CN109840469B

CN109840469B - Image recognition-based policy entry method and related device

Info

Publication number: CN109840469B
Application number: CN201811530442.1A
Authority: CN
Inventors: 罗柏发
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2018-12-13
Filing date: 2018-12-13
Publication date: 2023-10-24
Anticipated expiration: 2038-12-13
Also published as: CN109840469A

Abstract

The invention provides a policy entry method and a related device based on image recognition, wherein the method comprises the following steps: receiving a target policy in a picture format sent by an image acquisition terminal; image recognition is carried out on the target policy to obtain policy information corresponding to the target policy; determining a plurality of first information options corresponding to the target policy item according to the policy information and the target policy item; the method comprises the steps that a plurality of first information options are sent to an image acquisition terminal, so that the image acquisition terminal displays the plurality of first information options for a policy entry user when the policy entry user performs entry on a target policy item; receiving policy item information returned by the image acquisition terminal aiming at a target policy item, wherein the policy item information is associated with at least one information option in a plurality of first information options; and recording the information of the policy project as information corresponding to the target policy project into a policy information storage system, wherein the policy information storage system is used for storing the policy information. The technical scheme can improve the efficiency of policy entry.

Description

Image recognition-based policy entry method and related device

Technical Field

The invention relates to the technical field of computers, in particular to a policy entry method based on image recognition and a related device.

Background

The policy is short for insurance policy, which refers to written proof of insurance contract between insurer and applicant, and the policy clearly and completely records the rights and obligations of both parties, and includes the names of insured persons, the names of insurance targets and their storage places or states, insurance amount, insurance period, insurance fee, etc. both parties account for the matters related to insurance targets, and may also include other conditions agreed by insurance terms or both parties, and additional conditions such as policy change, transfer and cancellation.

After determining the policy signed by the insurance broker with the applicant, the insurance broker can enter the information in the policy through the electronic system for archiving, in the current mode, after filling the policy of the paper document, the insurance broker or the policy entry personnel needs to manually enter the information in the policy on the policy entry system, so that the problem is that: the efficiency of the entry is low.

Disclosure of Invention

The embodiment of the invention provides a policy entry method based on image recognition and a related device, which solve the problem of low entry efficiency of a manual policy entry mode.

In a first aspect, a policy entry method based on image recognition is provided, including:

Receiving a target policy sent by an image acquisition terminal, wherein the target policy is a policy in a picture format;

performing image recognition on the target policy to obtain policy information corresponding to the target policy;

determining a plurality of first information options corresponding to a target policy item according to the policy information and the target policy item, wherein the target policy item is a policy item to be input;

the plurality of first information options are sent to the image acquisition terminal, so that the image acquisition terminal displays the plurality of first information options for a policy entry user when the policy entry user performs entry on the target policy item;

receiving policy item information returned by the image acquisition terminal for the target policy item, wherein the policy item information is associated with at least one information option in the plurality of first information options;

and inputting the information of the policy item as information corresponding to the target policy item into a policy information storage system, wherein the policy information storage system is used for storing the policy information.

In the embodiment of the invention, the policy information in the policy is obtained by identifying the policy in the picture format, then a plurality of information options are generated for the policy items to be input, and the information options are displayed to the policy input user through the image acquisition terminal, so that the user can directly select the information options or slightly modify the information options, the input of the information corresponding to the policy items to be input can be completed, the process of manually inputting the policy item information by the user is omitted, and the policy input efficiency is improved.

With reference to the first aspect, in one possible implementation manner, the determining, according to the policy information and the target policy item, a plurality of first information options corresponding to the target policy item includes: generating a plurality of information options according to the policy information; ordering the information options according to the target policy items to obtain the sequence of each information option; and determining a plurality of first information options corresponding to the target policy item according to the sequence of the information options. By splitting the policy information into a plurality of information options and sorting the information options according to the target policy items, the association relationship between the information options and the target policy items can be determined, so that the information options corresponding to the target policy items can be determined.

With reference to the first aspect, in one possible implementation manner, the generating a plurality of information options according to the policy information includes: comparing the policy information with preset policy template information, and determining a first character and a second character, wherein the first character is a character which is different from the policy template information in the policy information, and the second character is a character which is the same as the policy template information in the policy information; and generating a plurality of information options according to the first character, wherein the information options do not contain the second character. Because the preset policy template information is inherent information in the policy, the content of the target policy, which is more than the blank policy, can be determined by comparing the policy information with the preset policy template information, and then the target policy can be split into a plurality of information options according to the content.

With reference to the first aspect, in a possible implementation manner, the generating a plurality of information options according to the first character includes: determining a third character and a first equivalent character corresponding to the third character in the first character, and searching a fourth character in the first character, wherein the first equivalent character and the third character correspond to the same position in the target policy, the fourth character is a character in which no second character exists between the policy information and the third character or between the fourth character and the first equivalent character, and the fourth character and the third character correspond to different positions in the target policy; under the condition that the fourth character is found, determining a second equivalent character corresponding to the fourth character in the first character, and generating a plurality of information options according to a first target character and a second target character, wherein the second equivalent character and the fourth character correspond to the same position in the target policy, the first target character is the third character or the first equivalent character, and the second target character is the fourth character or the second equivalent character; and generating a plurality of information options according to the first target character under the condition that the fourth character is not found. The policy information may be split by looking up consecutive characters in the policy information in the first character to generate a plurality of information options.

With reference to the first aspect, in a possible implementation manner, the generating a plurality of information options according to the first character includes: determining a third character in the first characters, and determining at least one fifth character according to the third character, wherein the similarity between the character form of the fifth character and the character form of the third character is larger than a first similarity threshold; searching a fourth character in the first character, wherein the fourth character is a character in which the second character does not exist between the third character and the policy information; under the condition that the fourth character is found, determining at least one sixth character according to the fourth character, and generating a plurality of information options according to a third target character and a fourth target character, wherein the similarity between the character form of the sixth character and the character form of the fourth character is larger than the first similarity threshold, the third target character is the third character or the fifth character, and the fourth target character is the fourth character or the sixth character; and generating a plurality of information options according to the third target character under the condition that the fourth character is not found. By searching for the continuous characters and characters similar to the form thereof in the first character, a plurality of information options can be generated.

With reference to the first aspect, in one possible implementation manner, the performing image recognition on the target policy to obtain policy information corresponding to the target policy includes: performing image preprocessing on the target policy to obtain a text image area of the target policy; image segmentation is carried out on the text image area of the target policy, so that a plurality of characters to be identified corresponding to the target policy are obtained; and respectively identifying each character to be identified in the plurality of characters to be identified to obtain the policy information corresponding to the target policy. The extraction and recognition of the policy information in the target policy can be realized by carrying out image preprocessing, image segmentation and character recognition on the target policy in the picture format.

With reference to the first aspect, in one possible implementation manner, the identifying each character to be identified in the plurality of characters to be identified to obtain policy information corresponding to the target policy includes: comparing each character to be recognized in the plurality of characters to be recognized with a preset character template respectively to determine one or more target character templates corresponding to the characters to be recognized respectively, wherein the target character templates are character templates with similarity to the characters to be recognized higher than a second similarity threshold; and determining the characters corresponding to one or more target character templates corresponding to the characters to be identified as policy information corresponding to the target policy. By matching the segmented characters with a pre-character template, the specific character to be recognized can be determined, and the realization is simple.

In a second aspect, there is provided an image recognition-based policy entry device, including:

the policy receiving module is used for receiving a target policy sent by the image acquisition terminal, wherein the target policy is in a picture format;

the image recognition module is used for carrying out image recognition on the target policy to obtain policy information corresponding to the target policy;

the option generation module is used for determining a plurality of first information options corresponding to a target policy item according to the policy information and the target policy item, wherein the target policy item is the policy item to be input;

the option sending module is used for sending the plurality of first information options to the image acquisition terminal so that the image acquisition terminal displays the plurality of first information options for the policy entry user when the policy entry user registers the target policy item;

the information receiving module is used for receiving the policy project information returned by the image acquisition terminal aiming at the target policy project, wherein the policy project information is associated with at least one information option in the plurality of first information options;

the information input module is used for inputting the information of the policy project as the information corresponding to the target policy project to a policy information storage system, and the policy information storage system is used for storing the policy information.

In a third aspect, there is provided another image recognition-based policy entry device comprising a processor, a memory and a communication interface, the processor, memory and communication interface being interconnected, wherein the communication interface is for transmitting or receiving data, the memory is for storing application code for performing the above method by the image recognition-based policy entry device, and the processor is configured for performing the method of the above first aspect.

In a fourth aspect, there is provided a computer storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of the first aspect described above.

In the embodiment of the invention, the information options are formed by identifying and processing the policy in the picture format for the policy to be input by a user to select, so that the process of manually inputting the policy project information by the user is omitted, and the efficiency of entering the policy is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic structural diagram of a policy entry system according to an embodiment of the present invention;

FIG. 2 is a schematic view of a scenario provided by an embodiment of the present invention;

fig. 3 is a schematic flow chart of a policy entry method based on image recognition according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a policy according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of policy segmentation according to an embodiment of the present invention;

fig. 6 is a schematic flow chart of determining, by the policy entry server according to the policy information and the target policy item, a plurality of first information options corresponding to the target policy according to the embodiment of the present invention;

FIG. 7 is a schematic flow chart of recording information of a policy item as information corresponding to a target policy item into a policy information storage system according to an embodiment of the present invention;

fig. 8 is a schematic diagram of a composition structure of a policy entry device based on image recognition according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a composition structure of another policy entry device based on image recognition according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a policy entry system according to an embodiment of the present invention, where the policy entry system includes one or more image capturing terminals 101 and one or more policy entry servers 102. The image acquisition terminal 101 may be used to acquire a policy in a picture format, and then submit the acquired policy in the picture format to the policy entry server 102; the image acquisition terminal 102 may also be used for user interaction, obtaining the operation of the policy entry user on the policy entry system, responding to user operation, and so on. The image acquisition terminal 101 may be, for example, a mobile phone, a computer, a tablet computer, etc. The image acquisition terminal 101 may be a user terminal held by a service person of the insurance institution, the service person of the insurance institution may log in the policy entry system supported by the policy entry server 102 in the background through the image acquisition terminal 101, and then complete entry of the policy through the image acquisition terminal 101. The policy entry server 102 is configured to identify a policy in a picture format according to the policy in the picture format submitted by the image acquisition terminal 101, so as to obtain information in the policy. Policy entry server 102 may be a server of an insurance agency. In the case where there are a plurality of policy entry servers 102, the plurality of policy entry servers 102 constitute a policy entry server group. In some embodiments, multiple policy entry servers in the policy entry server group may cooperate to complete entry of a policy, and each policy entry server may be used to complete a different operation. For example, a first policy entry server in the policy entry server group may be configured to interact with the image acquisition terminal 101, receive requests or data sent by the image acquisition terminal, and send requests or data to the image acquisition terminal; the second policy entry server in the policy entry server group can be used for identifying the policy in the picture format to obtain the information corresponding to the policy; a third policy entry server in the policy entry server group may be configured to store policy information; etc.; in other embodiments, the plurality of policy entry servers in the policy entry server group may also have the same function, so as to complete the same operation, that is, each policy entry server in the policy entry server group may be used to interact with the image acquisition terminal, identify a policy in a picture format, store policy information, and so on. The embodiments of the present invention are not limited.

In some possible implementations, the policy entry server group may be a blockchain system. The blockchain system may be, for example, a federated chain system, a private chain system, or the like. In the case where the policy entry server group is a federation chain system, each policy entry server 102 is a node in the federation chain system, which may specifically be one or more of a peer node (peer), an endorsement node (endorser), an order node (orderer), or a confirmation node (commit) of the federation chain system. Each policy entry server 102 may be referred to as an peer node, where the peer node is configured to obtain a block formed by packaging command nodes from the command nodes and store the block in a local account book; the command node is used for maintaining a plurality of alliance chains in the alliance chain system, receiving transaction messages subjected to an endorsement policy, ordering the transactions, packaging the ordered transactions to form blocks, and then transmitting the blocks to all the equivalent nodes in the alliance chains; the endorsement node and the confirmation node are two special nodes in the peer node, the endorsement node is used for endorsing the transaction in the process that the peer node issues the transaction to the alliance chain system, and the confirmation node is used for storing the block corresponding to the transaction subjected to endorsement and ordering to the local in the process that the peer node issues the transaction to the alliance chain system.

Based on the policy entry system shown in fig. 1, the scheme of the embodiment of the present invention can be implemented, and a specific application scenario and a technical scheme of the embodiment of the present invention are described next.

Referring to fig. 2, fig. 2 schematically illustrates a scenario in which a policy entry user enters policy information through a policy entry system. Firstly, a policy entry user logs in a policy entry system on an image acquisition terminal, and after successful login, selects to enter a home page of the policy entry system corresponding to a policy to be entered, as shown in (1) in fig. 2; then, the policy entry user clicks a policy entry button on the first page of the policy entry system and enters a policy uploading page of the policy entry system, as shown in (2) in fig. 2; then, uploading a picture format policy by the policy entry user through the image acquisition terminal, entering a policy entry page of a policy entry system, wherein the policy entry page is provided with one or more policy items to be entered, as shown in (3) in fig. 2; then, the image acquisition terminal sends the policy in the picture format to a policy entry server, the policy entry server processes the policy according to the policy item to be entered, generates a plurality of information options for the policy item to be entered, then sends the plurality of information options corresponding to the policy item to be entered to the image acquisition terminal, and the image acquisition terminal displays the plurality of information options corresponding to the policy item to the user when the user enters the policy item, as shown in (4) in fig. 2; finally, the user selects one of the information options, the image acquisition terminal sends the information option selected by the user to the policy entry server, and the policy entry server enters the information which is determined to correspond to the policy item into the policy storage system, as shown in (5) in fig. 2. Optionally, in stage (5) in fig. 2, after the user selects one of the information options, the user may modify the information option, and the image acquisition terminal may further send the policy item information obtained by modifying the selected information option to the policy entry server, and then the policy server determines that the policy entry server is the information corresponding to the policy item to be entered into the policy storage system.

As can be seen from fig. 2, for the policy item to be entered, the policy entry user only needs to select one of the information options provided by the policy entry system or make a small amount of modification to the one of the information options, so that the policy information entry is completed, the operation is simple, and the policy entry efficiency and the user experience are improved.

The following describes a technical scheme for implementing the above scenario.

Referring to fig. 3, fig. 3 is a schematic flow chart of a policy entry method based on image recognition, which is provided by the embodiment of the present invention, and the method may be implemented on the policy entry server or the policy entry server group shown in fig. 1, and is described below with the policy entry server as an execution subject. As shown, the method comprises the steps of:

s301, the policy entry server receives a target policy sent by the image acquisition terminal, wherein the target policy is in a picture format.

Here, the target policy is a policy to be entered. Specifically, the target policy may include policy information for feeding back the nature of the target policy, such as a policy name, an insurance company to which the policy belongs, a policy number, and the like. For example, the target policy is a car insurance policy of a security insurance company. The target policy may also include a name of the insured person, an identity card number of the insured person (organization code), an address of the insured person, a contact phone of the insured person, a name of the insured person, an identity card number of the insured person, an address of the insured person, a contact phone of the insured person, a start time of the insurance, a deadline of the insurance, a name of the insured person, an identity card number of the insured person, and other policy items that are not related to the user and that require corresponding information to be entered into the policy information storage system. The target policy may also include policy item information related to the user, such as insured name information, insured identification number (organization code) information, insured address information, insured contact phone information, insured name information, insured identification number information, insured address information, insured contact phone information, insurance start time information, insurance expiration time information, insured name information, insured identification number information, and the like. The target policy may also include notice, special prompt, etc. conditional instruction information, not limited to the description herein, and in alternative embodiments, the target policy may have fewer or more information, which is not limited by the embodiments of the present invention. For example, the target policy may be as shown in fig. 4, and fig. 4 is a policy with an insurance type of car insurance.

Specifically, when the policy entry user logs in the policy entry system through the image acquisition terminal and uploads the target policy locally stored by the image acquisition terminal or acquired by the image acquisition terminal to the policy entry system, the policy entry server can receive the target policy sent by the image acquisition terminal.

S302, the policy entry server performs image recognition on the target policy to obtain policy information corresponding to the target policy.

In the embodiment of the invention, the policy entry server can perform image recognition on the target policy through three processes of image preprocessing, image segmentation and character recognition to obtain the policy information corresponding to the target policy. The following describes the specific procedure:

step one, the policy entry server performs image preprocessing on a target policy to obtain a text image area of the target policy.

Specifically, the policy entry server may input the target policy into a pre-designed text region recognition model. The text region recognition model may be a connected-domain-based text region recognition model, or a sliding-window-based text region recognition model, or a deep-learning-based text region recognition model. The text region identification model extracts the target policy by a method based on connected domains, a method based on sliding windows or a method based on deep learning to obtain one or more text image regions corresponding to the target policy. Optionally, the text region identification model may further number one or more text image regions corresponding to the target policy according to the positions of the one or more text image regions corresponding to the target policy in the target policy, to obtain the region numbers of the text image regions. Then, the text region recognition model outputs one or more text image regions corresponding to the target policy, and region numbers of the respective text image regions, respectively.

For example, as shown in fig. 4, after the target policy is input into the text region recognition model, the output of the text region recognition model may be as shown in fig. 5, which marks 18 text image regions, and the region numbers corresponding to the 18 text image regions are 1 to 18, respectively.

Optionally, in order to improve accuracy of text recognition, the text region recognition model may further enhance text image information in each text image region corresponding to the target policy before outputting one or more text image regions corresponding to the target policy, so as to remove noise such as stain and blank in each text image region. And removing some non-essential signals according to a certain rule, and normalizing the size, position, stroke weight and the like of the characters in the text image area so as to reduce the complexity during recognition.

And secondly, respectively carrying out image segmentation on the text image area corresponding to the target policy by the policy entry server to obtain a plurality of characters to be identified corresponding to the target policy.

Specifically, the policy entry server may respectively perform line segmentation on the text image area of the target policy by using a horizontal projection method, so as to obtain a line text image area of the target policy. In the line cutting projection diagram, the region corresponding to the black pixel is the line text region. Optionally, the policy entry server may number the line text image areas corresponding to the text image areas according to the numbers of the text image areas corresponding to the target policy, so as to determine the numbers of the line text image areas corresponding to the target policy. Wherein, the text image areas with smaller numbers correspond to the text image areas with smaller numbers.

Then, the policy entry server may perform character segmentation on each line of the text image area of the target policy by using a vertical projection method, to obtain a plurality of character images. In the vertical cutting projection diagram, the area corresponding to the black pixel is the character image. The policy entry server further performs merging or cutting processing on the plurality of character images to determine a plurality of characters to be recognized corresponding to each line of text image area. Let N character images be obtained by character segmentation of the line text image area, each character image having a width w (i), i= [0, N-1]. Taking the average value L of the widths of the characters in the line text image area as the standard character width of the line text image area, merging the character images corresponding to w (i) and w (i+1) into one character image if w (i) is smaller than L1 and w (i+1) is smaller than L1 and L1=2L/3, dividing the character image corresponding to w (i) if w (i) is larger than L2 and L2=4L/3, searching a non-connected channel in the vertical direction in the character image range corresponding to the widths 2L/3 to 4L/3 of the character image, taking the channel as a dividing line, and taking the line with the minimum intersection point of w (i) in the range as the character dividing line if no non-connected channel exists. Optionally, the policy entry server may number the to-be-identified characters corresponding to each text image area according to the numbers of each line of text image areas corresponding to the target policy, so as to determine the numbers of the to-be-identified characters corresponding to the target policy. The line text image area with smaller number corresponds to the character to be recognized with smaller number.

And thirdly, the policy entry server respectively identifies a plurality of characters to be identified corresponding to the target policy to obtain policy information corresponding to the target policy.

Specifically, the policy entry server may respectively match a plurality of characters to be identified corresponding to the target policy with a preset character template, where the matching manner is specifically to determine one or more target character templates corresponding to each character to be identified by respectively comparing the morphology of the character to be identified (such as an upper structure, a lower structure, a radical of the character, an endpoint, an intersection point, a folding point, etc. of the character line) with the morphology of the preset character template, where the similarity between the target character template and the character to be identified is higher than a second similarity threshold. And then, the policy entry server determines the characters corresponding to one or more target character templates corresponding to the characters to be recognized as policy information corresponding to the target policy.

Here, the second similarity threshold may be a value close to 1 of 90%, 95%, 98%, or the like. The recognition of a character to be recognized is described below by way of example.

For example, four target character templates are obtained by matching a character to be recognized with a preset character template, namely a character template 1, a character template 2, a character template 3 and a character template 4, wherein the characters corresponding to the character template 1 are the condition, the characters corresponding to the character template 2 are the condition, the characters corresponding to the character template 3 are the request, and the characters corresponding to the character template 4 are clear, the condition, the request and the clear are determined as the characters corresponding to the character to be recognized, and the condition, the request and the clear are determined as the policy information corresponding to the target policy.

S303, the policy entry server determines a plurality of first information options corresponding to the target policy item according to the policy information corresponding to the target policy and the target policy item, wherein the target policy item is the policy item to be entered.

The specific implementation of step S303 may be referred to the following embodiment corresponding to fig. 6, and will not be described here too much.

S304, the policy entry server sends a plurality of first information options corresponding to the target policy item to the image acquisition terminal, so that the image acquisition terminal displays the plurality of first information options corresponding to the target policy item to the policy entry user when the policy entry user enters the target policy item.

Specifically, when the policy entry user performs entry on the target policy item, the image acquisition terminal may display a plurality of first information options corresponding to the target policy item to the policy entry user in a manner of a drop-down list, a floating manner of a floating window, and the like. Illustratively, the image capturing terminal may display the plurality of first information options corresponding to the target policy item to the policy entry user as shown in (4) of fig. 2.

S305, the policy entry server receives policy item information returned by the image acquisition terminal for the target policy item, wherein the policy item information is associated with at least one information option in the plurality of first information options.

The policy project information may be one of the information options in the plurality of first options, and the policy project information may also be information obtained by modifying the one of the information options by the user. The specific case where the policy entry server receives the policy item information returned by the image capturing terminal for the target policy item may be as shown in (5) of fig. 2.

S306, the policy entry server enters the policy item information as information corresponding to the target policy item into a policy information storage system, wherein the policy information storage system is used for storing the policy information.

Here, the policy information storage system may have two cases:

in the first case, the policy information storage system is a distributed storage system formed by one or more policy entry servers.

In the second case, the policy information storage system is a blockchain system composed of one or more policy entry servers.

In the first case, after the policy entry server stores the policy item information as information corresponding to the target policy item locally, the policy item information may be backed up as information corresponding to the target policy item to other policy entry servers.

In the second case, the specific implementation manner in which the policy entry server issues the policy item information as the information corresponding to the target policy item to the blockchain system for storage, and the policy entry server issues the policy item information as the information corresponding to the target policy item to the blockchain system for storage may refer to the description of the embodiment corresponding to fig. 7, which will not be described in detail herein.

In the embodiment of the invention, the policy entry server obtains the policy information in the policy by identifying the policy in the picture format, then generates a plurality of information options for the policy items to be entered and displays the information options to the policy entry user through the image acquisition terminal, so that the user can directly select the information options or slightly modify the information options, the entry of the information corresponding to the policy items to be entered can be completed, the process of manually inputting the policy item information by the user is omitted, and the policy entry efficiency is improved.

Referring to fig. 6, fig. 6 is a schematic flow chart of determining, by a policy entry server according to policy information and a target policy item, a plurality of first information options corresponding to the target policy according to an embodiment of the present invention, where as shown in the fig. 6, the flow chart includes the following steps:

s601, the policy entry server generates a plurality of information options according to the policy information corresponding to the target policy.

In one possible implementation manner, the policy entry server may compare the policy information corresponding to the target policy with preset policy template information, and determine a first character and a second character, where the first character is a character in the policy information different from the policy template information, and the second character is a character in the policy information identical to the policy template information; then, the policy entry server generates a plurality of information options from the first character, the information options not including the second character.

Here, the preset policy template information is information inherent in the target policy. For example, the format of the target policy is shown in fig. 4, and the preset policy template information may be information such as "insured person", "insured vehicle", etc. in fig. 4, which does not need to manually fill in the information already existing in the policy.

And according to the difference of the number of characters corresponding to the same character to be recognized in the policy information obtained by recognizing the target policy by the policy entry server, the policy entry server generates a plurality of information options according to the first character.

Case one: in the third step of the step S302, the number of the target character templates corresponding to the respective characters to be recognized is determined to be one in the process that the policy entry server matches the plurality of characters to be recognized corresponding to the target policy with the preset character templates, respectively.

The policy entry server may generate a plurality of information options from the first character in two ways:

the method comprises the steps that (1) a policy entry server determines a third character in first characters and searches a fourth character in the first characters, wherein the fourth character is a character in which no second character exists between the policy information and the third character; under the condition that the fourth character is found, the policy entry server generates an information option according to the third character and the fourth character; and under the condition that the fourth character is not found, the policy entry server generates an information option according to the third character.

For example, the preset policy template information includes "name of applicant", "sex of applicant", "age of applicant", the policy information is "name of applicant XX applicant sex female applicant age 50", and since "name of applicant" is identical to "name of applicant" of policy template information "the" sex of applicant "is identical to" sex of applicant "of policy template information" the "age of applicant" is identical to "age of applicant" of policy template information, the "king XX woman 50" in policy information is determined as the first character, and the "name of applicant, sex of applicant and age of applicant" in policy information is determined as the second character. Because the first character 'X', the character 'X' and the first character 'king' do not exist in the policy information, and the second character 'applicant name' exists between the first character 'X' and the first character 'girl', the information option 'king XX' is generated according to the first character 'king', 'X'; because the second character 'applicant age' exists between the first character 'girl' and the first character '5' in the policy information, the characters which do not exist between the first character 'girl' and the second character 'girl' cannot be found, and information options are generated according to the first character 'girl'; since there is no second character between the first character "5" and the first character "0" in the policy information, the information option "50" is generated from the first character "5" and the second character "0". The information options may be determined to be "king XX", "female", and "50".

The policy entry server determines a third character in the first characters and determines at least one fifth character according to the third character, wherein the similarity between the character form of the fifth character and the character form of the third character is larger than a first similarity threshold; the policy entry server searches a fourth character in the first character, wherein the fourth character is a character in which no second character exists between the policy information and the third character; under the condition that the fourth character is found, the policy entry server determines at least one sixth character according to the fourth character, and generates a plurality of information options according to a third target character and the fourth target character, wherein the similarity between the character form of the sixth character and the character form of the fourth character is larger than a first similarity threshold value, the third target character is a third character or a fifth character, and the fourth target character is a fourth character or a sixth character.

Specifically, the first similarity threshold may specifically be a value close to 1 of 90%, 96%, or the like.

For example, the first similarity threshold is 90%, the preset policy template information includes "name of the applicant", "sex of the applicant", and "age of the applicant", the policy information is "name of the applicant colludes as" name of the applicant "and" age of the applicant "30", and since "name of the applicant" is identical to "name of the applicant" of the policy template information in the policy information, "sex of the applicant" is identical to "sex of the applicant" of the policy template information, "age of the applicant" is identical to "age of the applicant" of the policy template information, the "collude as" 30 "in the policy information is determined as the first character. Since the second character does not exist between the first character hook and the first character guard, and the second character does not exist between the first character guard and the first character like, the first character hook is determined to be a third character, and the fourth character guard and the fourth character like are determined to be a fourth character; then determining one or more fifth characters with a character morphology similarity of more than 90% with the third character "hook", assuming that one is determined, the fifth characters are for example "sentences", then determining one or more sixth characters with a character morphology similarity of more than 90% with the fourth character "Jing", assuming that one is determined, the sixth characters are for example "Jing"; then, determining one or more sixth characters with character morphology of the fourth character 'e.g. "greater than 90%, and assuming that one character is determined and the sixth character is' girl ', generating a plurality of information options according to the characters as' girl 'and' sentence 'e.g', 'girl' and 'girl' respectively. Since the first character "such as" the name of the applicant "is between the first character" woman "and" the first character "woman", and "the age of the applicant" is between the first character "woman" and "the first character" 3", the first character" woman "is determined as the third character, then one or more fifth characters having a character morphology similarity of more than 90% with the third character" woman "are determined, and assuming that one is determined, the fifth character is, for example," Ru ", a plurality of information options generated from these several characters are" woman "and" Ru ". Since there is no second character between the first character "3" and the first character "0", the first character "3" and the fourth character "0" are determined to be the third character and the fourth character, respectively, then one or more fifth characters having a character morphology similarity of more than 90% with the third character "3" are determined, one is assumed to be determined, the fifth character is for example "2", then one or more sixth characters having a character morphology similarity of more than 90% with the fourth character "0" are determined, one is assumed to be determined, and a plurality of information options generated from these several characters are for example "30", "38", "20", "28". In summary, the generated plurality of information options are "reference to a layer", "sentence reference to a layer", "sentence pattern to a layer", "girl" and "Ru", "30", "38", "20", "28".

And a second case: in the third step of the step S302, the number of the target character templates corresponding to the respective characters to be recognized is determined to be plural in the process that the policy entry server matches the plural characters to be recognized corresponding to the target policy with the preset character templates, respectively.

The policy entry server generates a plurality of information options according to the first character specifically as follows: the policy entry server determines a third character and a first equivalent character corresponding to the third character in the first character, searches a fourth character in the first character, wherein the first equivalent character and the third character correspond to the same position in the target policy, the fourth character is a character which does not have a second character between the third character or the first equivalent character in the policy information corresponding to the target policy, and the fourth character and the third character correspond to different positions in the target policy; under the condition that the fourth character is found, the policy entry server determines a second equivalent character corresponding to the fourth character in the first character, and generates a plurality of information options according to the first target character and the second target character, wherein the first target character is a third character or a first equivalent character, and the second target character is a fourth character or a second equivalent character; and under the condition that the fourth character is not found, the policy entry server generates a plurality of information options according to the first target character.

For example, the preset policy template information includes "name of applicant", "sex of applicant", "age of applicant", and the policy information is "name of applicant colludes sentence and pattern, such as girl's age 3208". Since the "applicant name" and the "applicant name" in the policy information are the same as the "policy template information," applicant sex "and the" applicant sex "of the policy template information," applicant age "and the" applicant age "of the policy template information are the same, it is determined that the" colluded Jing "in the policy information is the first character, such as girl Ru 3208". Since the first character 'hook' corresponds to the same character to be recognized with the first character 'sentence', the first character 'hook' corresponds to the same position in the target policy with the first character 'sentence', and the first character 'sentence' is the equivalent character of the first character 'hook'. Since the first character 'Jing' and the first character 'Jing' correspond to the same character to be recognized, the first character 'Jing' and the first character 'Jing' correspond to the same position in the target policy, and the first character 'Jing' is the equivalent character of the first character 'Jing'. Since the first character "e.g." corresponds to the same character to be recognized as the first character "Gu", the first character "e.g." corresponds to the first character "Gu" in the same position in the target policy, and the first character "Gu" is the equivalent character of the first character "e.g.". Since the first character "girl" corresponds to the same character to be recognized as the first character "Ru", the first character "girl" corresponds to the same position in the target policy as the first character "Ru", and the first character "Ru" is the equivalent character of the first character "girl". Since the first character "3" corresponds to the same character to be recognized as the first character "2", the first character "3" corresponds to the first character "2" at the same position in the target policy, and the first character "2" is the equivalent character of the first character "3". Since the first character "0" corresponds to the same character to be recognized as the first character "8", the first character "0" corresponds to the same position in the target policy as the first character "8", and the first character "8" is the equivalent character of the first character "0".

Since there is no second character between the first character "collude", the first character "tie" and the first character "like girl", the first character "collude" may be regarded as the first target character, the first character "tie" and the first character "like girl" may be regarded as the second target character, and the plurality of information options generated according to the several characters are "tie" such as "tie", "sentence pattern" such as "," tie "such as", "sentence pattern" such as "," tie girl "," sentence tie "such as", "tie girl", "sentence pattern" and "sentence pattern" such as "tie" and "sentence pattern" as "girl". Since the second character exists between the first character 'girl' and the first character 'girl', and the second character exists between the first character 'girl' and the first character '3', the first character 'girl' is determined as the first target character, and since the second target character does not exist, a plurality of information options generated according to the first target character 'girl' are 'girl' and 'Ru'. Since there is a second character between the first character "girl" and the first character "girl", there is a second character between the first character "Ru" and the first character "3", there is no second character between the first character "32" and the first character "08", the first character "32" is a first target character, the second character "08" is a second target character, and then a plurality of information options generated according to the several characters are "30", "38", "20", "28". In summary, the generated plurality of information options are "reference to a layer", "sentence reference to a layer", "sentence pattern to a layer", "girl" and "Ru", "30", "38", "20", "28".

S602, the policy entry server sorts the information options according to the target policy items to obtain the sequence of each information option.

In the embodiment of the invention, the order of ordering the plurality of information options according to the target policy items by the policy entry server to obtain each information option can be in the following two modes:

in the first mode, the policy entry server sorts the plurality of information options according to character distances between the information options and the target policy items in the policy information corresponding to the target policy. The policy entry server may rank the information items with smaller character distances from the target policy item in the policy information in a preceding order, and rank the information items with larger character distances from the target policy item in the policy information in a following order. Here, the character distance of the information item from the target policy item refers to the number of characters separated from the information item from the target policy item in the target information.

For example, the policy information is "the applicant name king XX applicant's sex female applicant's age 50 applicant's mobile phone number 135XXXXXX is the applicant's name plum YY", the target item is the applicant's mobile phone number, the plurality of information options are "king XX", "female", "50", "135XXXXXXXX" and "plum YY", respectively, then the character distance of the information option "king XX" from the applicant's mobile phone number is 15, the character distance of the information option "female" from the applicant's mobile phone number is 6, the character distance of the information option "50" from the applicant's mobile phone number is 0, the character distance of the information option "135XXXXXXXX" from the applicant's mobile phone number is 0, and the character distance of the information option "plum YY" from the applicant's mobile phone number is 7; then the information options are ordered to be "135 xxxxx", "50", "female", "plum YY", "king XX", and the order of the information options "135 xxxxx" is determined to be 1, the order of the information options "50" is determined to be 2, the order of the information options "female" is determined to be 3, the order of the information options "plum YY" is determined to be 4, and the order of the information options "king XX" is determined to be 5.

It should be noted that, if the information options are generated by the (second) method in the first case in the above step S601, in the information options, the distances between the two corresponding information options corresponding to the two characters having the similarity of the character form greater than the first similarity threshold are the same. For example, the character distance of the information option "Ru" and the character distance of the information option "woman" are 6, and the character distance of the information option "Ru" is 6. If the information items are generated by the second method in step S602, the character distances corresponding to the plurality of information items corresponding to the same position in the policy are the same among the information items. For example, if the character distance of the information option "girl" is 6 at the same position in the target policy corresponding to the information option "girl", the character distance of the information option "Ru" is also 6.

In the second mode, the policy entry server determines the association degree of the information options and the target policy item according to a preset rule, and sorts the plurality of information options according to the association degree of each information option and the target policy item. The policy entry server ranks the information options with higher association with the target policy items in a front order and ranks the information options with lower association with the target policy items in a rear order.

For example, the items to be entered are the applicant mobile phone numbers, the plurality of information options are "king XX", "female", "50", "135 xxxxx" and "plum YY", "king XX" and the applicant mobile phone numbers are quantized to a value of 2 "," female "and the applicant mobile phone numbers are quantized to a value of 4", "50" and the applicant mobile phone numbers are quantized to a value of 8 "," 135xxxxxxx "and the applicant mobile phone numbers are quantized to a value of 10", and "plum YY" and the applicant mobile phone numbers are quantized to a value of 2, and the information options are ordered to a value of "135 xxxxxxx", "50", "female", "plum YY", "king XX".

It should be noted that, if the information options are generated by the (second) method in the first case in the above step S601, the association degrees corresponding to the two information options corresponding to the two characters having the similarity of the character form greater than the first similarity threshold are the same. For example, the information option "Ru" and the information option "woman" respectively correspond to the characters "Ru" and "woman", and the association degree of the information option "woman" is 4, so that the association degree of the information option "Ru" is also 4. If the information items are generated by the second method in step S602, the association degrees of the information items corresponding to the plurality of information items at the same position in the policy are the same among the information items. For example, if the association degree of the information option "girl" is 4 at the same position in the target policy corresponding to the information option "girl", the association degree of the information option "Ru" is also 4.

The method is not limited to the two modes, in alternative embodiments, there may be other ways to sort the plurality of information options to obtain the sequence of each information option, and embodiments of the present invention are not limited.

S603, the policy entry server determines a plurality of first information options corresponding to the target policy item according to the sequence of the information options.

Specifically, the policy entry server may determine, according to the order of the information options, the information option ranked in the first N digits as the first information option corresponding to the target policy item, where N is a positive integer greater than or equal to 1.

For example, the target policy item is the mobile phone number of the applicant, the ordered information options are sequentially "135 xxxxxxx", "50", "female", "plum YY", "king XX", and N is equal to 3, and then the information options "135XXXXXXXX", "50", "female" are determined as the first information option corresponding to the mobile phone number of the applicant.

In the embodiment of the invention, the information of the policy is split into a plurality of information options and the information options are ordered according to the target policy items, so that the association relationship between the information options and the target policy items can be determined, and the information options corresponding to the target policy items can be determined.

In some possible scenarios, the policy information storage system related to the embodiment corresponding to fig. 3 may be a blockchain system, which may be a private chain system or a federation system. The specific process of inputting the information of the policy item as the information corresponding to the target policy item into the policy information storage system is described below by taking the policy information storage system as a alliance chain system as an example. Fig. 7 is a schematic flow chart of entering policy information as information corresponding to a target policy item into a policy information storage system according to an embodiment of the present invention, where the flow chart includes:

s701, the policy entry server generates a policy information issuing transaction, wherein the policy information issuing transaction comprises policy item information returned by the image acquisition terminal for a target policy item.

The policy entry server is an equivalent node in the federated chain system. In a specific implementation, the policy entry server may generate the policy information issuing transaction through a software development kit (software development kit, SDK). Optionally, the policy information issuing transaction may include, in addition to the policy item information, identification information of the target policy item and/or the target policy item, a transaction version, and so on.

S702, the policy entry server sends the policy information issuing transaction to an endorsement node in the alliance chain system, and the endorsement node receives the policy information issuing transaction.

The endorsement node is a node in an endorsement policy of the policy entry server, which is set based on the intelligent contract, and the endorsement node and the policy entry server can belong to the same alliance chain channel. An endorsement node is one or more policy entry servers of a policy entry server group in the architecture shown in fig. 1.

In the specific implementation, the policy entry server can send the policy information issuing transaction to an endorsement node in the alliance chain system in a multicast mode or a mode of respectively sending, and the endorsement node is used for carrying out transaction endorsement on the blockchain transaction sent by the policy entry server so as to ensure the authenticity and legality of the transaction.

S703, the endorsing node endorses the policy information issuing transaction.

Here, the endorsement process of the endorsement node for the policy information issuing transaction is: and the endorsement node takes the policy information issuing transaction as input to execute the intelligent contract to obtain an output result, and then signs the output result by adopting a private key of the endorsement node to obtain an endorsement result.

And S704, the endorsement node sends an endorsement result obtained by endorsing the policy information issuing transaction to the policy entry server, and the policy entry server receives the endorsement result.

The policy entry server can determine that the transaction endorsement of the policy information issuing transaction is completed under the condition that endorsement results sent by most of the peer nodes are received. The method comprises the steps that the transaction endorsement completion of the policy information issuing transaction is determined by receiving endorsement results of how many equivalent nodes, and the transaction endorsement completion can be set according to specific situations. For example, when there are fewer endorsement nodes in the endorsement policy, it may be designed to determine that the transaction endorsement for the policy information issuing transaction is completed when more than 90% of the endorsement results sent by the endorsement nodes are received; when more endorsement nodes are included in the endorsement policy, the method can be designed to determine that the transaction endorsement of the transaction for issuing the policy information is completed when more than 80% of endorsement results sent by the endorsement nodes are received.

The policy entry server executes step S705 in the case where it is determined that the transaction endorsement for the policy information issuing transaction is completed according to the endorsement result.

And S705, the policy entry server transmits the policy information issuing transaction to the command node in the alliance chain system.

Here, the policy entry server packages and transmits the policy information issuing transaction and all the received endorsement results to the command node in the coalition chain system.

S706, ordering the policy information issuing transactions by the command node according to the time of the policy information issuing transactions.

S707, the command node generates a block corresponding to the policy information issuing transaction.

Here, the command node packages all transactions that are currently generated in the federation chain and have not been packaged, including the policy information issuing transaction, in time order to construct a block.

S708, the command node sends the block corresponding to the policy information issuing transaction to all the peer nodes in the alliance chain system, and all the peer nodes in the alliance chain receive the block corresponding to the policy information issuing transaction.

In a specific implementation, the command node may select one from peer nodes as a leader node (leader), send a block corresponding to the policy information issuing transaction to the leader node, and then the leader node randomly communicates with some peer nodes in the federation chain based on a Gossip protocol to synchronize the policy information issuing transaction in the peer nodes of the federation chain, so as to synchronize the block corresponding to the policy information issuing transaction to all peer nodes on the federation chain.

S709, all the peer nodes in the alliance chain system verify the block corresponding to the policy information issuing transaction.

Here, the verification of the block corresponding to the policy information issuing transaction by the peer node means that the endorsement policy and the transaction version of all the transactions in the block corresponding to the policy information issuing transaction are verified, and the specific verification mode is as follows: and respectively verifying the signature in the endorsement result of each transaction in the block, verifying whether the endorsement node corresponding to the signature is a node in the endorsement policy corresponding to the transaction, and verifying whether the version of each transaction is the same as the local version. And if the endorsement result and the verification of the transaction version of each transaction are passed, determining that the verification of the block corresponding to the transaction of the policy information release is passed.

If the verification of the block corresponding to the policy information issuing transaction is passed, the peer node executes step S710.

S710, the same node stores the block corresponding to the policy information issuing transaction to the local.

Through three links of endorsement, ordering and verification, the policy information issued to the alliance chain system can be verified, so that only correct and legal policy information can be issued to the alliance chain system, the authenticity and reliability of the policy information in the alliance chain system are ensured, and the policy information is issued to the alliance chain system to play a role in backing up the policy information and preventing the policy information from being tampered.

The method of the embodiment of the invention is described above, and the apparatus of the embodiment of the invention is described below.

Referring to fig. 8, fig. 8 is a schematic diagram of a composition structure of a policy entry device based on image recognition, where the device may be the policy entry server or the policy entry server group shown in fig. 1, and the device 80 includes:

the policy receiving module 801 is configured to receive a target policy sent by the image acquisition terminal, where the target policy is a policy in a picture format;

the image recognition module 802 is configured to perform image recognition on the target policy to obtain policy information corresponding to the target policy;

the option generating module 803 is configured to determine, according to the policy information and a target policy item, a plurality of first information options corresponding to the target policy item, where the target policy item is a policy item to be entered;

an option sending module 804, configured to send the plurality of first information options to the image acquisition terminal, so that the image acquisition terminal displays the plurality of first information options to a policy entry user when the policy entry user performs entry on the target policy item;

an information receiving module 805, configured to receive policy item information returned by the image capturing terminal for the target policy item, where the policy item information is associated with at least one information option of the plurality of first information options;

The information input module 806 is configured to input the policy item information as information corresponding to the target policy item to a policy information storage system, where the policy information storage system is configured to store policy information.

In one possible design, the option generation module 803 is specifically configured to:

generating a plurality of information options according to the policy information;

ordering the information options according to the target policy items to obtain the sequence of each information option;

and determining a plurality of first information options corresponding to the target policy item according to the sequence of the information options.

comparing the policy information with preset policy template information, and determining a first character and a second character, wherein the first character is a character which is different from the policy template information in the policy information, and the second character is a character which is the same as the policy template information in the policy information;

and generating a plurality of information options according to the first character, wherein the information options do not contain the second character.

Determining a third character and a first equivalent character corresponding to the third character in the first character, and searching a fourth character in the first character, wherein the first equivalent character and the third character correspond to the same position in the target policy, the fourth character is a character in which no second character exists between the policy information and the third character or between the fourth character and the first equivalent character, and the fourth character and the third character correspond to different positions in the target policy;

under the condition that the fourth character is found, determining a second equivalent character corresponding to the fourth character in the first character, and generating a plurality of information options according to a first target character and a second target character, wherein the second equivalent character and the fourth character correspond to the same position in the target policy, the first target character is the third character or the first equivalent character, and the second target character is the fourth character or the second equivalent character;

and generating a plurality of information options according to the first target character under the condition that the fourth character is not found.

Determining a third character in the first characters, and determining at least one fifth character according to the third character, wherein the similarity between the character form of the fifth character and the character form of the third character is larger than a first similarity threshold;

searching a fourth character in the first character, wherein the fourth character is a character in which the second character does not exist between the third character and the policy information;

and under the condition that the fourth character is found, determining at least one sixth character according to the fourth character, and generating a plurality of information options according to a third target character and a fourth target character, wherein the similarity between the character form of the sixth character and the character form of the fourth character is larger than the first similarity threshold, the third target character is the third character or the fifth character, and the fourth target character is the fourth character or the sixth character.

And generating a plurality of information options according to the third target character under the condition that the fourth character is not found.

In one possible design, the image recognition module 802 is specifically configured to:

performing image preprocessing on the target policy to obtain a text image area of the target policy;

Image segmentation is carried out on the text image area of the target policy, so that a plurality of characters to be identified corresponding to the target policy are obtained;

and respectively identifying each character to be identified in the plurality of characters to be identified to obtain the policy information corresponding to the target policy.

comparing each character to be recognized in the plurality of characters to be recognized with a preset character template respectively to determine one or more target character templates corresponding to the characters to be recognized respectively, wherein the target character templates are character templates with similarity to the characters to be recognized higher than a second similarity threshold;

and determining the characters corresponding to one or more target character templates corresponding to the characters to be identified as policy information corresponding to the target policy.

In one possible design, the information entry module 806 is specifically configured to:

generating the policy information issuing transaction, wherein the policy information issuing transaction comprises the policy item information;

transmitting the policy information issuing transaction to an endorsement node in the blockchain system for transaction endorsement, wherein the endorsement node is a node in an endorsement policy set based on an intelligent contract;

When the transaction endorsement of the policy information issuing transaction is determined to be completed according to an endorsement result returned by the endorsement node, the policy information issuing transaction is sent to a command node in the alliance chain system, so that the command node orders the policy information issuing transaction and forms a block corresponding to the policy information issuing transaction;

receiving the block sent by the command node;

if the verification of the block is passed, the block is saved locally.

It should be noted that, in the embodiment corresponding to fig. 8, the content not mentioned may be referred to the description of the method embodiment, and will not be repeated here.

In the embodiment of the invention, the policy entry device based on image recognition obtains the policy information in the policy by recognizing the policy in the picture format, then generates a plurality of information options for the policy items to be entered and displays the information options to the policy entry user through the image acquisition terminal, so that the user can directly select the information options or slightly modify the information options, the entry of the information corresponding to the policy items to be entered can be completed, the process of manually inputting the policy item information by the user is omitted, and the policy entry efficiency is improved.

Referring to fig. 9, fig. 9 is a schematic diagram of the composition structure of another policy entry device based on image recognition according to an embodiment of the present invention, where the device may be the policy entry server or the policy entry server group shown in fig. 1, and the device 90 includes a processor 901, a memory 902, and a communication interface 903. The processor 901 is connected to the memory 902 and the communication interface 903, for example, the processor 901 may be connected to the memory 902 and the communication interface 903 by a bus.

The processor 901 is configured to support the image recognition based policy entry device to perform the corresponding functions in the image recognition based policy entry method described in fig. 3-7. The processor 901 may be a central processing unit (central processing unit, CPU), a network processor (network processor, NP), a hardware chip, or any combination thereof. The hardware chip may be an application specific integrated circuit (application specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD), or a combination thereof. The PLD may be a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), general-purpose array logic (generic array logic, GAL), or any combination thereof.

The memory 902 is used for storing program codes and the like. The memory 902 may include Volatile Memory (VM), such as random access memory (random access memory, RAM); the memory 902 may also include a non-volatile memory (NVM), such as read-only memory (ROM), flash memory (flash memory), hard disk (HDD) or Solid State Drive (SSD); the memory 902 may also include a combination of the above types of memory. In the embodiment of the present invention, the memory 902 is used to store policy information and the like.

The communication interface 903 is used to send or receive data.

The processor 901 may call the program code to:

receiving a target policy sent by an image acquisition terminal through a communication interface 903, wherein the target policy is a policy in a picture format;

determining a plurality of first information options corresponding to a target policy item according to the policy information and the target policy item, wherein the target policy item is a policy item to be entered in the target policy;

The plurality of first information options are sent to the image acquisition terminal through the communication interface 903, so that the image acquisition terminal displays the plurality of first information options to a policy entry user when the policy entry user registers the target policy item;

It should be noted that implementation of each operation may also correspond to the corresponding description of the method embodiment shown with reference to fig. 3-7; the processor 901 may also cooperate with the communication interface 903 to perform other operations in the method embodiments described above.

Embodiments of the present invention also provide a computer storage medium storing a computer program comprising program instructions which, when executed by a computer, cause the computer to perform a method as described in the previous embodiments, which may be part of an image recognition based policy entry device as mentioned above. Such as the processor 901 described above.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Wherein the storage medium can be a magnetic disk, an optical disk, a ROM or a RAM, etc.

The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.

Claims

1. The policy entry method based on image recognition is characterized by comprising the following steps:

Determining the characters corresponding to one or more target character templates corresponding to the characters to be identified as policy information corresponding to the target policy;

generating a plurality of information options according to the first character, wherein the information options do not contain the second character;

ordering the information options according to a target policy item to obtain the sequence of each information option, wherein the target policy item is a policy item to be input;

determining a plurality of first information options corresponding to the target policy item according to the sequence of the information options;

2. The method of claim 1, wherein the generating a plurality of information options from the first character comprises:

3. The method of claim 1, wherein the generating a plurality of information options from the first character comprises:

under the condition that the fourth character is found, determining at least one sixth character according to the fourth character, and generating a plurality of information options according to a third target character and a fourth target character, wherein the similarity between the character form of the sixth character and the character form of the fourth character is larger than the first similarity threshold, the third target character is the third character or the fifth character, and the fourth target character is the fourth character or the sixth character;

4. An image recognition-based policy entry device, comprising:

the image recognition module is used for carrying out image preprocessing on the target policy to obtain a text image area of the target policy; image segmentation is carried out on the text image area of the target policy, so that a plurality of characters to be identified corresponding to the target policy are obtained; comparing each character to be recognized in the plurality of characters to be recognized with a preset character template respectively to determine one or more target character templates corresponding to the characters to be recognized respectively, wherein the target character templates are character templates with similarity to the characters to be recognized higher than a second similarity threshold; determining the characters corresponding to one or more target character templates corresponding to the characters to be identified as policy information corresponding to the target policy;

the option generation module is used for comparing the policy information with preset policy template information and determining a first character and a second character, wherein the first character is a character which is different from the policy template information in the policy information, and the second character is the same character as the policy template information in the policy information; generating a plurality of information options according to the first character, wherein the information options do not contain the second character; ordering the information options according to a target policy item to obtain the sequence of each information option, wherein the target policy item is a policy item to be input; determining a plurality of first information options corresponding to the target policy item according to the sequence of the information options;

5. A policy entry device based on image recognition, comprising a processor, a memory and a communication interface, the processor, the memory and the communication interface being interconnected, wherein the communication interface is for transmitting or receiving data, the memory is for storing program code, and the processor is for invoking the program code to perform the method of any of claims 1-3.

6. A computer storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1-3.