Method, device and equipment for processing sensitive information in logistics address

Through lexical and syntactic analysis, natural language processing and encryption technology, the problems of sensitive information leakage and low efficiency in logistics address processing are solved, and high-security and high-efficiency logistics information processing are achieved, address errors are automatically corrected, and operating costs are reduced.

CN119066703APending Publication Date: 2024-12-03SHANGHAI DONGPU INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411112401.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing logistics address processing methods have problems such as leakage of sensitive information, low processing efficiency and difficult to guarantee accuracy, resulting in delays, loss or misplacement of packages, increasing operating costs.

Method used

The lexical analysis and syntactic analysis algorithm are used to analyze logistics addresses, combine natural language processing technology to convert sensitive area information into numerical vectors, and the sensitive element identification model is used to identify key sensitive elements and then encrypt it, separate and store public and sensitive information, and use high security levels. database storage, real-time monitoring and abnormal detection prevent information leakage.

Benefits of technology

It improves the security and efficiency of logistics information processing, automatically identify and correct address errors, reduces human intervention, protects user sensitive information, and meets logistics business needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066703A_ABST
    Figure CN119066703A_ABST
Patent Text Reader

Abstract

The invention discloses a processing method, device and equipment for sensitive information in a logistics address, the method is applied to the technical field of logistics, and the method comprises the steps: obtaining logistics address information in a logistics order management system; analyzing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information; inputting the numerical vector corresponding to the sensitive area information into a sensitive element identification model for sensitive element identification processing to obtain a key sensitive element in the sensitive area information; encrypting the key sensitive element to obtain encrypted sensitive information; and public area information in the logistics address information is stored in a first database, and encrypted sensitive information corresponding to sensitive area information in the logistics address information is stored in a second database. According to the invention, the security and efficiency of logistics information processing are improved while the sensitive information of the logistics address of the user is protected.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and equipment for processing sensitive information in a logistics address. Background Art

[0002] Although the common logistics address processing methods in the current market have alleviated the problem to a certain extent, they still have significant shortcomings. First of all, the problem of sensitive information being easily leaked is particularly prominent. Traditional paper documents, unencrypted electronic files, or insecure data transmission methods may all become ways for hackers to attack or internal personnel to abuse information. Secondly, low processing efficiency is also a major pain point. With the surge in order volume, how to quickly and accurately process and protect each address information has become a difficult problem that logistics companies must overcome. Furthermore, the problem of difficulty in ensuring accuracy cannot be ignored. Minor errors in address information may cause packages to be delayed, lost, or misdelivered, which not only affects the user experience, but also increases the company's operating costs. Summary of the invention

[0003] The present invention provides a method, device and equipment for processing sensitive information in a logistics address, which can improve the security and efficiency of logistics information processing while protecting the sensitive information of the user's logistics address.

[0004] In one aspect, the present invention provides a method for processing sensitive information in a logistics address, the method comprising:

[0005] Obtain logistics address information from the logistics order management system;

[0006] Parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result;

[0007] Using natural language processing technology to convert the text in the sensitive area information into a numerical vector;

[0008] Inputting the numerical vector into a sensitive element identification model to perform sensitive element identification processing to obtain key sensitive elements in the sensitive area information;

[0009] Using a preset encryption algorithm to encrypt the key sensitive elements to obtain encrypted sensitive information;

[0010] The public area information in the logistics address information is stored in the first database, and the encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in the second database.

[0011] Optionally, the parsing of the logistics address information based on the lexical analysis algorithm and the syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result, includes:

[0012] Based on the lexical analysis algorithm and the syntactic analysis algorithm, the logistics address information is parsed to obtain a parsing result;

[0013] Determine whether there are specific keywords or preset address structures in the analysis results, and preliminarily divide the logistics address information into initial public area information and initial sensitive area information according to the determination results;

[0014] The initial public area information and the initial sensitive area information are verified and adjusted according to the area classification model and the address classification rule base to obtain the public area information and the sensitive area information.

[0015] Optionally, the training method of the region classification model includes:

[0016] Obtaining sample logistics address information; the sample logistics address information includes a sample public area label and a sample sensitive area label;

[0017] Input the sample logistics address information into the first preset model for regional classification processing to obtain sample public area results and sample sensitive area results;

[0018] Determine first loss data according to a difference between the sample common area result and the sample common area label, and a difference between the sample sensitive area result and the sample sensitive area label;

[0019] The first preset model is trained according to the first loss data to obtain the regional classification model.

[0020] Optionally, the training method of the sensitive element recognition model includes:

[0021] Acquire training logistics address information, and use natural language processing technology to convert sensitive area information in the training logistics address information into a training numerical vector; the training numerical vector is annotated with a training sensitive element label;

[0022] Inputting the training numerical vector into a second preset model to extract training context information and training semantic features;

[0023] Determining a prediction result of a training sensitive element according to the training context information and the training semantic features;

[0024] According to the difference between the training sensitive element prediction result and the training sensitive element label, the second preset model is trained to obtain an initial sensitive element recognition model;

[0025] Based on a genetic algorithm or a whale optimization algorithm, the hyperparameters in the initial sensitive element recognition model are optimized to obtain the sensitive element recognition model.

[0026] Optionally, the adopting a preset encryption algorithm to encrypt the key sensitive element to obtain encrypted sensitive information includes:

[0027] When there are multiple key sensitive elements, group the multiple key sensitive elements to obtain multiple key sensitive element groups;

[0028] A symmetric encryption algorithm is used to generate a random encryption key corresponding to each key sensitive element group;

[0029] Using a group encryption method, each key sensitive element group is encrypted according to a random encryption key corresponding to each key sensitive element group to obtain an initial processing result;

[0030] The initial processing result is converted into a hash value of fixed length using a hash function to obtain encrypted sensitive information.

[0031] Optionally, storing the public area information in the logistics address information in the first database, and storing the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database, includes:

[0032] The public area information in the logistics address information is stored in a first database in plain text, and a data index and a data query strategy are set; the first database is a relational database;

[0033] The encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in a second database; the second database is a MongoDB or Redis database; the access level of the second database is higher than the access level of the first database.

[0034] Optionally, the method further includes:

[0035] In response to the request for obtaining the logistics address information, obtaining data access rights of the accessing user;

[0036] According to the data access rights, determine the target database to which the access user has access rights, and extract information corresponding to the logistics address information from the target database; the target database is at least one of the first database and the second database;

[0037] Through the audit log function of the database and the real-time monitoring system, the call operation information of each logistics address information is recorded; the call operation information includes the identity of the caller, the call time and the call purpose;

[0038] Adopt anomaly detection algorithm to detect in real time whether each call operation information is abnormal;

[0039] If abnormal calling behavior is identified, an alarm message is generated according to the abnormal calling behavior.

[0040] On the other hand, a device for processing sensitive information in a logistics address is provided, the device comprising:

[0041] Logistics information acquisition module, used to obtain logistics address information in the logistics order management system;

[0042] A parsing module, used to parse the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decompose the logistics address information into public area information and sensitive area information according to the parsing result;

[0043] A vector conversion module, used to convert the text in the sensitive area information into a numerical vector using natural language processing technology;

[0044] A key element identification module, used for inputting the numerical vector into a sensitive element identification model to perform sensitive element identification processing, and obtaining key sensitive elements in the sensitive area information;

[0045] An encryption module, used to encrypt the key sensitive elements using a preset encryption algorithm to obtain encrypted sensitive information;

[0046] The storage module is used to store the public area information in the logistics address information in the first database, and store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database.

[0047] Optionally, the parsing module includes:

[0048] A parsing unit, used to parse the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm to obtain a parsing result;

[0049] A judgment unit, used to judge whether there are specific keywords or preset address structures in the analysis result, and preliminarily divide the logistics address information into initial public area information and initial sensitive area information according to the judgment result;

[0050] The sensitive information determination unit is used to verify and adjust the initial public area information and the initial sensitive area information according to the area classification model and the address classification rule library to obtain the public area information and the sensitive area information.

[0051] Optionally, the device further comprises:

[0052] A sample address acquisition module is used to acquire sample logistics address information; the sample logistics address information includes a sample public area label and a sample sensitive area label;

[0053] A sample result determination module, used for inputting the sample logistics address information into a first preset model for regional classification processing to obtain a sample public area result and a sample sensitive area result;

[0054] A first loss determination module, configured to determine first loss data according to a difference between the sample common area result and the sample common area label, and a difference between the sample sensitive area result and the sample sensitive area label;

[0055] The regional classification model determination module is used to train the first preset model according to the first loss data to obtain the regional classification model.

[0056] Optionally, the device further comprises:

[0057] A training information acquisition module is used to acquire training logistics address information, and use natural language processing technology to convert sensitive area information in the training logistics address information into a training numerical vector; the training numerical vector is annotated with a training sensitive element label;

[0058] A training feature extraction module, used for inputting the training numerical vector into a second preset model to extract training context information and training semantic features;

[0059] A training result determination module, used to determine the prediction result of the training sensitive element according to the training context information and the training semantic features;

[0060] An initial model determination module, used to train the second preset model according to the difference between the training sensitive element prediction result and the training sensitive element label to obtain an initial sensitive element recognition model;

[0061] The sensitive element identification model optimization module is used to optimize the hyperparameters in the initial sensitive element identification model based on a genetic algorithm or a whale optimization algorithm to obtain the sensitive element identification model.

[0062] Optionally, the encryption module includes:

[0063] A grouping unit, used for grouping the multiple key sensitive elements to obtain multiple key sensitive element groups when there are multiple key sensitive elements;

[0064] A key generation unit, used to generate a random encryption key corresponding to each key sensitive element group using a symmetric encryption algorithm;

[0065] The initial encryption unit is used to encrypt each key sensitive element group using a group encryption method according to a random encryption key corresponding to each key sensitive element group to obtain an initial processing result;

[0066] The encrypted information determination unit is used to convert the initial processing result into a hash value of fixed length by using a hash function to obtain encrypted sensitive information.

[0067] Optionally, the storage module includes:

[0068] A policy setting unit, used to store the public area information in the logistics address information in plain text in a first database, and set a data index and a data query policy; the first database is a relational database;

[0069] A data storage unit is used to store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in a second database; the second database is a MongoDB or Redis database; the access level of the second database is higher than the access level of the first database.

[0070] Optionally, the device further comprises:

[0071] An authority acquisition module, used to obtain data access rights of an accessing user in response to a request to obtain the logistics address information;

[0072] An information extraction module is used to determine, based on the data access rights, a target database to which the accessing user has access rights, and extract information corresponding to the logistics address information from the target database; the target database is at least one of the first database and the second database;

[0073] An information recording module is used to record each call operation information of the logistics address information through the audit log function of the database and the real-time monitoring system; the call operation information includes the identity of the caller, the call time and the call purpose;

[0074] The anomaly detection module is used to use an anomaly detection algorithm to detect in real time whether each call operation information is abnormal;

[0075] The alarm information generation module is used to generate alarm information according to the abnormal calling behavior if abnormal calling behavior is identified.

[0076] On the other hand, an electronic device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for processing sensitive information in the logistics address as described above.

[0077] On the other hand, a computer storage medium is provided, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the method for processing sensitive information in a logistics address as described above.

[0078] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the above-mentioned method for processing sensitive information in the logistics address.

[0079] The method, device and equipment for processing sensitive information in logistics addresses provided by the present invention have the following technical effects:

[0080] The present invention obtains logistics address information in a logistics order management system; parses the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposes the logistics address information into public area information and sensitive area information according to the parsing result; uses natural language processing technology to convert the text in the sensitive area information into a numerical vector; inputs the numerical vector into a sensitive element recognition model for sensitive element recognition processing to obtain key sensitive elements in the sensitive area information; uses a preset encryption algorithm to encrypt the key sensitive elements to obtain encrypted sensitive information; stores the public area information in the logistics address information in a first database, and stores the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in a second database. While protecting the user's logistics address sensitive information, the present invention meets the normal needs of the logistics business and improves the security and efficiency of logistics information processing. The intelligent address resolution system can automatically identify and correct address errors, reduce human intervention, and improve overall efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions and advantages of the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0082] Figure 1 It is a schematic diagram of a system for processing sensitive information in a logistics address provided in an embodiment of this specification;

[0083] Figure 2 It is a flowchart of a method for processing sensitive information in a logistics address provided in an embodiment of this specification;

[0084] Figure 3 It is a flowchart of a method provided in an embodiment of this specification for parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result;

[0085] Figure 4 is a flowchart of a method for training a regional classification model provided in an embodiment of this specification;

[0086] Figure 5 It is a flowchart of a method provided in an embodiment of this specification for encrypting the key sensitive element using a preset encryption algorithm to obtain encrypted sensitive information;

[0087] Figure 6 It is a structural diagram of a device for processing sensitive information in a logistics address provided in an embodiment of this specification;

[0088] Figure 7 It is a structural diagram of a server provided in an embodiment of this specification. DETAILED DESCRIPTION

[0089] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0090] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0091] See also Figure 1 , Figure 1 is a schematic diagram of a system for processing sensitive information in a logistics address provided by an embodiment of this specification, such as Figure 1 As shown, the system for processing sensitive information in the logistics address may include at least a server 01 and a client 02.

[0092] Specifically, in the embodiments of this specification, the server 01 may include an independently operated server, or a distributed server, or a server cluster composed of multiple servers, and may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, a memory, and the like. Specifically, the server 01 can be used to determine public area information and encrypt sensitive information based on logistics address information.

[0093] Specifically, in the embodiments of this specification, the client 02 may include physical devices such as smart phones, desktop computers, tablet computers, laptop computers, digital assistants, smart wearable devices, smart speakers, vehicle terminals, smart TVs, etc., and may also include software running in physical devices, such as web pages provided by some service providers to users, or applications provided by these service providers to users. Specifically, the client 02 may be used to query public area information and sensitive area information of a logistics address.

[0094] The following describes a method for processing sensitive information in a logistics address of the present invention. Figure 2It is a flowchart of a method for processing sensitive information in a logistics address provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method may include:

[0095] S201: Obtain logistics address information in the logistics order management system.

[0096] In the embodiments of the present specification, the logistics address information in the logistics order management system can be obtained, and the system obtains the newly generated logistics address information in real time through the interface with the logistics order management system.

[0097] S203: parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result.

[0098] In the embodiments of this specification, Figure 3 As shown, Figure 3 The present invention is a flowchart of a method for parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result, including:

[0099] S2031: parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm to obtain a parsing result;

[0100] S2033: Determine whether there is a specific keyword or a preset address structure in the parsing result, and preliminarily divide the logistics address information into initial public area information and initial sensitive area information according to the determination result;

[0101] S2035: Verify and adjust the initial public area information and the initial sensitive area information according to the area classification model and the address classification rule library to obtain the public area information and the sensitive area information.

[0102] In the embodiments of this specification, lexical analysis and syntactic analysis algorithms can be used to perform preliminary analysis of the address. For example, by determining whether the address contains specific keywords or common address structures, such as "community", "unit", "house number", etc., the address is preliminarily divided into possible public area information and sensitive area information. Then, a rule-based classification model is used, combined with existing address classification experience and rule base, to further verify and adjust the results of the preliminary division. For example, if the address contains a specific floor and room number, and the name of the community is clear, it is classified as sensitive area information; and the part that only contains the city, district, county and street name is classified as public area information.

[0103] In an embodiment of the present specification, the logistics address information can be input into a regional classification model to obtain predicted public area information and predicted sensitive area information, and the initial public area information in the analysis result can be compared with the predicted public area information, and the predicted sensitive area information can be compared with the initial sensitive area information, and based on the comparison results of the two, the initial public area information and the initial sensitive area information can be adjusted until the comparison result indicates that the similarity between the two compared information is greater than a preset similarity threshold, and the preset similarity threshold can be set according to actual conditions, for example, it can be set to 99%; then the address classification rule library is used to verify and re-adjust the adjusted initial public area information and initial sensitive area information to obtain public area information and sensitive area information, thereby improving the accuracy of the public area information and the sensitive area information.

[0104] In the embodiments of this specification, Figure 4 As shown, Figure 4 The flowchart is a method for training a region classification model, the method comprising:

[0105] S401: Obtaining sample logistics address information; the sample logistics address information includes a sample public area label and a sample sensitive area label;

[0106] S403: Inputting the sample logistics address information into a first preset model for regional classification processing to obtain sample public area results and sample sensitive area results;

[0107] S405: determining first loss data according to a difference between the sample common area result and the sample common area label, and a difference between the sample sensitive area result and the sample sensitive area label;

[0108] S407: Training the first preset model according to the first loss data to obtain the regional classification model.

[0109] In the embodiments of the present specification, the first preset model can be trained with the sample logistics address information to obtain a regional classification model. Obtain the sample logistics address information; input the sample logistics address information into the first preset model for regional classification processing to obtain a sample public area result and a sample sensitive area result; determine the first loss data based on the difference between the sample public area result and the sample public area label, and the difference between the sample sensitive area result and the sample sensitive area label; adjust the parameters of the first preset model based on the first loss data until the training end condition is met to obtain the regional classification model. The first preset model can be any network with classification function.

[0110] S205: Using natural language processing technology to convert the text in the sensitive area information into a numerical vector.

[0111] In the embodiment of this specification, the use of natural language processing technology to convert the text in the sensitive area information into a numerical vector includes:

[0112] A word vector model is used to convert the text in the sensitive area information into a numerical vector; the word vector model is Word2Vec or GloVe.

[0113] In the embodiments of this specification, a word vector model in natural language processing, such as Word2Vec or GloVe, can be used to convert the text in the sensitive area information into a numerical vector.

[0114] S207: Input the numerical vector into a sensitive element identification model to perform sensitive element identification processing to obtain key sensitive elements in the sensitive area information.

[0115] In the embodiment of this specification, the training method of the sensitive element recognition model includes:

[0116] Acquire training logistics address information, and use natural language processing technology to convert sensitive area information in the training logistics address information into a training numerical vector; the training numerical vector is annotated with a training sensitive element label;

[0117] Inputting the training numerical vector into a second preset model to extract training context information and training semantic features;

[0118] Determining a prediction result of a training sensitive element according to the training context information and the training semantic features;

[0119] According to the difference between the training sensitive element prediction result and the training sensitive element label, the second preset model is trained to obtain an initial sensitive element recognition model;

[0120] Based on a genetic algorithm or a whale optimization algorithm, the hyperparameters in the initial sensitive element recognition model are optimized to obtain the sensitive element recognition model.

[0121] In the embodiment of the present specification, the second preset model can be a long short-term memory network (LSTM) or a gated recurrent unit (GRU) to capture the context information and semantic features in the text; the training logistics address information and the sample logistics address information can be the same or different; the training numerical vector can be input into the second preset model to extract the training context information and the training semantic features; the training sensitive element prediction result is determined according to the training context information and the training semantic features; the second preset model is trained according to the difference between the training sensitive element prediction result and the training sensitive element label to obtain the training loss data, the second preset model is trained according to the training loss data until the model converges, and the converged second preset model is determined as the initial sensitive element recognition model; the genetic algorithm or the whale optimization algorithm is used to optimize the hyperparameters in the model to obtain the final recognition model, and the key sensitive elements such as the specific house number, room number, recipient name, etc. are accurately determined through the output of the model. Therefore, the key sensitive elements in the sensitive area information can be quickly and accurately predicted through the sensitive element recognition model.

[0122] S209: Using a preset encryption algorithm to encrypt the key sensitive elements to obtain encrypted sensitive information.

[0123] In the embodiments of this specification, Figure 5 As shown, Figure 5 The present invention is a flowchart of a method for encrypting the key sensitive elements using a preset encryption algorithm to obtain encrypted sensitive information, the method comprising:

[0124] S2091: when there are multiple key sensitive elements, group the multiple key sensitive elements to obtain multiple key sensitive element groups;

[0125] S2093: using a symmetric encryption algorithm to generate a random encryption key corresponding to each key sensitive element group;

[0126] S2095: using a group encryption method, encrypting each key sensitive element group according to a random encryption key corresponding to each key sensitive element group to obtain an initial processing result;

[0127] S2097: Using a hash function to convert the initial processing result into a hash value of a fixed length to obtain encrypted sensitive information.

[0128] In the embodiments of this specification, during the anonymization process, a hash function, such as MD5 or SHA-256, is used to process the encrypted sensitive information. The sensitive elements are converted into a hash value of fixed length, thereby removing the identification directly associated with the individual, so that the processed information cannot be directly traced back to the original personal identity. For the identified sensitive information, an advanced symmetric encryption algorithm, such as AES (Advanced Encryption Standard), is used. During the encryption process, a random encryption key is generated, and a key expansion algorithm is used to increase the complexity and security of the key. The working mode of the block cipher, such as CBC (Cipher Block Chaining) mode, can be used to encrypt the sensitive information in groups to ensure the strength and randomness of the encryption. At the same time, the encryption key is updated regularly to cope with the possible risk of key leakage.

[0129] S2011: Store the public area information in the logistics address information in the first database, and store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database.

[0130] In the embodiment of this specification, the storing of the public area information in the logistics address information in the first database and the storing of the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database include:

[0131] The public area information in the logistics address information is stored in a first database in plain text, and a data index and a data query strategy are set; the first database is a relational database;

[0132] The encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in a second database; the second database is a MongoDB or Redis database; the access level of the second database is higher than the access level of the first database.

[0133] In the embodiments of this specification, the processed logistics address information is stored in different databases, the public area information is stored in a conventional database, and the encrypted and anonymized sensitive information is stored in a dedicated database; in the information storage stage, the public area information is stored in a relational database such as MySQL in plain text, and the query efficiency is improved by setting reasonable indexes and query optimization strategies. The encrypted and anonymized sensitive information is stored in a dedicated database with strict access control, such as a MongoDB or Redis database with advanced security features.

[0134] In the embodiment of this specification, the method further includes:

[0135] In response to the request for obtaining the logistics address information, obtaining data access rights of the accessing user;

[0136] According to the data access rights, determine the target database to which the access user has access rights, and extract information corresponding to the logistics address information from the target database; the target database is at least one of the first database and the second database;

[0137] Through the audit log function of the database and the real-time monitoring system, the call operation information of each logistics address information is recorded; the call operation information includes the identity of the caller, the call time and the call purpose;

[0138] Adopt anomaly detection algorithm to detect in real time whether each call operation information is abnormal;

[0139] If abnormal calling behavior is identified, an alarm message is generated according to the abnormal calling behavior.

[0140] In the embodiments of this specification, during the permission calling process, the role-based access control (RBAC) model is used to assign different permission levels according to the user's role and responsibilities. During use, each call operation of the address information is recorded through the audit log function of the database and the real-time monitoring system, including detailed information such as the identity of the caller, the call time, and the purpose of the call. Anomaly detection algorithms, such as statistical outlier detection or machine learning-based classification algorithms, are used to monitor in real time whether there are abnormal call behaviors, issue alarms in time, and take corresponding security measures. After the alarm information is generated, an alarm information can be sent to the user terminal to prompt the user to stop the abnormal call behavior in time.

[0141] In the embodiments of this specification, on the one hand, the application of data encryption and privacy protection technology is strengthened, such as using advanced encryption algorithms to encrypt, store and transmit address information to ensure the security of data in all links. At the same time, the characteristics of blockchain technology that cannot be tampered with and can be traced are used to provide an additional security layer for logistics information.

[0142] By obtaining the logistics address information in the system, the obtained logistics addresses are preliminarily classified into public area information and sensitive area information; sensitive information identification, using natural language processing technology and machine learning algorithms to accurately identify sensitive area information and determine key sensitive elements; anonymizing the encrypted sensitive information to remove the identification directly associated with the individual; information encryption, encrypting the identified sensitive information, using advanced encryption algorithms to ensure information security; storing the processed logistics address information in different databases, public area information in regular databases, and encrypted and anonymized sensitive information in dedicated databases; calling address information according to permissions, and real-time monitoring and auditing during use. While protecting the user's logistics address sensitive information, it meets the normal needs of logistics business and improves the security and efficiency of logistics information processing. The intelligent address resolution system can automatically identify and correct address errors, reduce human intervention, and improve overall efficiency.

[0143] It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification obtain the logistics address information in the logistics order management system; based on the lexical analysis algorithm and the syntactic analysis algorithm, the logistics address information is parsed, and the logistics address information is decomposed into public area information and sensitive area information according to the parsing results; the text in the sensitive area information is converted into a numerical vector using natural language processing technology; the numerical vector is input into the sensitive element recognition model for sensitive element recognition processing to obtain the key sensitive elements in the sensitive area information; the key sensitive elements are encrypted using a preset encryption algorithm to obtain encrypted sensitive information; the public area information in the logistics address information is stored in the first database, and the encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in the second database. While protecting the user's logistics address sensitive information, the present invention meets the normal needs of the logistics business and improves the security and efficiency of logistics information processing. The intelligent address resolution system can automatically identify and correct address errors, reduce human intervention, and improve overall efficiency.

[0144] The embodiment of this specification also provides a device for processing sensitive information in a logistics address, such as Figure 6 As shown, the device comprises:

[0145] Logistics information acquisition module 610, used to acquire logistics address information in the logistics order management system;

[0146] The parsing module 620 is used to parse the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decompose the logistics address information into public area information and sensitive area information according to the parsing result;

[0147] A vector conversion module 630, configured to convert the text in the sensitive area information into a numerical vector using natural language processing technology;

[0148] A key element identification module 640 is used to input the numerical vector into a sensitive element identification model to perform sensitive element identification processing to obtain key sensitive elements in the sensitive area information;

[0149] The encryption module 650 is used to encrypt the key sensitive elements using a preset encryption algorithm to obtain encrypted sensitive information;

[0150] The storage module 660 is used to store the public area information in the logistics address information in the first database, and store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database.

[0151] Optionally, the parsing module includes:

[0152] A parsing unit, used to parse the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm to obtain a parsing result;

[0153] A judgment unit, used to judge whether there are specific keywords or preset address structures in the analysis result, and preliminarily divide the logistics address information into initial public area information and initial sensitive area information according to the judgment result;

[0154] The sensitive information determination unit is used to verify and adjust the initial public area information and the initial sensitive area information according to the area classification model and the address classification rule library to obtain the public area information and the sensitive area information.

[0155] Optionally, the device further comprises:

[0156] A sample address acquisition module is used to acquire sample logistics address information; the sample logistics address information includes a sample public area label and a sample sensitive area label;

[0157] A sample result determination module, used for inputting the sample logistics address information into a first preset model for regional classification processing to obtain a sample public area result and a sample sensitive area result;

[0158] A first loss determination module, configured to determine first loss data according to a difference between the sample common area result and the sample common area label, and a difference between the sample sensitive area result and the sample sensitive area label;

[0159] The regional classification model determination module is used to train the first preset model according to the first loss data to obtain the regional classification model.

[0160] Optionally, the device further comprises:

[0161] A training information acquisition module is used to acquire training logistics address information, and use natural language processing technology to convert sensitive area information in the training logistics address information into a training numerical vector; the training numerical vector is annotated with a training sensitive element label;

[0162] A training feature extraction module, used for inputting the training numerical vector into a second preset model to extract training context information and training semantic features;

[0163] A training result determination module, used to determine the prediction result of the training sensitive element according to the training context information and the training semantic features;

[0164] An initial model determination module, used to train the second preset model according to the difference between the training sensitive element prediction result and the training sensitive element label to obtain an initial sensitive element recognition model;

[0165] The sensitive element identification model optimization module is used to optimize the hyperparameters in the initial sensitive element identification model based on a genetic algorithm or a whale optimization algorithm to obtain the sensitive element identification model.

[0166] Optionally, the encryption module includes:

[0167] A grouping unit, used for grouping the multiple key sensitive elements to obtain multiple key sensitive element groups when there are multiple key sensitive elements;

[0168] A key generation unit, used to generate a random encryption key corresponding to each key sensitive element group using a symmetric encryption algorithm;

[0169] The initial encryption unit is used to encrypt each key sensitive element group using a group encryption method according to a random encryption key corresponding to each key sensitive element group to obtain an initial processing result;

[0170] The encrypted information determination unit is used to convert the initial processing result into a hash value of fixed length by using a hash function to obtain encrypted sensitive information.

[0171] Optionally, the storage module includes:

[0172] A policy setting unit, used to store the public area information in the logistics address information in plain text in a first database, and set a data index and a data query policy; the first database is a relational database;

[0173] A data storage unit is used to store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in a second database; the second database is a MongoDB or Redis database; the access level of the second database is higher than the access level of the first database.

[0174] Optionally, the device further comprises:

[0175] An authority acquisition module, used to obtain data access rights of an accessing user in response to a request to obtain the logistics address information;

[0176] An information extraction module is used to determine, based on the data access rights, a target database to which the accessing user has access rights, and extract information corresponding to the logistics address information from the target database; the target database is at least one of the first database and the second database;

[0177] An information recording module is used to record each call operation information of the logistics address information through the audit log function of the database and the real-time monitoring system; the call operation information includes the identity of the caller, the call time and the call purpose;

[0178] The anomaly detection module is used to use an anomaly detection algorithm to detect in real time whether each call operation information is abnormal;

[0179] The alarm information generation module is used to generate alarm information according to the abnormal calling behavior if abnormal calling behavior is identified.

[0180] The device and method embodiments in the described device embodiments are based on the same inventive concept.

[0181] An embodiment of the present specification provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement a method for processing sensitive information in a logistics address as provided in the above method embodiment.

[0182] An embodiment of the present invention also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to a method for processing sensitive information in a logistics address in a method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for processing sensitive information in a logistics address provided in the above method embodiment.

[0183] The embodiment of the present invention further provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the method for processing sensitive information in a logistics address provided in the above method embodiment.

[0184] Optionally, in the embodiments of this specification, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0185] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0186] The method for processing sensitive information in the logistics address provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 7 This is a hardware structure diagram of a server for a method for processing sensitive information in a logistics address provided in an embodiment of this specification. Figure 7As shown, the server 700 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 710 (the central processing unit 710 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 730 for storing data, and one or more storage media 720 (such as one or more mass storage devices) for storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 can be short-term storage or permanent storage. The program stored in the storage medium 720 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 710 can be configured to communicate with the storage medium 720 and execute a series of instruction operations in the storage medium 720 on the server 700. The server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0187] The input / output interface 740 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 700. In one example, the input / output interface 740 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 740 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0188] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0189] It can be seen from the embodiments of the processing method, device, electronic device or storage medium of sensitive information in the logistics address provided by the present invention that the present invention obtains the logistics address information in the logistics order management system; based on the lexical analysis algorithm and the syntactic analysis algorithm, the logistics address information is parsed, and the logistics address information is decomposed into public area information and sensitive area information according to the parsing result; the text in the sensitive area information is converted into a numerical vector by using natural language processing technology; the numerical vector is input into the sensitive element recognition model for sensitive element recognition processing to obtain the key sensitive elements in the sensitive area information; the key sensitive elements are encrypted by using a preset encryption algorithm to obtain encrypted sensitive information; the public area information in the logistics address information is stored in the first database, and the encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in the second database. While protecting the user's logistics address sensitive information, the present invention meets the normal needs of the logistics business and improves the security and efficiency of logistics information processing. The intelligent address resolution system can automatically identify and correct address errors, reduce human intervention, and improve overall efficiency.

[0190] It should be noted that the above sequence of the embodiments of this specification is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0191] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0192] A person skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0193] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing sensitive information in a logistics address, characterized in that: The method comprises: Obtain logistics address information from the logistics order management system; Parsing the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decomposing the logistics address information into public area information and sensitive area information according to the parsing result; Using natural language processing technology to convert the text in the sensitive area information into a numerical vector; Inputting the numerical vector into a sensitive element identification model to perform sensitive element identification processing to obtain key sensitive elements in the sensitive area information; Using a preset encryption algorithm to encrypt the key sensitive elements to obtain encrypted sensitive information; The public area information in the logistics address information is stored in the first database, and the encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in the second database.

2. The method according to claim 1, characterized in that The logistics address information is parsed based on the lexical analysis algorithm and the syntactic analysis algorithm, and the logistics address information is decomposed into public area information and sensitive area information according to the parsing result, including: Based on the lexical analysis algorithm and the syntactic analysis algorithm, the logistics address information is parsed to obtain a parsing result; Determine whether there are specific keywords or preset address structures in the analysis results, and preliminarily divide the logistics address information into initial public area information and initial sensitive area information according to the determination results; The initial public area information and the initial sensitive area information are verified and adjusted according to the area classification model and the address classification rule base to obtain the public area information and the sensitive area information.

3. The method according to claim 2, characterized in that The training method of the region classification model includes: Obtaining sample logistics address information; the sample logistics address information includes a sample public area label and a sample sensitive area label; Input the sample logistics address information into the first preset model for regional classification processing to obtain sample public area results and sample sensitive area results; Determine first loss data according to a difference between the sample common area result and the sample common area label, and a difference between the sample sensitive area result and the sample sensitive area label; The first preset model is trained according to the first loss data to obtain the regional classification model.

4. The method according to claim 1, characterized in that: The training method of the sensitive element recognition model includes: Acquire training logistics address information, and use natural language processing technology to convert sensitive area information in the training logistics address information into a training numerical vector; the training numerical vector is annotated with a training sensitive element label; Inputting the training numerical vector into a second preset model to extract training context information and training semantic features; Determining a prediction result of a training sensitive element according to the training context information and the training semantic features; According to the difference between the training sensitive element prediction result and the training sensitive element label, the second preset model is trained to obtain an initial sensitive element recognition model; Based on a genetic algorithm or a whale optimization algorithm, the hyperparameters in the initial sensitive element recognition model are optimized to obtain the sensitive element recognition model.

5. The method according to any one of claims 1 to 4, characterized in that: The key sensitive elements are encrypted using a preset encryption algorithm to obtain encrypted sensitive information, including: When there are multiple key sensitive elements, group the multiple key sensitive elements to obtain multiple key sensitive element groups; A symmetric encryption algorithm is used to generate a random encryption key corresponding to each key sensitive element group; Using a group encryption method, each key sensitive element group is encrypted according to a random encryption key corresponding to each key sensitive element group to obtain an initial processing result; The initial processing result is converted into a hash value of fixed length using a hash function to obtain encrypted sensitive information.

6. The method according to claim 1, characterized in that The storing of the public area information in the logistics address information into the first database, and storing the encrypted sensitive information corresponding to the sensitive area information in the logistics address information into the second database, includes: The public area information in the logistics address information is stored in a first database in plain text, and a data index and a data query strategy are set; the first database is a relational database; The encrypted sensitive information corresponding to the sensitive area information in the logistics address information is stored in a second database; the second database is a MongoDB or Redis database; the access level of the second database is higher than the access level of the first database.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: In response to the request for obtaining the logistics address information, obtaining data access rights of the accessing user; According to the data access rights, determine the target database to which the access user has access rights, and extract information corresponding to the logistics address information from the target database; the target database is at least one of the first database and the second database; Through the audit log function of the database and the real-time monitoring system, the call operation information of each time of the logistics address information is recorded; the call operation information includes the identity of the caller, the call time and the call purpose; Adopt anomaly detection algorithm to detect in real time whether each call operation information is abnormal; If abnormal calling behavior is identified, an alarm message is generated according to the abnormal calling behavior.

8. A device for processing sensitive information in a logistics address, characterized in that: The device comprises: Logistics information acquisition module, used to obtain logistics address information in the logistics order management system; A parsing module, used to parse the logistics address information based on a lexical analysis algorithm and a syntactic analysis algorithm, and decompose the logistics address information into public area information and sensitive area information according to the parsing result; A vector conversion module, used to convert the text in the sensitive area information into a numerical vector using natural language processing technology; A key element identification module, used for inputting the numerical vector into a sensitive element identification model to perform sensitive element identification processing, and obtaining key sensitive elements in the sensitive area information; An encryption module, used to encrypt the key sensitive elements using a preset encryption algorithm to obtain encrypted sensitive information; The storage module is used to store the public area information in the logistics address information in the first database, and store the encrypted sensitive information corresponding to the sensitive area information in the logistics address information in the second database.

9. An electronic device, characterized in that: The device includes: a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for processing sensitive information in a logistics address as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for processing sensitive information in the logistics address as described in any one of claims 1-7.