Airport license type lost and found method and device

Abstract

The invention provides an airport license type lost and found method and device, and the method comprises the steps: constructing a knowledge graph for each user according to the data of a full-scene system in an airport, and the full-scene system at least comprises a security check system, a departure system and a self-service check-in system; determining the user information of the target owner according to the certificate characteristics of the to-be-found certificate lost article; matching the user information of the target loser with the knowledge graph, and determining a contact way set of the target loser; according to an activity track of the target loser, a contact strategy is determined from the contact way set, the target loser is notified based on the contact strategy, and the activity track comprises interaction data of the target loser and any one full-scene system. According to the scheme provided by the invention, the efficiency and reliability of finding the airport license lost articles can be improved.

Description

Technical Field

[0001] This article belongs to the field of computer technology, specifically relating to a method and device for finding lost and found airport documents. Background Technology

[0002] Currently, major airports, high-speed rail stations, and airlines across China offer lost and found services through their official websites or WeChat mini-programs. These services include 24 / 7 customer service via hotline and WeChat mini-program for reporting lost items, submitting supporting documents / authorizations online, and scheduling pickup appointments. Airport lost and found counters also provide access to these services for inquiry, reporting, and pickup. Furthermore, the system integrates QR code tags and RFID tags (NFC functionality) for the registration and management of items entering and leaving the warehouse.

[0003] The aforementioned lost and found process relies on the owner proactively making a request, with airport on-site service departments passively accepting and processing it. It also requires passengers to provide extensive supporting documentation, which must be verified before the lost item can be legally retrieved. While this process can mitigate fraudulent claims to some extent, there is significant room for improvement in customer satisfaction and process efficiency. Summary of the Invention

[0004] In view of the above-mentioned problems in the prior art, the purpose of this paper is to provide a method and device for finding lost and found airport documents and certificates, so as to improve the efficiency and reliability of finding lost and found airport documents and certificates.

[0005] To solve the above-mentioned technical problems, the specific technical solution presented in this paper is as follows: On the one hand, this article provides a method for finding lost and found items such as airport documents, the method including: Based on data from the airport's full-scenario system, a knowledge graph is constructed for each user. The full-scenario system includes at least the security check system, the departure system, and the self-service check-in system. Based on the characteristics of the lost documents and certificates to be recovered, the user information of the target owner can be determined; The user information of the target lost person is matched with the knowledge graph to determine the set of contact methods of the target lost person; Based on the activity trajectory of the target owner, a contact strategy is determined from the set of contact methods to notify the target owner. The activity trajectory includes the interaction data between the target owner and any full-scene system.

[0006] Furthermore, based on the full-scenario system data within the airport, a knowledge graph is constructed for each user, including: Determine the user's unique identification information, which represents information that exists in every full-scenario system, and the unique identification information includes at least user identity information; The user data type is determined for each full-scenario system. The user data features include user identity information, user contact information, user order information, user flight information, and user image information. Based on the unique identifier information, heterogeneous association data associated with the unique identifier information is extracted from each full-scene system, and each heterogeneous association data has a time tag; Establish a first association relationship between the unique identifier information and the heterogeneous association data; Based on each user's order information or flight information, the associated users of the user are determined, and each associated user has a time tag; Establish a second association relationship between the user and the associated user; Based on the first association and the second association, construct the user's knowledge graph.

[0007] Furthermore, based on each user's order information or flight information, the associated users of the user are determined, including: Based on the user's order information, other users on the same order are identified and designated as associated users, and / or... Based on the user's total flight information, extract all passenger information from each flight information; Passengers who have taken at least two of the same flights as the user will be identified as associated users.

[0008] Furthermore, based on the characteristics of the lost documents to be recovered, the user information of the target owner is determined, including: When the lost document has a built-in chip, the information from the built-in chip is read to obtain the document characteristics of the lost document; or When the lost certificate does not have a built-in chip, the document features of the lost certificate are obtained based on the image information of the lost certificate. The document features include at least one of the following: the user identification information and document information of the target owner; Based on the document characteristics of the lost certificate, the user information of the target owner is determined.

[0009] Further, based on the image information of the lost document, the document characteristics of the lost document are obtained, including: Obtain multi-view image information of the lost certificate or document; Based on the image information from the multi-view, determine the document type of the lost document; Determine the document feature layout rules corresponding to the document type; Based on the document feature arrangement rules and combined with multi-view image information, the document features of the lost document are determined.

[0010] Furthermore, the user information of the target owner is matched with the knowledge graph to determine the set of contact methods for the target owner, including: Based on the user information of the target owner, a set of search keywords is determined; Based on the set of search keywords, keyword matching is performed from all knowledge graphs, and the knowledge graph that matches completely is determined as the target knowledge graph; The set of contact information for the target owner is determined from the target knowledge graph.

[0011] Furthermore, based on the activity trajectory of the target missing person, a contact strategy is determined from the set of contact information. Based on the time tag and contact attribute of each contact method in the set of contact methods, determine the priority sequence of the contact methods; A set of contact methods is determined by selecting a predetermined number of contact methods from the priority sequence of the contact methods.

[0012] Furthermore, based on the time tag and contact information attributes of each candidate contact method, a priority sequence of contact methods is determined, including: Determine the priority weights of time tags and contact information attributes, wherein the contact information attribute represents the degree of dialogue established with the user, different time tag intervals correspond to different priority weights, and different contact information attributes correspond to different priority weights. Based on the time tag and contact method attributes of each candidate contact method, as well as the priority weight, determine the communication efficiency of each contact method; Based on the communication efficiency of each contact method, a priority sequence for all contact methods is determined.

[0013] Furthermore, when the target owner cannot be contacted through the aforementioned set of contact methods, the method further includes: Identify associated users related to the target owner from the target knowledge graph; Determine the associated knowledge graph of the associated user from the entire knowledge graph, and extract the contact information of the associated user based on the associated knowledge graph; Based on the contact information of the associated user, the lost item information of the target owner is fed back to the associated user.

[0014] On the other hand, this article also provides an airport document lost and found device, the device comprising: The knowledge graph construction module is used to construct a knowledge graph for each user based on data from the full-scenario system in the airport. The full-scenario system includes at least the security check system, the departure system, and the self-service check-in system. The user information determination module is used to determine the user information of the target owner based on the characteristics of the lost documents to be recovered; The contact information set determination module is used to match the user information of the target lost person with the knowledge graph to determine the contact information set of the target lost person; The contact module is used to determine a contact strategy from the set of contact methods based on the activity trajectory of the target owner, so as to notify the target owner based on the contact strategy. The activity trajectory includes the interaction data between the target owner and any full-scene system.

[0015] By employing the above technical solution, the airport document and certificate lost and found method and device described in this paper constructs a knowledge graph for each user based on the full-scene system data in the airport. The full-scene system includes at least the security check system, departure system, and self-service check-in system. Based on the document characteristics of the lost document to be found, the user information of the target owner is determined. The user information of the target owner is matched with the knowledge graph to determine the set of contact methods for the target owner. Based on the activity trajectory of the target owner, a contact strategy is determined from the set of contact methods to notify the target owner. The activity trajectory includes the interaction data between the target owner and any full-scene system. The solution provided in this paper can improve the efficiency and reliability of airport document and certificate lost and found.

[0016] To make the above and other objects, features and advantages of this document more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This document illustrates the steps of a method for finding lost and found airport documents and certificates provided in an embodiment. Figure 2 A schematic diagram of the framework of an airport document lost and found device provided in an embodiment of this article is shown. Detailed Implementation

[0019] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0020] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] In current technology, the recovery of lost and found items at airports generally follows a model where the owner proactively requests the item, and the airport's on-site service department passively accepts and processes the request. This requires passengers to provide extensive supporting documentation, which must be verified before the item can be legally retrieved. While this process can prevent fraudulent claims to some extent, there is still significant room for improvement in terms of customer satisfaction and the efficiency of the processing.

[0022] To address the aforementioned issues, this embodiment provides a method for finding lost and found airport documents and certificates, which can improve the efficiency of such transactions. Figure 1 This document illustrates the steps of a lost and found method for airport documents and certificates provided in this embodiment. While this specification provides the operational steps described in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel. Specifically, as shown... Figure 1 As shown, the method may include: S101: Construct a knowledge graph for each user based on data from the full-scenario system in the airport, wherein the full-scenario system includes at least the security check system, the departure system, and the self-service check-in system; S102: Based on the characteristics of the lost documents to be recovered, determine the user information of the target owner; S103: Match the user information of the target owner with the knowledge graph to determine the set of contact methods for the target owner; S104: Based on the activity trajectory of the target owner, determine a contact strategy from the set of contact methods, and notify the target owner based on the contact strategy. The activity trajectory includes the interaction data between the target owner and any full-scene system.

[0023] This paper can be understood as follows: First, it constructs a knowledge graph of users within the airport based on information input from various operational systems. This allows for rapid indexing and searching of all information for each user. Then, it identifies the target owner's information based on the document characteristics of lost items. Combining this with the pre-constructed knowledge graph, it quickly retrieves the target owner's contact information. Finally, it determines the contact strategy for the target owner based on their activity trajectory within the airport. This approach enables accurate and efficient loss and recovery, improving the efficiency of the process.

[0024] This could involve other passengers at the airport finding the lost document and handing it over to airport staff, who would then retrieve information about the lost document and, based on a finalized contact strategy, directly contact the target owner.

[0025] For example, passenger information may exist in multiple airport information systems. The content and data format of the information stored in each system are very different, and cannot be accessed simply by joining data tables in the database. Moreover, the databases of these information systems may be heterogeneous, including relational databases such as Oracle, MS-SQL, and MySQL, as well as file data based on text files or image files. For instance, security check systems, departure systems, self-service check-in systems, and lost and found systems may all store passenger identification information. Some store the ID card information used during registration, some store the passport information used during the last check-in, and some store the identification number used during the current security check.

[0026] At the same time, even the same passenger's document information stored in different systems can vary greatly. The validity of the documents and the effectiveness of contact information such as mobile phones are different. For example, the airline's self-service check-in system stores the user's registered mobile phone number, but the mobile phone number used to receive SMS verification codes is also stored when checking in online. The emergency contact's mobile phone number is also stored when the bank card is linked to the ticket purchase. Therefore, it is crucial to accurately identify valid contact information.

[0027] In the embodiments of this specification, a knowledge graph for each user is constructed based on full-scene system data in the airport, including: Determine the user's unique identification information, which represents information that exists in every full-scenario system, and the unique identification information includes at least user identity information; The user data type is determined for each full-scenario system. The user data features include user identity information, user contact information, user order information, user flight information, and user image information. Based on the unique identifier information, heterogeneous association data associated with the unique identifier information is extracted from each full-scene system, and each heterogeneous association data has a time tag; Establish a first association relationship between the unique identifier information and the heterogeneous association data; Based on each user's order information or flight information, the associated users of the user are determined, and each associated user has a time tag; Establish a second association relationship between the user and the associated user; Based on the first association and the second association, construct the user's knowledge graph.

[0028] This can be understood as follows: in different scenario systems, users are required to interact, which inevitably involves basic user information, such as name, date of birth, ID card number, passport number, and other core user identity information. One or more of these can be used as the user's unique identifier, such as the combination of name and date of birth. Of course, to avoid duplication with other users, the ID card number can be used as the unique identifier, and so on. It should be noted that this unique identifier must appear in every scenario system, that is, it must serve as the basis for user information input in each scenario system, thereby ensuring the reliability of the knowledge graph construction.

[0029] Furthermore, different scenario systems and user interaction tasks differ, so the data types of users may also differ. For example, a security check system may include user identity information, image information (such as facial features), and user order information; a self-service check-in system includes user identity information and flight information, and may further include all historical flight information and seat information, etc. By clustering data from different scenario systems based on the user's unique identifier information, a user information set is formed. Then, the first association relationship is constructed by combining the relationship between different data and users. It should be noted that the data from different scenario systems has timeliness, that is, it has time tags. Each data is bound to an interaction time point, so the user's status can be updated in a timely manner. For example, if multiple phone numbers exist in multiple scenario systems, the interaction time point corresponding to each phone number can be labeled by combining the time points when different phone numbers are used (i.e., the latest usage time of each phone number, such as registration time, verification code receiving time, etc.).

[0030] For example, security check systems, departure systems, self-service check-in systems, lost and found systems, etc., may all store passengers' identification information. Some store the ID card information used during registration, some store the passport information used during the last check-in, and some store the identification number used during this security check. By combining this information with the facial feature data of passengers that may be stored in each system, the above-mentioned multiple different identification information can be associated with a single passenger.

[0031] In addition to the user's own data, this embodiment of the specification also includes other users who are related to the user in the user's knowledge graph. In this way, even if the user cannot be contacted by their own contact information, they can be contacted again by their related users to help the airport quickly contact the target owner. Therefore, binding related users to the user's knowledge graph can better explore the use value of the knowledge graph, thereby providing a more comprehensive means to accurately contact the target owner.

[0032] In the embodiments of this specification, determining the associated users of a user based on each user's order information or flight information includes: Based on the user's order information, other users on the same order are identified and designated as associated users, and / or... Based on the user's total flight information, extract all passenger information from each flight information; Passengers who have taken at least two of the same flights as the user will be identified as associated users.

[0033] In other words, user order information can be obtained through the booking system of the airport or the airline associated with the airport. Users on the same order must have some kind of relationship, such as relatives, colleagues, or classmates. By contacting one user, there is a high probability that another user can be contacted. Therefore, based on the user's order information, other users who have direct contact with the target owner can be identified and mined. These other users can be treated as related users and bound to the target owner's knowledge graph. Of course, related users also have time tags. That is, the more recent the order information, the more reliable the related users are. Therefore, the newer the order, the more likely the related user has had a recent direct contact with the target owner and the greater the possibility of contacting the target owner.

[0034] In another embodiment, when the user's order information cannot be obtained, or when the user's order information is all their own, the associated user can also be identified by the information of the user's flight. That is, if the associated user and the target owner have taken the same flight multiple times in recent times, the two users are likely to know each other and can be identified as each other's associated users, thereby expanding the ways to identify associated users and improving the possibility and efficiency of contacting the target owner.

[0035] In this embodiment of the specification, the user information of the target owner is determined based on the document characteristics of the lost document to be recovered, including: When the lost document has a built-in chip, the information from the built-in chip is read to obtain the document characteristics of the lost document; or When the lost certificate does not have a built-in chip, the document features of the lost certificate are obtained based on the image information of the lost certificate. The document features include at least one of the following: the user identification information and document information of the target owner; Based on the document characteristics of the lost certificate, the user information of the target owner is determined.

[0036] In other words, appropriate methods can be selected to extract user information based on the type of physical document. For example, documents with built-in chips, such as ID cards and bank cards, can have their features extracted using airport card readers, including user name, place of origin, ID number, bank card number, photo, and fingerprints. On the other hand, for documents without chips, such as household registration books and student IDs (without chips), image scanning is required, followed by image analysis to extract document features. This can be done by taking photos of the documents using mobile phones or document scanners, and then using OCR technology to extract data such as the document number, name, and photo. Alternatively, both methods can be used in parallel. Finally, the information can be clustered to ensure the completeness and reliability of the extracted user information.

[0037] In a further embodiment, obtaining the document characteristics of the lost document based on the image information of the lost document includes: Obtain multi-view image information of the lost certificate or document; Based on the image information from the multi-view, determine the document type of the lost document; Determine the document feature layout rules corresponding to the document type; Based on the document feature arrangement rules and combined with multi-view image information, the document features of the lost document are determined.

[0038] This can be understood as follows: In order to improve the completeness of user information extraction from lost certificates and documents, for lost certificates and documents without chips, the type of certificate or document can be determined based on the appearance of the certificate or the arrangement of information in the certificate. For example, a household registration booklet is in booklet form, and the information in the user information page is arranged in a certain format. In this way, the type of certificate or document can be determined first, and then the information layout rules of the certificate type can be matched with the image information captured by the camera. This allows for the rapid extraction of certificate features, improving the accuracy and completeness of certificate feature extraction.

[0039] In this embodiment of the specification, the user information of the target lost person is matched with the knowledge graph to determine the set of contact methods for the target lost person, including: Based on the user information of the target owner, a set of search keywords is determined; Based on the set of search keywords, keyword matching is performed from all knowledge graphs, and the knowledge graph that matches completely is determined as the target knowledge graph; The set of contact information for the target owner is determined from the target knowledge graph.

[0040] The target owner's user information includes all feature data that can identify user characteristics, such as name, ID number, mobile phone number, bank card number, facial image, etc. These features need to be matched with a knowledge graph. When all features can be matched, the matching knowledge graph is used as the target knowledge graph of the target owner. Then, the target knowledge graph is used to query all the target owner's contact information, including but not limited to: email, mobile phone number, and landline number.

[0041] Furthermore, based on the activity trajectory of the target owner, a contact strategy is determined from the set of contact information, including: Based on the time tag and contact attribute of each contact method in the set of contact methods, determine the priority sequence of the contact methods; A set of contact methods is determined by selecting a predetermined number of contact methods from the priority sequence of the contact methods.

[0042] This can be understood as follows: when there are multiple contact methods, such as the mobile phone number that received the SMS verification code during the last check-in, the mobile phone number or email address registered during user registration, or the called number in the contact record after the lost item was lost last month, etc. These contact methods can also be associated with a single passenger in a similar way. It is necessary to determine that at least one valid method can directly contact the target owner. Therefore, the embodiments of this specification consider the time stamp and contact method attributes as factors to select the reliable contact method. The time stamp represents the timestamp of the user's interaction with any scenario system in the airport using the contact method. Preferably, it should be the timestamp of the most recent interaction. Of course, the timestamps of each contact method in the entire interaction process with the airport scenario system can also be used as a time chain and bound to the contact method. The longer the time chain, the higher the frequency of the user's use of the contact method. The more recent the interaction timestamp, the greater the probability that the user is still using the contact method.

[0043] In addition, the contact information attribute indicates the directness of establishing a dialogue with the user. For example, mobile phone numbers are the most direct, allowing direct dialogue with the user; email is next, as users need to check their email to see contact information, and if the email does not have a notification function, it is difficult to contact the user directly; landline is the worst, as users need to be in a specific area to receive a call.

[0044] By taking into account both time tags and contact information attributes, a priority sequence of all contact methods is obtained. The higher the priority, the greater the likelihood that the target owner can be contacted directly. For example, the top three contact methods in the priority sequence can be selected to contact the target owner in order to increase the likelihood of contacting the target owner.

[0045] Furthermore, based on the time tag and contact information attributes of each candidate contact method, a priority sequence of contact methods is determined, including: Determine the priority weights of time tags and contact information attributes, wherein the contact information attribute represents the degree of dialogue established with the user, different time tag intervals correspond to different priority weights, and different contact information attributes correspond to different priority weights. Based on the time tag and contact method attributes of each candidate contact method, as well as the priority weight, determine the communication efficiency of each contact method; Based on the communication efficiency of each contact method, a priority sequence for all contact methods is determined.

[0046] For example, as described above, mobile phone numbers have the highest degree of direct contact with users, allowing for direct conversations, and their weight can be set to 1; email is next, as users need to check their email to see contact information, and if the email does not have a notification function, it is difficult to contact users directly, so its weight can be set to 0.8; landline is the worst, as users need to be in a specific area to receive calls, so its weight can be set to 0.5.

[0047] Priority weights are set for different time tags. For example, the weight of the interaction timestamp in the most recent hour is set to 1, the weight between 1 and 6 hours is set to 0.8, and the weight between 6 hours and 3 days is set to 0.5. Different priority weights are set in this way. Finally, the priority weights of the timestamps and the priority weights of the contact method attributes are summed to obtain the communication efficiency of each contact method. The communication efficiency represents the probability of directly contacting the target owner. The higher the communication efficiency, the greater the probability of contacting the target owner.

[0048] In this embodiment of the specification, when the target owner cannot be contacted through the set of contact methods, the method further includes: Identify associated users related to the target owner from the target knowledge graph; Determine the associated knowledge graph of the associated user from the entire knowledge graph, and extract the contact information of the associated user based on the associated knowledge graph; Based on the contact information of the associated user, the lost item information of the target owner is fed back to the associated user.

[0049] This can be understood as follows: when the target owner's contact information is invalid, meaning it is impossible to directly contact the target owner, we can try to contact the target owner through their associated users. Specifically, we can use the knowledge graph corresponding to the target user to identify their associated users. Of course, associated users also have time tags. The associated user with the latest timestamp indicates that they may have had an intersection with the target owner at the latest time. Therefore, the associated user with the latest timestamp can be selected as the priority user. If the target owner cannot be contacted even with higher priority associated users, then associated users can be determined in order of their timestamps.

[0050] Furthermore, each associated user has its corresponding knowledge graph. Therefore, when an associated user is identified, their knowledge graph can be extracted, and their set of contact information can be determined. The method for determining the set of contact information is similar to that for determining the target owner's set of contact information, and will not be described in detail here. Finally, the associated user is contacted using the identified contact information to reach the target owner and provide detailed information about the lost item.

[0051] The lost and found method for documents provided in this specification extracts document features from user information in the lost documents, then uses a pre-constructed user knowledge graph to perform feature matching to determine the contact information of the target owner, and finally selects the optimal contact method to contact the target owner based on the interaction process between the target owner and the airport system. This improves the efficiency and reliability of contacting the target owner, automates the entire lost and found process, greatly reduces manual intervention, significantly improves processing efficiency, and enhances passenger satisfaction.

[0052] On the other hand, this article also provides an airport document and certificate lost and found device, such as... Figure 2 As shown, the device includes: The knowledge graph construction module 210 is used to construct a knowledge graph for each user based on the full-scenario system data in the airport, wherein the full-scenario system includes at least the security check system, the departure system, and the self-service check-in system; The user information determination module 220 is used to determine the user information of the target owner based on the document characteristics of the lost property to be found; The contact information set determination module 230 is used to match the user information of the target lost owner with the knowledge graph to determine the contact information set of the target lost owner; The contact module 240 is used to determine a contact strategy from the set of contact methods based on the activity trajectory of the target owner, so as to notify the target owner based on the contact strategy. The activity trajectory includes the interaction data between the target owner and any full-scene system.

[0053] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0054] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0055] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0056] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0057] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0058] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0059] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0060] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0062] This document uses specific embodiments to illustrate the principles and implementation methods of this document. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this document. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this document. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A method for finding lost and found items such as airport documents, characterized in that, The method includes: Based on data from the airport's full-scenario system, a knowledge graph is constructed for each user. The full-scenario system includes at least the security check system, the departure system, and the self-service check-in system. Based on the characteristics of the lost documents and certificates to be recovered, the user information of the target owner can be determined; The user information of the target lost person is matched with the knowledge graph to determine the set of contact methods of the target lost person; Based on the activity trajectory of the target owner, a contact strategy is determined from the set of contact methods to notify the target owner. The activity trajectory includes the interaction data between the target owner and any full-scene system.

2. The method according to claim 1, characterized in that, Based on full-scenario system data within the airport, a knowledge graph is constructed for each user, including: Determine the user's unique identification information, which represents information that exists in every full-scenario system, and the unique identification information includes at least user identity information; The user data type is determined for each full-scenario system. The user data features include user identity information, user contact information, user order information, user flight information, and user image information. Based on the unique identifier information, heterogeneous association data associated with the unique identifier information is extracted from each full-scene system, and each heterogeneous association data has a time tag; Establish a first association relationship between the unique identifier information and the heterogeneous association data; Based on each user's order information or flight information, the associated users of the user are determined, and each associated user has a time tag; Establish a second association relationship between the user and the associated user; Based on the first association and the second association, construct the user's knowledge graph.

3. The method according to claim 2, characterized in that, Based on each user's order information or flight information, the associated users of the user are determined, including: Based on the user's order information, other users on the same order are identified and designated as associated users, and / or... Based on the user's total flight information, extract all passenger information from each flight information; Passengers who have taken at least two of the same flights as the user will be identified as associated users.

4. The method according to claim 1, characterized in that, Based on the characteristics of the lost documents, determine the user information of the target owner, including: When the lost document has a built-in chip, the information from the built-in chip is read to obtain the document characteristics of the lost document; or When the lost certificate does not have a built-in chip, the document features of the lost certificate are obtained based on the image information of the lost certificate. The document features include at least one of the following: the user identification information and document information of the target owner; Based on the document characteristics of the lost certificate, the user information of the target owner is determined.

5. The method according to claim 1, characterized in that, Based on the image information of the lost document, the document characteristics of the lost document are obtained, including: Obtain multi-view image information of the lost certificate or document; Based on the image information from the multi-view, determine the document type of the lost document; Determine the document feature layout rules corresponding to the document type; Based on the document feature arrangement rules and combined with multi-view image information, the document features of the lost document are determined.

6. The method according to claim 1, characterized in that, The user information of the target lost person is matched with the knowledge graph to determine the set of contact information for the target lost person, including: Based on the user information of the target owner, a set of search keywords is determined; Based on the set of search keywords, keyword matching is performed from all knowledge graphs, and the knowledge graph that matches completely is determined as the target knowledge graph; The set of contact information for the target owner is determined from the target knowledge graph.

7. The method according to claim 1, characterized in that, Based on the activity trajectory of the target missing person, a contact strategy is determined from the set of contact information, including: Based on the time tag and contact attribute of each contact method in the set of contact methods, determine the priority sequence of the contact methods; A set of contact methods is determined by selecting a predetermined number of contact methods from the priority sequence of the contact methods.

8. The method according to claim 7, characterized in that, Based on the time tag and contact information attributes of each candidate contact method, a priority sequence for the contact methods is determined, including: Determine the priority weights of time tags and contact information attributes, wherein the contact information attribute represents the degree of dialogue established with the user, different time tag intervals correspond to different priority weights, and different contact information attributes correspond to different priority weights. Based on the time tag and contact method attributes of each candidate contact method, as well as the priority weight, determine the communication efficiency of each contact method; Based on the communication efficiency of each contact method, a priority sequence for all contact methods is determined.

9. The method according to claim 6, characterized in that, When the target owner cannot be contacted through the aforementioned set of contact methods, the method further includes: Identify associated users related to the target owner from the target knowledge graph; Determine the associated knowledge graph of the associated user from the entire knowledge graph, and extract the contact information of the associated user based on the associated knowledge graph; Based on the contact information of the associated user, the lost item information of the target owner is fed back to the associated user.

10. An airport lost and found device for documents and certificates, characterized in that, The device includes: The knowledge graph construction module is used to construct a knowledge graph for each user based on data from the full-scenario system in the airport. The full-scenario system includes at least the security check system, the departure system, and the self-service check-in system. The user information determination module is used to determine the user information of the target owner based on the characteristics of the lost documents to be recovered; The contact information set determination module is used to match the user information of the target lost person with the knowledge graph to determine the contact information set of the target lost person; The contact module is used to determine a contact strategy from the set of contact methods based on the activity trajectory of the target owner, so as to notify the target owner based on the contact strategy. The activity trajectory includes the interaction data between the target owner and any full-scene system.

Images