Method and hybrid device for validating transactions based on the comparison of two character strings

Abstract

The method for validating a transaction compares a candidate character string (Cc) with a reference string (Cr), representing names of countries, persons or organizations. The method uses: · a primary block (Bs) that determines an initial score (Si) based on rules or a lightweight model and then compares this score to predefined domains for immediate validation (Da), non-validation (Dna), and control (Dc); and · an expert block (Be) that uses complex AI to determine a similarity score (Sc) with complex rules and advanced models. The method generates a validation status (A) or non-validation status (NA) based on these scores, and activates the expert block if necessary to obtain a similarity validation (Ds).

Description

Hybrid method and device for transaction validation based on the comparison of two strings Scope of the invention

[0001] The present invention relates to a hybrid device for validating a transaction by comparing a string of characters, called the candidate string, with a string of characters, called the reference string. It also relates to an associated method. Previous art

[0002] Verifying the correspondence between two names, whether of people or organizations, is an essential function in many applications ranging from database management to security protocols.

[0003] In the payments industry, there is a wide range of use cases that require robust name matching.

[0004] For example, instant verification of payment names: in many fraud scenarios, a fraudster lies about their name to a victim in order to deceive them. The ability to compare the entered name to the real name associated with an IBAN is therefore crucial to preventing this type of fraud.

[0005] Money laundering can also be more easily avoided if account holder names can be verified before each transaction.

[0006] Furthermore, preventing blacklisted users from making transactions requires checking a cardholder's name against public sanctions lists to prevent money laundering and criminal activity.

[0007] A name matching process must be able to handle a very diverse set of matching cases: matching names with typographical errors or omitted characters: e.g., Sarah / Sarag, Kjel / Kjeld; matching homonyms, e.g., Kristof / Christophe; matching synonyms, e.g., Kristof / Christophe; detecting and ignoring titles, e.g., Mr / Dr / Ms…; detecting matches with initials; detecting matches with duplicate surnames; processing data relating to legal entities (BV, NV, SA, etc.).

[0008] A name matching process must respect constraints of time, cost and linguistic variability for each matching operation.

[0009] One idea that is at the heart of the invention is the observation that these matching operations are complex, lengthy and energy-intensive to process.

[0010] A device and a process is proposed applying an original method of validating a transaction by comparing a string of characters, called candidate, with a string of characters, called reference, the two strings of characters transcribing names of countries or people or organization, comprising: a processing block called primary, and a processing block called expert including an artificial intelligence module, called complex.

[0011] The device and method are configured to generate a transaction validation state for the case where an initial comparison score belongs to a predetermined immediate validation domain, generate a transaction non-validation state for the case where said initial comparison score belongs to a predetermined immediate non-validation domain, activate the expert processing block when said initial comparison score belongs to a predetermined control domain, generate a validation state when the similarity score belongs to a predetermined similarity validation domain.The primary processing block is configured to: determine the initial comparison score of the two strings, the comparison score being determined on the basis of a set of predefined rules or a lightweight machine learning model, then compare said initial comparison score with a predetermined domain called immediate validation, a predetermined domain called non-immediate validation and a predetermined domain called control.

[0012] The expert processing block is configured to: determine a similarity score for the two strings, the comparison similarity score being determined using a combination of complex rules and advanced machine learning models,

[0013] The device and method are configured to generate a transaction validation state for the case where said initial comparison score belongs to the predetermined immediate validation domain, generate a transaction non-validation state for the case where said initial comparison score belongs to the predetermined immediate non-validation domain, activate the expert processing block when said initial comparison score belongs to the predetermined control domain, generate a validation state when the similarity score belongs to a predetermined domain called similarity validation.

[0014] The hybrid device / method improves efficiency by employing the primary block for the rapid resolution of primary name-matching scenarios, thus conserving computing resources.

[0015] The device / method ensures the robustness and accuracy of name matching by using the expert block for the most difficult cases, which the primary block cannot solve.

[0016] The two-block device / method is scalable, enabling the device to handle a wide range of complexities in multilingual name searching without compromising speed or accuracy.

[0017] The hybrid device / method offers the advantage of modularity, allowing the inclusion of a primary block and a complex expert block. This modularity enables the device to quickly resolve cases of primary and common name matching, while also handling more complex matching scenarios.

[0018] The device / method can be configured to return a suggested string of characters when the similarity score belongs to a predetermined domain called the similarity suggestion domain.

[0019] The suggested string of characters can be determined from an entry in a pre-existing database.

[0020] The device / method according to the invention can be configured to generate an invalidation state, when after the suggested string has been returned, the expert processing block is activated during a comparison of another candidate string with the reference string, and the similarity score of said other candidate string and the reference string does not belong to the similarity validation domain.

[0021] The suggested string of characters can be determined from an entry in a database.

[0022] Advantageously, the primary processing block is further configured to preprocess strings corresponding to names by converting them to lowercase and removing strings corresponding to common titles

[0023] Preprocessing names according to a uniform case and removing common titles normalizes the input data, which can significantly reduce the complexity of the matching process.

[0024] The initial preprocessing step can improve device performance by reducing the risk of false matches due to case sensitivity or irrelevant title information.

[0025] Simplifying input data through preprocessing can lead to faster processing times for the primary block, thereby improving the overall throughput of the device.

[0026] Preferably, the primary processing block identifies and replaces initials in character strings with corresponding full names.

[0027] By converting initials into full names, the system can improve the accuracy of matches, particularly in cases where abbreviations can be a source of ambiguity or confusion. The conversion involves searching the reference string for a word that begins with the same letter as an initial present in the target string, and if so, performing the replacement.

[0028] This feature can improve the user experience by reducing the number of potential false negatives, thereby increasing the reliability of the name matching process.

[0029] The expert processing block can use semantic embedding models to generate vector representations of names and compare the vectors to determine the complex similarity score.

[0030] Including semantic embedding models in the expert block offers the advantage of automation. These models generate vector representations of names. It is then possible to determine a similarity score from these representations (for example, using a distance calculation), thus automating the process of determining name matches without manual intervention.

[0031] The use of semantic embedding models to create vector representations allows for a nuanced comparison of names, capturing semantic similarities that may not be apparent in a direct comparison of character strings.

[0032] Generating similarity scores based on vector comparisons allows the device to more effectively manage orthographic and phonetic variations of names, as well as cases of transliteration (transcription of a name into a different writing system).

[0033] Vector representations facilitate the matching of names in different languages ​​and scripts, which is particularly useful in a multilingual context.

[0034] Advantageously, the expert processing block can include a language detection function to identify and adjust transliteration cases. The adjustment involves a language detection step followed by transcription of the candidate character string into a target (Latin) alphabet.

[0035] This offers the advantage of heterogeneity. This function allows the system to identify and adjust for transliteration cases, where names can be written differently in different languages. By taking linguistic variations into account, the system can more efficiently handle multilingual name matching.

[0036] By identifying the language of the names, the device can apply language-specific processing rules, which improves the accuracy of the matching process.

[0037] Adjusting transliteration cases ensures that the device remains effective even when dealing with names that have been converted from one writing system to another, which is common in a globalized environment.

[0038] Preferably, the primary processing block also includes a calculation component configured to return a matching score between two paired strings.

[0039] Providing a matching score indicating the determination of the match allows for a quantifiable evaluation of the results, which can be critical for applications requiring high accuracy, such as identity verification or data deduplication.

[0040] The matching score allows the device to rank potential matches, facilitating user review and further analysis, thereby improving the efficiency of manual verification processes.

[0041] The calculation component can implement the Levenshtein distance between the two strings.

[0042] Using Levenshtein distance ensures that the matching score reflects the true similarity between character strings, thus improving the reliability of the matching process.

[0043] The matching score can be the one returned for the identity of two strings when the Levenshtein distance is less than a predetermined threshold.

[0044] The predetermined threshold for the Levenshtein distance allows the device to avoid false positives that can occur in the case of minor spelling variations or common typographical errors in a string of characters, thus improving the accuracy of the device.

[0045] The processing block system can be configured to rearrange the components of a name in order to minimize Levenshtein distance and facilitate matching

[0046] Reorganizing the components of a name to minimize Levenshtein distance can significantly improve matching accuracy for multicultural or multilingual datasets where name order may vary, thus ensuring better quality data normalization.

[0047] The ability to facilitate matching by minimizing the Levenshtein distance can reduce the need to manually correct or normalize data, saving time and resources in data processing workflows. Brief description of the figures

[0048] Other features and advantages of the invention will become apparent during the reading of the detailed description which follows, for the understanding of which reference will be made to the attached drawings on which: is a schematic view of a hybrid device according to the invention; is another schematic view of the hybrid device. Detailed description of the invention

[0049] The present invention relates to a hybrid device (D) designed to validate a transaction by comparing a string of characters Sc, called candidate, with a string of characters Sr, called reference, the two strings of characters transcribing names of countries, people, organizations or others.

[0050] The device comprises two parts: a primary processing block Bs equipped to handle primary matching tasks, and an expert processing block Be configured to handle the most complex name matching scenarios.

[0051] The first element of the invention is the primary processing block Bs, which can be a carefully crafted set of rules or a lightweight machine learning model.

[0052] The primary goal of the Bs block is to accelerate the name matching process by quickly resolving the most common and basic cases, such as exact matches or variations due to typographical errors. This first line of defense in the name matching sequence allows for the immediate determination and return of matching results when possible, significantly improving the system's efficiency.

[0053] The primary processing block is configured to: determine an initial Si score for comparison of the two strings, the comparison score being determined on the basis of a set of predefined rules or a lightweight machine learning model, then compare said initial Si score with a predetermined domain Da called immediate validation, a predetermined domain Dna called non-immediate validation and a predetermined domain Dc called control.

[0054] The so-called expert processing block Be includes a complex artificial intelligence module Mi, configured to: determine a similarity score Sc of the two strings of characters, the comparison similarity score being determined using a combination of complex rules and advanced machine learning models.

[0055] The hybrid device D is configured to: generate a validation state A of the transaction for the case where said initial comparison score belongs to the predetermined immediate validation domain Da, generate a non-validation state Na of the transaction for the case where said initial comparison score belongs to the predetermined immediate non-validation domain Dna, activate the expert processing block Be when the initial comparison score Si belongs to the predetermined control domain, generate a validation state A when the similarity score belongs to a predetermined domain Ds called similarity validation.

[0056] When the primary block Bs fails to find a match, the task is transferred to the second block: the expert block Be. This sophisticated level consists of a combination of complex rules and high-level machine learning models. Semantic embedding models can be used to compare homonyms and multilingual names, using the distance between vectors as a similarity score. Language detection and transcription to a common Latin alphabet can also be used to handle transliteration cases. The expert block considers linguistic nuances and cultural contexts to distinguish similar names with high accuracy.

[0057] The cornerstone of this invention is the collaboration between the primary and complex blocks of artificial intelligence. The former acts as a filter, resolving primary cases and passing only the complex cases to the latter, thus saving computing resources and time. This multi-layered approach allows the Hybrid D device to remain lightweight and fast without compromising its ability to handle complex matching tasks.

[0058] The diagram shown above comprises two primary blocks representing the main components of the system: Reference Bs. "Primary Processing Block" — represented by a rectangular block at the top, this block is responsible for the initial filtering and processing of names based on predefined rules or a lightweight machine learning model. This block corresponds to the first part of the system, which handles cases of primary and common name matches. Reference Be. "Expert Processing Block" — represented by a rectangular block below the primary block, this sophisticated block undertakes further name processing using complex rules and advanced machine learning models when the primary AI block is insufficient to find a match.

[0059] In addition, three outcome states are described in the diagram: Reference A — "Validation" — an oval shape suggests a successful matching result when a match is determined, Reference NA — "Non-Validation" — an oval shape indicates a negative result when it is determined that there is no match, Reference SC — "Suggest Correction" — another oval shape indicates a negative result when a match is determined.

[0060] Thus, the diagram allows visualization of the overall process and decision flow of the device for matching multilingual names.

[0061] The device is preferably of an electronic type comprising at least one processor (CPU) and a non-transient memory containing instructions which, when executed by the processor, configure the device to: a) receive, via a digital communication interface, a candidate character string (Cc) and a reference character string (Cr) representing respectively a country name, a person's name, or an organization's name; b) calculate, in a primary processing block (Bs) implemented in hardware or software executed by the processor, an initial score (Si) for comparing said strings using a set of predefined rules or a lightweight machine learning model stored in memory; c) compare, by the processor, the initial score (Si) to: a first domain of values ​​(Da) called immediate validation; a second domain of values ​​(Dna) called non-immediate validation; a third domain of values ​​(Dc) called control;d) automatically generate a validation state (A) and store it in memory or transmit it over the network when the initial score (Si) belongs to the domain (Da); e) automatically generate a non-validation state (NA) when the initial score (Si) belongs to the domain (Dna); f) activate, by emitting an internal digital signal, an expert processing block (Be) comprising a complex artificial intelligence module (Mi) executed by the processor or reconfigurable logic circuits, when the initial score (Si) belongs to the domain (Dc), then calculate a similarity score (Sc) between the two strings using a combination of complex rules and advanced machine learning models; g) automatically generate the validation state (A) when the similarity score (Sc) belongs to a predetermined domain (Ds) called the similarity validation domain.

[0062] all steps b) to g) are executed in a fully automated manner by technical means of digital data processing, without human intervention, so that the validation of the transaction relies exclusively on the hardware and software resources of the electronic device, resulting in a measurable reduction in processing latency.

[0063] Technical aspects of transaction validation

[0064] Validation begins with the receipt of a message structured according to a banking standard: ISO 8583 for card payments or ISO 20022 for bank transfers. These formats require numbered fields and bitmaps that unambiguously define the length and type of each piece of data, thus guaranteeing interoperability between terminal, acquirer, and issuer.

[0065] Before any decision is made, the system calculates or verifies a Message Authentication Code (MAC) or an EMV cryptogram (ARQC) on the critical fields of the message. This operation is performed in a PCI PTS-certified hardware security module (HSM), which holds the AES / RSA keys and prevents any physical extraction. Any alteration of a single byte triggers an error code and the automatic rejection of the transaction.

[0066] To eliminate malicious duplication, each message contains a unique identifier or nonce and / or a timestamp; the server maintains a time window and rejects any frame that has already been seen or is outside the time limit ΔT. These mechanisms neutralize replay attacks, which consist of replaying a legitimate transmission to cause double spending or impersonate someone.

[0067] These operations solve concrete technical problems: data integrity in transit, key confidentiality, duplicate exclusion, and latency control. They rely on specific hardware and software resources (standardized formats, cryptographic algorithms, HSMs), creating measurable technical effects (rejection of a falsified message, reduction of cycle time).

[0068] Of course, the invention is not limited to the examples just described, and many modifications can be made to these examples without departing from the scope of the invention. Furthermore, the various features, forms, variants, and embodiments of the invention can be combined in various ways, provided they are not incompatible or mutually exclusive.

Claims

A method (P) for validating a transaction, implemented by a transaction validation device, based on the comparison of a character string (Cc), called the candidate string, with a character string (Cr), called the reference string, the two character strings transcribing the names of countries, people, or organizations, the method implementing: a processing block (Bs) called the primary block configured to: determine a score (Si), called the initial score, for comparing said two character strings, the comparison score being determined on the basis of a set of predefined rules or a lightweight machine learning model, then compare said initial comparison score with a predetermined domain (Da) called the immediate validation domain, a predetermined domain (Dna) called the non-immediate validation domain, and a predetermined domain (Dc) called the control domain; a processing block (Be) called the expert block comprising an artificial intelligence module (Mi), called the complex block.configured to: determine a score (Sc), called the similarity score, of said two strings, the comparison similarity score being determined using a combination of complex rules and advanced machine learning models, the process comprising: a step of generating a validation state (A) of the transaction for the case where said initial comparison score belongs to the predetermined domain of immediate validation, a step of generating a non-validation state (NA) of the transaction for the case where said initial comparison score belongs to the predetermined domain of immediate non-validation, a step of activating the expert processing block when said initial comparison score belongs to the predetermined control domain, a step of generating a validation state (A) when the similarity score belongs to a predetermined domain (Ds) called the similarity validation domain. Method according to the preceding claim, comprising a step of returning a string of characters (Sc), said to be suggested, when the similarity score belongs to a predetermined domain called similarity suggestion. A method according to the preceding claim, wherein the suggested character string (Sc) is determined from an entry in a database (Bd). A method according to one of the two preceding claims, further configured to generate an invalidation state (Na), where after the suggested string has been returned, the expert processing block (Be) is activated when comparing another candidate string with the reference string, and the similarity score of said other candidate string and the reference string does not belong to the similarity validation domain. A method according to any one of the preceding claims in which the primary processing block (Bs) identifies and replaces, in character strings, the initials with corresponding full names. A method according to any one of the preceding claims, wherein the expert processing block uses semantic embedding models to generate vector representations of names and compare the vectors to determine the complex similarity score. A method according to any one of the preceding claims, wherein the expert processing block (Be) includes a language detection function for identifying and adjusting transliteration cases. A method according to any one of the preceding claims, wherein the primary processing block further comprises a computation component (C) configured to return a matching score between two paired strings. A method according to the preceding claim, wherein the primary processing block (Bs) is configured to rearrange the components of a name in order to minimize the Levenshtein distance and facilitate matching. Device (D) for validating a transaction by comparing a string of characters (Cc), called the candidate string, with a string of characters (Cr), called the reference string, the two strings of characters transcribing the names of countries or people, said device comprising: a processing block (Bs) called the primary block configured to: determine a score (Si), called the initial score, for comparing said two strings of characters, the comparison score being determined on the basis of a set of predefined rules or a lightweight machine learning model, then comparing said initial comparison score with a predetermined domain (Da) called the immediate validation domain, a predetermined domain (Dna) called the non-immediate validation domain and a predetermined domain (Dc) called the control domain, a processing block (Be) called the expert block comprising an artificial intelligence module (Mi), called the complex block, configured to: determine a score (Sc), called the similarity score, for said two strings of characters,The comparison similarity score is determined using a combination of complex rules and advanced machine learning models. The device is configured to generate a transaction validation state (A) if the initial comparison score falls within the predetermined immediate validation domain, a transaction non-validation state (NA) if the initial comparison score falls within the predetermined immediate non-validation domain, the expert processing block activates when the initial comparison score falls within the predetermined control domain, and a validation state (A) is generated when the similarity score falls within a predetermined domain (Ds) known as the similarity validation domain.

Images