13 | 2019-06-04 | 中国平安财产保险股份有限公司 | Declaration form input method and relevant apparatus based on image recognition |
| CN109918984A (en) * | 2018-12-15 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Insurance policy number identification method, device, electronic equipment and storage medium |
| CN109918679A (en) * | 2019-03-22 | 2019-06-21 | 成都晟堃科技有限责任公司 | A method of parsing papery declaration form data |
Non-Patent Citations (2)
| Title |
|---|
| 祁凯: "保险投保单的电子签名服务研究", 《电子商务》 * |
| 贾旸: "单证识别领域的OCR技术应用探索", 《金融电子化》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10657370B2 (en) | Determining images having unidentifiable license plates | |
| CN109614433B (en) | Method, device, equipment and storage medium for identifying data blooding margin between business systems | |
| US9679354B2 (en) | Duplicate check image resolution | |
| CN109740417B (en) | Invoice type identification method, invoice type identification device, storage medium and computer equipment | |
| CN111191568A (en) | Method, device, equipment and medium for identifying copied image | |
| CN113569863B (en) | Document checking method, system, electronic equipment and storage medium | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN111222409A (en) | Vehicle brand labeling method, device and system | |
| CN111353485A (en) | Seal identification method, device, equipment and medium | |
| CN115840964A (en) | Data processing method and device, electronic equipment and computer storage medium | |
| CN115631494A (en) | Financial data processing method, system, electronic device and storage medium | |
| CN111898555B (en) | Book checking identification method, device, equipment and system based on images and texts | |
| CN111611821B (en) | Two-dimensional code identification method and device, computer equipment and readable storage medium | |
| CN113051601B (en) | Sensitive data identification method, device, equipment and medium | |
| CN111178347B (en) | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image | |
| US11887292B1 (en) | Two-step anti-fraud vehicle insurance image collecting and quality testing method, system and device | |
| CN110942069A (en) | Method, device, storage medium and equipment for extracting key information of vehicle insurance policy | |
| CN113033562A (en) | Image processing method, device, equipment and storage medium | |
| CN115359302A (en) | Coin identification method, system and storage medium | |
| CN113657378B (en) | Vehicle tracking method, vehicle tracking system and computing device | |
| CN114090650A (en) | Sample data identification method and device, electronic equipment and storage medium | |
| CN108491843B (en) | Image processing method, device and storage medium | |
| CN114266267A (en) | Automatic identification method and device for collecting two-dimensional codes, documents, certificates and human faces and storage medium | |
| CN113239126A (en) | Business activity information standardization scheme based on BOR method | |
| CN112862409A (en) | Picking bill verification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200331 |