A document encryption method and device

Abstract

The present application provides a document encryption method and device, wherein, in the present application, when it is necessary to convert target medical clinical management data into a text document, it is necessary to encrypt the characters in the target medical clinical management data before generating the text document. During the encryption process, it is necessary to obtain a fingerprint for encryption, and then merge the fingerprint features with the strokes of the characters so that the visual effect of the strokes presented on the computer is different from the original strokes, thereby making the presentation of the characters on the computer different from the original characters. After the text document is generated, the characters in the text document are all encrypted characters, so that the content presented in the text document is inconsistent with the target medical clinical management data, thereby achieving the purpose of confidentiality.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a document encryption method and device. Background Art

[0002] Medical clinical management is an important part of the medical and health field. Its purpose is to ensure the safety, effectiveness and economy of medical services, while improving patient satisfaction and the competitiveness of medical institutions. In the process of medical clinical management, the medical clinical management data generated will involve sensitive data such as patient privacy and internal data of medical institutions. It is important data that needs to be kept strictly confidential.

[0003] Medical clinical management data sometimes needs to be converted into text documents in order to view the medical clinical management data. However, after conversion into text documents, there is a risk of loss or leakage. Therefore, how to ensure the security of the generated text documents is an urgent problem to be solved. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a document encryption method to improve the security of medical clinical management data.

[0005] In a first aspect, an embodiment of the present application provides a document encryption method, which is applied to a document encryption system, wherein the document encryption system includes a fingerprint input terminal for obtaining fingerprint information and an encryption terminal for encrypting a document, wherein the document encryption method is configured at the encryption terminal, wherein the encryption terminal stores medical clinical management data, and when the target medical clinical management data needs to be converted into a text document, the document encryption method includes:

[0006] In response to the document conversion instruction, after acquiring the target medical clinical management data indicated by the document conversion instruction, sending a first fingerprint input instruction to the fingerprint input terminal;

[0007] After acquiring the first fingerprint image sent by the fingerprint input terminal, acquiring a feature vector corresponding to each fingerprint feature included in the first fingerprint image;

[0008] For each fingerprint feature, the fingerprint feature including the feature vector is fused to obtain a first fusion vector corresponding to the fingerprint feature;

[0009] Performing statistics on each character included in the target medical clinical management data to obtain the strokes included in the statistics of each character, and determining a stroke vector corresponding to each stroke, wherein the number of dimensions of the stroke vectors corresponding to each stroke is equal;

[0010] The similarity between strokes is calculated using the following formula:

[0011] Tex= ;

[0012] in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector;

[0013] After obtaining the similarity between all strokes, the similarity between all strokes is clustered using the following formula:

[0014] ;

[0015] Among them, Xi represents the i-th similarity among all the similarities between the strokes, Vj represents the j-th similarity among all the similarities between the strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, represents the similarity value of the j-th similarity;

[0016] For each clustering result, the stroke vectors corresponding to the strokes included in the clustering result are fused to obtain a second fused vector;

[0017] For each clustering result, calculating the cosine angle between each of the first fusion vectors and the second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as the target fusion vector;

[0018] The target fusion vector is used to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data, so as to generate a text document according to the characters obtained after all the strokes are fused.

[0019] Optionally, the using the target fusion vector to perform feature fusion on the strokes included in the clustering result in the target medical clinical management data to generate a text document according to the characters obtained after all the strokes are fused, includes:

[0020] According to the generation format indicated by the document conversion instruction, the target medical clinical management data is converted to obtain a document to be encrypted that matches the generation format;

[0021] The strokes included in each character in the document to be encrypted are subjected to feature fusion using the corresponding target fusion vector and the stroke vector corresponding to the stroke to obtain the text document.

[0022] Optionally, the acquiring a feature vector corresponding to each fingerprint feature included in the fingerprint image includes:

[0023] Binarizing the fingerprint image to obtain a binary image of the fingerprint image;

[0024] According to the binary image, a feature vector corresponding to each fingerprint feature is obtained.

[0025] Optionally, different identifiers are assigned to different first fusion vectors, and the method further includes:

[0026] The identifier corresponding to the target fusion vector and the stroke vector that performs feature fusion with the target fusion vector are stored in the form of a data pair.

[0027] Optionally, the method further comprises:

[0028] In response to the document decryption instruction, sending a second fingerprint input instruction to the fingerprint input terminal;

[0029] After acquiring the second fingerprint image sent by the fingerprint input terminal, the text document is decrypted according to the second fingerprint image and the data pair.

[0030] In a second aspect, an embodiment of the present application provides a document encryption device, the device is configured at an encryption end of a document encryption system, the document encryption system includes a fingerprint input end for obtaining fingerprint information and an encryption end for encrypting a document, the encryption end stores medical clinical management data, and the device includes:

[0031] a sending unit, configured to respond to a document conversion instruction when it is necessary to convert the target medical clinical management data into a text document, and after acquiring the target medical clinical management data indicated by the document conversion instruction, send a first fingerprint input instruction to the fingerprint input terminal;

[0032] an acquisition unit, configured to acquire, after acquiring the first fingerprint image sent by the fingerprint input terminal, a feature vector corresponding to each fingerprint feature included in the first fingerprint image;

[0033] A first processing unit is used to fuse each fingerprint feature including a feature vector to obtain a first fusion vector corresponding to the fingerprint feature;

[0034] A statistical unit, used for performing statistics on each character included in the target medical clinical management data, obtaining the strokes included in the statistics of each character, and determining a stroke vector corresponding to each stroke, wherein the number of dimensions of the stroke vectors corresponding to each stroke is equal;

[0035] The first calculation unit is used to calculate the similarity between strokes using the following formula:

[0036] Tex= ;

[0037] in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector;

[0038] The second calculation unit is used to cluster the similarities between all the strokes using the following formula after obtaining the similarities between all the strokes:

[0039] ;

[0040] Among them, Xi represents the i-th similarity among all the similarities between the strokes, Vj represents the j-th similarity among all the similarities between the strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, represents the similarity value of the j-th similarity;

[0041] A second processing unit is used for fusing, for each clustering result, the stroke vectors corresponding to the strokes included in the clustering result to obtain a second fused vector;

[0042] a comparing unit, configured to calculate, for each clustering result, a cosine angle between each of the first fusion vectors and a second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as a target fusion vector;

[0043] A generating unit is used to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data using the target fusion vector, so as to generate a text document according to the characters obtained after all the strokes are fused.

[0044] Optionally, the generating unit is used to perform feature fusion on the strokes included in the clustering result in the target medical clinical management data using the target fusion vector to generate a text document according to the characters obtained after all the strokes are fused, including:

[0045] According to the generation format indicated by the document conversion instruction, the target medical clinical management data is converted to obtain a document to be encrypted that matches the generation format;

[0046] The strokes included in each character in the document to be encrypted are subjected to feature fusion using the corresponding target fusion vector and the stroke vector corresponding to the stroke to obtain the text document.

[0047] Optionally, when the acquisition unit is used to acquire the feature vector corresponding to each fingerprint feature included in the fingerprint image, it includes:

[0048] Binarizing the fingerprint image to obtain a binary image of the fingerprint image;

[0049] According to the binary image, a feature vector corresponding to each fingerprint feature is obtained.

[0050] Optionally, different identifiers are assigned to different first fusion vectors, and the device further includes:

[0051] The storage unit is used to store the identifier corresponding to the target fusion vector and the stroke vector that performs feature fusion with the target fusion vector in the form of data pairs.

[0052] Optionally, the sending unit is further used to respond to the document decryption instruction and send a second fingerprint input instruction to the fingerprint input terminal;

[0053] The device also includes:

[0054] The decryption unit is used to decrypt the text document according to the second fingerprint image and the data pair after acquiring the second fingerprint image sent by the fingerprint input terminal.

[0055] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0056] In the present application, when it is necessary to convert the target medical clinical management data into a text document, it is necessary to encrypt the characters in the target medical clinical management data before generating the text document. During the encryption process, it is necessary to obtain the fingerprint used for encryption, and then merge the fingerprint features with the strokes of the characters so that the visual effect of the strokes presented on the computer is different from the original strokes, thereby making the presentation of the characters on the computer different from the original characters. After the text document is generated, the characters in the text document are all encrypted characters, so that the content presented in the text document is inconsistent with the target medical clinical management data, thereby achieving the purpose of confidentiality.

[0057] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1A flowchart of a document encryption method provided in an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a document encryption device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0062] Figure 1 A flowchart of a document encryption method provided in an embodiment of the present application is provided. The method is applied to a document encryption system. The document encryption system includes a fingerprint input terminal for obtaining fingerprint information and an encryption terminal for encrypting a document. The document encryption method is configured at the encryption terminal. The encryption terminal stores medical clinical management data, such as Figure 1 As shown, when the target medical clinical management data needs to be converted into a text document, the method includes the following steps:

[0063] Step 101, responding to a document conversion instruction, after acquiring the target medical clinical management data indicated by the document conversion instruction, sending a first fingerprint input instruction to the fingerprint input terminal.

[0064] Step 102: After obtaining the first fingerprint image sent by the fingerprint input terminal, obtain a feature vector corresponding to each fingerprint feature included in the first fingerprint image.

[0065] Step 103: For each fingerprint feature, the fingerprint feature including the feature vector is fused to obtain a first fusion vector corresponding to the fingerprint feature.

[0066] Step 104: Count the characters included in the target medical clinical management data to obtain the strokes included in the characters, and determine the stroke vectors corresponding to the strokes, wherein the dimensions of the stroke vectors corresponding to the strokes are equal.

[0067] Step 105: Calculate the similarity between the strokes using the following formula:

[0068] Tex= ; (Formula 1)

[0069] in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector;

[0070] Step 106: After obtaining the similarities between all strokes, cluster the similarities between all strokes using the following formula 2:

[0071] ; (Formula 2)

[0072] Among them, Xi represents the i-th similarity among all the similarities between the strokes, Vj represents the j-th similarity among all the similarities between the strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, Denotes the similarity value of the j-th similarity.

[0073] Step 107: For each clustering result, the stroke vectors corresponding to the strokes included in the clustering result are merged to obtain a second fused vector.

[0074] Step 108: For each clustering result, calculate the cosine angle between each of the first fusion vectors and the second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as the target fusion vector.

[0075] Step 109: Use the target fusion vector to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data, so as to generate a text document according to the characters obtained after all the strokes are fused.

[0076] Specifically, the document encryption system may include multiple fingerprint input terminals, and the permissions of the personnel corresponding to different fingerprint input terminals are different. For example, when the first designated person (such as a department manager) is required to encrypt the data on the encryption terminal, the first designated person can be configured as the encryption person when configuring the document conversion instruction. After the document conversion instruction is configured, the encryption terminal can send a fingerprint input instruction to the fingerprint input terminal corresponding to the first designated person. In this way, data of different levels can be encrypted by personnel of different levels, so as to achieve level distinction.

[0077] After the fingerprint input terminal receives the first fingerprint input instruction, it can prompt the corresponding person to input the fingerprint through a specified prompt method (such as flashing lights or audio reminders, etc.), and then the fingerprint input terminal sends the acquired first fingerprint image to the encryption terminal for encryption.

[0078] After acquiring the first fingerprint image, the encryption end can perform fingerprint analysis on the first fingerprint image to obtain feature vectors corresponding to each fingerprint feature included in the first fingerprint image. For example, the fingerprint includes triangular features (a specific area located in the fingerprint pattern, usually formed by the intersection of three or more lines. The shape and position of the triangle are very important for fingerprint recognition), line features (the raised part in the fingerprint is called a ridge, and the concave part is called a valley. The arrangement, density and shape of the ridges and valleys are all one of the features of the fingerprint), bifurcation features (the ridge line is divided into two or more lines at a certain point. The position and shape of the bifurcation point are also one of the features of the fingerprint), etc. At this time, the feature vectors obtained include: a triangular feature vector corresponding to the triangular feature, a line feature vector corresponding to the line feature, a bifurcation feature vector corresponding to the bifurcation feature, etc., and for a certain fingerprint feature, the fingerprint feature includes multiple, so the fingerprint features of the same type can be fused to obtain the first fusion vector corresponding to the fingerprint feature of this type.

[0079] If a manual is required, the specific fusion method can be selected according to actual needs and is not specifically limited here.

[0080] Multiple medical clinical management data may be managed at one encryption end. When configuring the document conversion instruction, the corresponding medical clinical management data can be selected according to the project that needs to be encrypted. After the configuration is completed, the medical clinical management data to be encrypted set by the document conversion instruction can be used as the target medical clinical management data. After obtaining the target medical clinical management data, the characters (including: text, letters and numbers) included in the target medical clinical management data are traversed and deduplicated to determine the strokes involved in all the characters included in the target medical clinical management data, and then the stroke vector corresponding to each stroke is determined. At this time, the stroke vector data set corresponding to the target medical clinical management data can be obtained.

[0081] After obtaining all the stroke vectors included in the target medical clinical management data, in order to reduce the amount of data processing, the same fusion method can be used for similar strokes. Therefore, after obtaining all the stroke vectors, the similarities between the strokes are calculated first (the number of similarities can be obtained by combining two by two according to the number of stroke types). After obtaining the similarities between the two strokes, the multiple similarities are clustered to fuse the strokes with relatively close similarities using the first fusion vector corresponding to the same feature.

[0082] After obtaining the clustering results, in order to determine the first fusion vector corresponding to each clustering result, for each clustering result, the stroke vectors included in the clustering result are fused to obtain the second fusion vector, and then the cosine angle between the first fusion vector corresponding to each fingerprint feature and the second fusion vector corresponding to the clustering result is calculated. The larger the cosine angle, the greater the difference in direction between the two. After using the first fusion vector corresponding to the largest cosine angle as the fusion vector of the clustering result, the strokes under the clustering result can be greatly changed, so that the similarity between the original character and the fused character is also the lowest, and then the fused character is visually different from the original character, thereby playing a role in character encryption. After each character is encrypted, the encryption of the text document is completed.

[0083] For a character, if the character includes multiple strokes and different strokes correspond to different clustering results, the strokes of the character will be feature fused with the first fusion vectors corresponding to different fingerprint features, so as to achieve better encryption effect of the character.

[0084] In a feasible implementation scheme, when executing step 109, the target medical clinical management data can be first converted according to the generation format indicated by the document conversion instruction to obtain a document to be encrypted that matches the generation format; then, the strokes included in each character in the document to be encrypted are feature fused with the stroke vector corresponding to the stroke using the corresponding target fusion vector to obtain the text document.

[0085] Specifically, in order to make the fused characters have the same arrangement position as the original characters in the text document, a document to be encrypted can be generated first. At this time, the position of each character in the text document can be determined, and then the strokes included in the characters in the document to be encrypted can be feature fused, so that the character order in the text document is the same as the character order in the document to be encrypted, and the characters in the decrypted document can also have the correct arrangement order.

[0086] In a feasible implementation scheme, when obtaining the feature vector corresponding to each fingerprint feature included in the fingerprint image, the fingerprint image can be first binarized to obtain a binary image of the fingerprint image; then, based on the binarized image, the feature vector corresponding to each fingerprint feature is obtained.

[0087] Specifically, fingerprint binarization refers to converting the pixel values ​​in the fingerprint image into black and white, that is, realizing the black and white processing of the fingerprint image. This not only helps to simplify the fingerprint image, but also makes the features in the fingerprint image clearer, making it easier to obtain fingerprint features.

[0088] In a feasible implementation scheme, in order to facilitate subsequent decryption, after obtaining the first fusion vector corresponding to each fingerprint feature, different identifiers can be assigned to different first fusion vectors to identify the fingerprint features fused by different strokes through the identifiers, and after completing the feature fusion, the identifier corresponding to the target fusion vector and the stroke vector that is feature fused with the target fusion vector are stored in the form of a data pair, so as to facilitate subsequent decryption based on the stored data pair.

[0089] In a feasible implementation scheme, when decrypting an encrypted text document, in response to a document decryption instruction, a second fingerprint input instruction is sent to the fingerprint input terminal, and then after obtaining the second fingerprint image sent by the fingerprint input terminal, the text document is decrypted based on the second fingerprint image and the data pair.

[0090] Specifically, when decrypting an encrypted text document, a second fingerprint input instruction can be sent to the fingerprint input terminal corresponding to the encryption in order to obtain the decryption authorization of the corresponding person. After obtaining the second fingerprint image, the fusion vector corresponding to each fingerprint feature in the second fingerprint image can be obtained. Then, based on the fusion vector and the above-mentioned stored data pairs, the characters in the encrypted text document are reversely fused so that the characters can be restored to the original characters, making it easier to read.

[0091] It should be noted that the specific reverse fusion method can be set according to actual needs and is not specifically limited here.

[0092] Figure 2 A schematic diagram of the structure of a document encryption device provided in an embodiment of the present application, wherein the device is configured at an encryption end of a document encryption system, wherein the document encryption system comprises a fingerprint input end for acquiring fingerprint information and an encryption end for encrypting documents, wherein the encryption end stores medical clinical management data, such as Figure 2 As shown, the device comprises:

[0093] The sending unit 21 is used for responding to the document conversion instruction when the target medical clinical management data needs to be converted into a text document, and after acquiring the target medical clinical management data indicated by the document conversion instruction, sending a first fingerprint input instruction to the fingerprint input terminal;

[0094] An acquisition unit 22, configured to acquire a feature vector corresponding to each fingerprint feature included in the first fingerprint image after acquiring the first fingerprint image sent by the fingerprint input terminal;

[0095] The first processing unit 23 is used to fuse the fingerprint features including the feature vectors for each fingerprint feature to obtain a first fusion vector corresponding to the fingerprint feature;

[0096] A statistical unit 24, used for performing statistics on each character included in the target medical clinical management data, obtaining the strokes included in the statistics of each character, and determining a stroke vector corresponding to each stroke, wherein the number of dimensions of the stroke vectors corresponding to each stroke is equal;

[0097] The first calculation unit 25 is used to calculate the similarity between strokes using the following formula:

[0098] Tex= ;

[0099] in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector;

[0100] The second calculation unit 26 is used to cluster the similarities between all the strokes using the following formula after obtaining the similarities between all the strokes:

[0101] ;

[0102] Among them, Xi represents the i-th similarity among all the similarities between the strokes, Vj represents the j-th similarity among all the similarities between the strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, represents the similarity value of the j-th similarity;

[0103] A second processing unit 27 is used for fusing the stroke vectors corresponding to the strokes included in each clustering result to obtain a second fused vector;

[0104] A comparison unit 28 is used to calculate, for each clustering result, a cosine angle between each of the first fusion vectors and a second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as a target fusion vector;

[0105] The generating unit 29 is used to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data using the target fusion vector, so as to generate a text document according to the characters obtained after all the strokes are fused.

[0106] In a feasible implementation, the generating unit is used to perform feature fusion on the strokes included in the clustering result in the target medical clinical management data using the target fusion vector to generate a text document according to the characters obtained after all the strokes are fused, including:

[0107] According to the generation format indicated by the document conversion instruction, the target medical clinical management data is converted to obtain a document to be encrypted that matches the generation format;

[0108] The strokes included in each character in the document to be encrypted are subjected to feature fusion using the corresponding target fusion vector and the stroke vector corresponding to the stroke to obtain the text document.

[0109] In a feasible implementation manner, when the acquisition unit is used to acquire the feature vector corresponding to each fingerprint feature included in the fingerprint image, it includes:

[0110] Binarizing the fingerprint image to obtain a binary image of the fingerprint image;

[0111] According to the binary image, a feature vector corresponding to each fingerprint feature is obtained.

[0112] In a feasible implementation manner, different identifiers are assigned to different first fusion vectors, and the device further includes:

[0113] The storage unit is used to store the identifier corresponding to the target fusion vector and the stroke vector that performs feature fusion with the target fusion vector in the form of data pairs.

[0114] In a feasible implementation manner, the sending unit is further used to send a second fingerprint input instruction to the fingerprint input terminal in response to the document decryption instruction;

[0115] The device also includes:

[0116] The decryption unit is used to decrypt the text document according to the second fingerprint image and the data pair after acquiring the second fingerprint image sent by the fingerprint input terminal.

[0117] about Figure 2 For related explanations, please refer to Figure 1 The relevant instructions will not be explained in detail here.

[0118] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0122] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0123] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A document encryption method, characterized in that: The method is applied to a document encryption system, the document encryption system includes a fingerprint input terminal for obtaining fingerprint information and an encryption terminal for encrypting a document, the document encryption method is configured at the encryption terminal, the encryption terminal stores medical clinical management data, and when it is necessary to convert the target medical clinical management data into a text document, the document encryption method includes: In response to the document conversion instruction, after acquiring the target medical clinical management data indicated by the document conversion instruction, sending a first fingerprint input instruction to the fingerprint input terminal; After acquiring the first fingerprint image sent by the fingerprint input terminal, acquiring a feature vector corresponding to each fingerprint feature included in the first fingerprint image; For each fingerprint feature, the fingerprint feature including the feature vector is fused to obtain a first fusion vector corresponding to the fingerprint feature; Performing statistics on each character included in the target medical clinical management data to obtain the strokes included in the statistics of each character, and determining a stroke vector corresponding to each stroke, wherein the number of dimensions of the stroke vectors corresponding to each stroke is equal; The similarity between strokes is calculated using the following formula: Tex= ; in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector; After obtaining the similarity between all strokes, the similarity between all strokes is clustered using the following formula: ； Among them, Xi represents the i-th similarity among all similarities between strokes, Vj represents the j-th similarity among all similarities between strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, represents the similarity value of the jth similarity; For each clustering result, the stroke vectors corresponding to the strokes included in the clustering result are fused to obtain a second fused vector; For each clustering result, calculating the cosine angle between each of the first fusion vectors and the second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as the target fusion vector; The target fusion vector is used to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data, so as to generate a text document according to the characters obtained after all the strokes are fused.

2. The method according to claim 1, characterized in that The step of using the target fusion vector to perform feature fusion on the strokes included in the clustering result in the target medical clinical management data to generate a text document according to the characters obtained after all the strokes are fused includes: According to the generation format indicated by the document conversion instruction, the target medical clinical management data is converted to obtain a document to be encrypted that matches the generation format; The strokes included in each character in the document to be encrypted are subjected to feature fusion using the corresponding target fusion vector and the stroke vector corresponding to the stroke to obtain the text document.

3. The method according to claim 1, characterized in that The step of obtaining a feature vector corresponding to each fingerprint feature included in the fingerprint image includes: Binarizing the fingerprint image to obtain a binary image of the fingerprint image; According to the binary image, a feature vector corresponding to each fingerprint feature is obtained.

4. The method according to claim 1, characterized in that Allocating different identifiers to different first fusion vectors, the method further comprising: The identifier corresponding to the target fusion vector and the stroke vector that performs feature fusion with the target fusion vector are stored in the form of a data pair.

5. The method according to claim 4, characterized in that The method further comprises: In response to the document decryption instruction, sending a second fingerprint input instruction to the fingerprint input terminal; After acquiring the second fingerprint image sent by the fingerprint input terminal, the text document is decrypted according to the second fingerprint image and the data pair.

6. A document encryption device, characterized in that: The device is configured at an encryption end of a document encryption system, the document encryption system includes a fingerprint input end for acquiring fingerprint information and an encryption end for encrypting documents, the encryption end stores medical clinical management data, and the device includes: a sending unit, configured to respond to a document conversion instruction when it is necessary to convert the target medical clinical management data into a text document, and after acquiring the target medical clinical management data indicated by the document conversion instruction, send a first fingerprint input instruction to the fingerprint input terminal; an acquisition unit, configured to acquire, after acquiring the first fingerprint image sent by the fingerprint input terminal, a feature vector corresponding to each fingerprint feature included in the first fingerprint image; A first processing unit is used to fuse each fingerprint feature including a feature vector to obtain a first fusion vector corresponding to the fingerprint feature; A statistical unit, used for performing statistics on each character included in the target medical clinical management data, obtaining the strokes included in the statistics of each character, and determining a stroke vector corresponding to each stroke, wherein the number of dimensions of the stroke vectors corresponding to each stroke is equal; The first calculation unit is used to calculate the similarity between strokes using the following formula: Tex= ; in, represents the features of the stroke vector a in the i-th dimension, represents the feature of the stroke vector b in the i-th dimension, and n represents the number of dimensions of the stroke vector; The second calculation unit is used to cluster the similarities between all the strokes using the following formula after obtaining the similarities between all the strokes: ； Among them, Xi represents the i-th similarity among all similarities between strokes, Vj represents the j-th similarity among all similarities between strokes as the cluster center, is the total number of similarities between all strokes, represents the similarity value of the i-th similarity, represents the similarity value of the j-th similarity; A second processing unit is used for fusing, for each clustering result, the stroke vectors corresponding to the strokes included in the clustering result to obtain a second fused vector; a comparing unit, configured to calculate, for each clustering result, a cosine angle between each of the first fusion vectors and a second fusion vector corresponding to the clustering result, so as to use the first fusion vector corresponding to the largest cosine angle as a target fusion vector; A generating unit is used to perform feature fusion on the stroke vectors corresponding to the strokes included in the clustering result in the target medical clinical management data using the target fusion vector, so as to generate a text document according to the characters obtained after all the strokes are fused.

7. The device according to claim 6, characterized in that The generating unit is used to perform feature fusion on the strokes included in the clustering result in the target medical clinical management data using the target fusion vector to generate a text document according to the characters obtained after all the strokes are fused, including: According to the generation format indicated by the document conversion instruction, the target medical clinical management data is converted to obtain a document to be encrypted that matches the generation format; The strokes included in each character in the document to be encrypted are subjected to feature fusion using the corresponding target fusion vector and the stroke vector corresponding to the stroke to obtain the text document.

8. The device according to claim 6, characterized in that When the acquisition unit is used to acquire the feature vector corresponding to each fingerprint feature included in the fingerprint image, it includes: Binarizing the fingerprint image to obtain a binary image of the fingerprint image; According to the binary image, a feature vector corresponding to each fingerprint feature is obtained.

9. The device according to claim 6, characterized in that Different identifiers are assigned to different first fusion vectors, and the device further includes: The storage unit is used to store the identifier corresponding to the target fusion vector and the stroke vector that performs feature fusion with the target fusion vector in the form of data pairs.

10. The device according to claim 9, characterized in that The sending unit is further used to respond to the document decryption instruction and send a second fingerprint input instruction to the fingerprint input terminal; The device also includes: The decryption unit is used to decrypt the text document according to the second fingerprint image and the data pair after acquiring the second fingerprint image sent by the fingerprint input terminal.

Images