Bank name identification method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a bank name identification method, electronic equipment, a storage medium and a program product, and relates to the technical field of financial science and technology, the method comprises the following steps: obtaining a to-be-processed bank name text, and carrying out word segmentation processing on the bank name text to obtain a first entry set; screening bank name entries matched with the original entries in the first entry set from a bank name database to obtain a second entry set; retrieving bank names in a bank name database by adopting bank name entries in the second entry set to obtain a candidate bank name set; and screening a bank name matched with the bank name text from the candidate bank name set to obtain a target bank name. Through word segmentation processing and bank name database matching, the bank names matched with the text can be accurately screened out, a user does not need to manually input or search for complete and accurate bank names one by one, the system carries out automatic processing and recognition, the operation process is simplified, and the error possibility is reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of financial technology, and in particular to a bank name recognition method, electronic device, storage medium and program product. Background Technology

[0002] In interbank transactions, users typically need to manually enter or select the accurate bank name from a drop-down menu. For example, when making an interbank transfer, it's crucial to ensure that the recipient's name, account number, and bank name are all correct for the funds to be successfully credited. If the bank name is entered incorrectly, even if the account number is correct, the funds will not be credited and will be returned.

[0003] However, not all banks' online or mobile banking systems provide complete and accurate bank name information display and search functions. This makes it difficult for users to find the correct bank name, increasing the complexity of operations and the possibility of errors. Furthermore, different banks' online or mobile banking systems vary in their bank name information display and search methods. This lack of a unified standard forces users to adapt to different interfaces and processes when conducting cross-bank transactions, increasing the learning curve and difficulty of use. Summary of the Invention

[0004] This invention provides a bank name recognition method, electronic device, storage medium, and program product, which can achieve intelligent recognition of bank names, improve the accuracy of bank name recognition, and improve the overall efficiency of interbank transactions.

[0005] In a first aspect, the bank name recognition method provided in the embodiments of the present invention includes:

[0006] Obtain the bank name text to be processed, and perform word segmentation on the bank name text to obtain the first word set;

[0007] The second set of terms is obtained by filtering bank name terms from the bank name database that match the original terms in the first term set;

[0008] The bank name entries in the second term set are used to retrieve bank names from the bank name database to obtain a candidate bank name set.

[0009] The target bank name is obtained by filtering out bank names that match the text of the bank name from the candidate bank name set.

[0010] Secondly, the electronic device provided in the embodiments of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the bank name recognition method as described in any embodiment of the present invention.

[0011] Thirdly, the computer-readable storage medium provided in the embodiments of the present invention stores a computer program thereon, which, when executed by a processor, implements the bank name recognition method as described in any embodiment of the present invention.

[0012] Fourthly, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the bank name recognition method as described in any embodiment of the present invention.

[0013] In this embodiment of the invention, intelligent recognition of bank names is achieved by utilizing technologies such as word segmentation and database matching. Users do not need professional banking knowledge or to memorize a large number of bank names. The system's intelligent processing makes operation simpler and easier, allowing even users unfamiliar with banking systems to easily complete interbank transactions. Through efficient word segmentation and matching algorithms, the system can quickly filter target bank names from a vast database, significantly shortening the time for bank name recognition and matching, improving the overall efficiency of interbank transactions, and reducing transaction delays and failures caused by information errors. This invention is applicable to various forms of bank name input. Whether the bank name text is manually entered by the user or obtained through other means, as long as it has undergone word segmentation, it can be accurately recognized and matched using the method of this invention, demonstrating strong flexibility and adaptability. Users do not need to manually enter complete and accurate bank names, nor do they need to search and select from lengthy drop-down menus. The system's automatic processing and recognition greatly simplifies the user's operation process and reduces the possibility of errors. Especially when faced with a large number of bank names, it can quickly locate the target bank, saving users time and effort. Furthermore, the bank name recognition method of the present invention is universal and is not affected by the differences in online banking or mobile banking systems of different banks. When conducting cross-bank transactions, users do not need to adapt to different operating interfaces and processes, which greatly reduces the learning cost and improves the convenience and smoothness of use. Attached Figure Description

[0014] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart illustrating a bank name recognition method provided in an embodiment of the present invention;

[0016] Figure 2 This is another flowchart illustrating the bank name recognition method provided in this embodiment of the invention;

[0017] Figure 3 This is an example diagram of the bank name recognition method provided in an embodiment of the present invention;

[0018] Figure 4 This is a schematic diagram of a bank name recognition device provided in an embodiment of the present invention;

[0019] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 of the invention 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 non-exclusive inclusion; for example, a process, method, system, product, or apparatus 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 apparatus.

[0022] Figure 1 This is a flowchart illustrating a bank name recognition method provided in an embodiment of the present invention. This method is applicable to scenarios where interbank transactions require bank name recognition. The bank name recognition method can be executed by a bank name recognition device provided in this embodiment, which can be implemented using software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, such as a computer or server corresponding to a bank platform. The electronic device can have applications or software supporting interbank transactions installed, allowing users to initiate interbank transactions. The following embodiment illustrates the integration of a bank name recognition device into an electronic device. (See also...) Figure 1 The bank name recognition method in this embodiment may include the following steps:

[0023] Step 101: Obtain the bank name text to be processed, and perform word segmentation on the bank name text to obtain the first set of terms.

[0024] The bank name text to be processed refers to the text of the bank name that needs to be recognized and matched. It can be text manually input by the user or text obtained by converting the user's speech through speech recognition technology. Word segmentation is the process of splitting a complete text string into individual words or phrases according to certain rules and semantics. In Chinese processing, word segmentation is to decompose continuous text into meaningful units for subsequent analysis and processing. The first set of terms is a set of words or phrases obtained through word segmentation. These terms are extracted from the bank name text and are used for subsequent matching and searching in the database.

[0025] Specifically, after obtaining the bank name text to be processed, text cleaning can be performed first. For example, special characters and symbols can be removed, extra spaces can be removed, spelling mistakes can be corrected, etc. to improve the text quality. Then, according to language rules and semantic logic, the continuous text is split into independent words or phrases. Finally, stop words can be removed. Stop words refer to words that frequently appear in the text but usually do not contain important information, such as "de" (的), "shi" (是), "he" (和), "zai" (在), "le" (了), "wo" (我), etc. The stop words can be removed from the text by referring to the stop word list, reducing the data volume and improving the processing efficiency, and at the same time making the subsequent analysis more focused on meaningful words. After removing the stop words, the remaining words form the first set of terms.

[0026] Through preprocessing such as text cleaning, word segmentation, and stop word removal, the quality of the text data can be improved, making it more suitable for subsequent analysis and processing.

[0027] Step 102: Screen out the bank name terms in the bank name database that match the original terms in the first set of terms to obtain the second set of terms.

[0028] The bank name database is a database that stores a large number of bank names and related information. Each bank name can be a complete bank name or a collection of multiple terms or keywords. The purpose of the bank name database is to provide basic data support for subsequent matching and searching. The original terms are words or phrases in the first term set, extracted from the bank name text without further processing or modification. Bank name terms are words or phrases extracted from the bank name database and used to match the original terms in the first term set. Each bank name term can be a single word or a phrase. The second term set is a collection of bank name terms selected from the bank name database that match the original terms in the first term set. This set is obtained through matching operations and is used for further retrieval and analysis.

[0029] Keyword matching algorithms can be used to compare the preprocessed original terms with bank name terms in the database one by one. Exact matching can be used, where only completely identical terms are considered a successful match; alternatively, fuzzy matching can be used, allowing a certain degree of similarity (such as containing some identical characters or slight spelling differences), with a similarity threshold set to determine whether a match exists. For fuzzy matching, the similarity between the original terms and terms in the database can be calculated, using algorithms such as cosine similarity and edit distance to quantify the similarity between the two terms, and terms with higher similarity can be filtered out based on a set threshold to obtain a second set of terms.

[0030] In practical applications, fuzzy matching is a preferred method for obtaining the second term set. The advantages of using fuzzy matching are as follows:

[0031] Improve error tolerance. For example, users may misspell bank names. Fuzzy matching can identify these spelling errors and match them with the correct entries, thus improving the system's error tolerance. Alternatively, when converting voice input to text, homophones or near-homophones may appear. Fuzzy matching can effectively handle these issues, ensuring matching accuracy.

[0032] Enhance matching flexibility. For example, users may habitually use abbreviations or shortened forms of bank names. Fuzzy matching can identify these abbreviations and shortened forms and match them with the complete bank name, increasing matching flexibility. Alternatively, different users may have different ways of expressing the same bank name; fuzzy matching can adapt to these different expressions, increasing the success rate of matching.

[0033] Improve the comprehensiveness and convenience of matching. Exact matching may miss some potential results due to incomplete or inaccurate user input. Fuzzy matching avoids this problem to some extent by considering the similarity and relevance of terms, finding as many possible matches as possible and providing users with a more comprehensive selection. Users do not need to enter the full bank name; they only need to enter partial keywords or abbreviations to complete the match, reducing the user's input burden, especially when the user is unfamiliar with or unsure of the bank name, thus improving the ease of operation.

[0034] Step 103: Use the bank name entries in the second term set to retrieve bank names from the bank name database to obtain a candidate bank name set.

[0035] Retrieval refers to the process of searching a bank name database for complete bank names related to bank name terms in the second term set. Through retrieval, complete bank names containing these terms can be found. The candidate bank name set is the collection of complete bank names containing bank name terms from the second term set, obtained through retrieval. These candidate bank names represent preliminary results that may match the bank name text entered by the user.

[0036] Specifically, a database query can be constructed based on the terms in the second term set. Terms can be combined using operators such as AND and OR to form query conditions. The constructed query is then executed in the bank name database to retrieve the complete bank names containing these terms. The query results are then organized and filtered to remove duplicates or bank names that do not meet the conditions, forming a candidate bank name set.

[0037] Step 104: Select bank names that match the bank name text from the candidate bank name set to obtain the target bank name.

[0038] Matching refers to the process of determining the similarity between the text of a bank name and each candidate bank name in a set of candidate bank names using certain algorithms or rules, in order to find the bank name that best matches the user's input. The target bank name is the bank name selected from the set of candidate bank names that matches the text of the bank name entered by the user. It can be a unique result used for subsequent transaction processing.

[0039] In this embodiment, intelligent recognition of bank names is achieved by utilizing technologies such as word segmentation and database matching. Users do not need specialized banking knowledge or to memorize a large number of bank names. The system's intelligent processing makes operation simpler and easier, allowing even users unfamiliar with banking systems to easily complete interbank transactions. Through efficient word segmentation and matching algorithms, the system can quickly filter target bank names from a vast database, significantly shortening the time for bank name recognition and matching, improving the overall efficiency of interbank transactions, and reducing transaction delays and failures caused by information errors. It is applicable to various forms of bank name input, whether manually entered by the user or obtained through other means. As long as the bank name text has undergone word segmentation, it can be accurately recognized and matched using the method of this invention, demonstrating strong flexibility and adaptability. Users do not need to manually enter complete and accurate bank names, nor do they need to search through lengthy drop-down menus. The system's automatic processing and recognition greatly simplifies the user's operation process and reduces the possibility of errors. Especially when faced with a large number of bank names, it can quickly locate the target bank, saving users time and effort. Furthermore, the bank name recognition method of the present invention is universal and is not affected by the differences in online banking or mobile banking systems of different banks. Users do not need to adapt to different operating interfaces and processes when conducting cross-bank transactions, which greatly reduces the learning cost and improves the convenience and smoothness of use.

[0040] The following is combined Figure 2 and Figure 3 The following example further illustrates the bank name recognition method provided in the embodiments of the present invention. Figure 2 This is another flowchart illustrating the bank name recognition method provided in this embodiment of the invention. Figure 3 This is an example diagram of a bank name recognition method provided in an embodiment of the present invention.

[0041] Please refer to the following: Figure 2 The bank name recognition method in this embodiment may include:

[0042] Step 201: Obtain the bank name input by the user in speech and convert the speech of the bank name into the text of the bank name.

[0043] The bank name in voice refers to the voice information of the bank name entered by the user into the system through a voice input device (such as a mobile phone microphone, computer voice input device, etc.). This voice information is usually captured and stored in the form of an audio file. The bank name in text refers to the bank name in text form obtained by converting the user's voice information through speech recognition technology. The text format facilitates subsequent processing and analysis. The voice input of the bank name can be obtained when a user initiates an interbank transaction and needs to enter the bank name.

[0044] Step 202: Segment the bank name text into words to obtain the first set of terms.

[0045] Specifically, the bank name text can be preprocessed by cleaning, word segmentation, and removal of stop words to improve the quality of the text data and make it more suitable for subsequent analysis and processing.

[0046] Step 203: Filter out bank name entries from the bank name database that match the original entries in the first entry set to obtain the second entry set.

[0047] Fuzzy matching can be used to calculate the similarity between the original terms and terms in the database, and terms with higher similarity can be filtered out according to a set threshold to obtain a second term set.

[0048] Step 204: Use the bank name entries in the second term set to retrieve bank names from the bank name database to obtain a candidate bank name set.

[0049] A database query can be constructed based on the terms in the second term set. Terms can be combined using operators such as AND and OR to form query conditions. The constructed query is then executed in the bank name database to retrieve complete bank names containing these terms. The query results are then organized and filtered to remove duplicates or bank names that do not meet the conditions, forming a candidate bank name set.

[0050] Step 205: Obtain the vector representation of each candidate bank name in the candidate bank name set to obtain the inventory vector set.

[0051] Vector representation is a method for converting text information into numerical vectors. In this embodiment, the text features can be represented by calculating the weight of each indexing term, thereby vectorizing the text. Vector representation can be used to calculate the similarity between texts. The inventory vector set is the set obtained by converting each candidate bank name in the candidate bank name set into a vector representation. Each vector represents the feature information of a candidate bank name.

[0052] Specifically, the inventory vector set includes the inventory vector corresponding to the current bank name, where the current bank name is any candidate bank name in the candidate bank name set. The inventory vector corresponding to the current bank name is obtained in the following way:

[0053] (1) Calculate the local weight and global weight of each preset index term for the current bank name. The local weight of each preset index term represents the frequency of occurrence of the corresponding index term in the current bank name, and the global weight of each preset index term represents the rarity of the corresponding index term in the bank name database.

[0054] Predefined indexing terms are pre-defined keywords used to describe and distinguish bank names. They are representative and distinctive words extracted from a large number of bank names. The local weight calculated here represents the frequency of a predefined indexing term in the current bank name database, reflecting the importance and representativeness of that term within the database. The global weight calculated here represents the rarity of a predefined indexing term in the bank name database, reflecting its importance in distinguishing different bank names.

[0055] (2) Multiply the local weight of each preset index term calculated for the current bank name with the global weight of the corresponding index term to obtain the comprehensive weight of each preset index term.

[0056] (3) The comprehensive weight of each preset index term calculated for the current bank name is used as the vector component corresponding to the current bank name, and the inventory vector corresponding to the current bank name is constructed based on each vector component corresponding to the current bank name.

[0057] Assuming the current bank name is d j Constructing inventory vectors For example, the construction process can be as follows:

[0058] Regarding d j Preset indexing term k for calculation i Local weight ij =freq ij ;

[0059] Where, freq ij Indicates the predefined index term k i In the current bank name d j Frequency of occurrence in.

[0060] Preset indexing term k i global weight

[0061] Where N represents the total number of bank names in the bank name database, n i This indicates that the bank name database contains the preset index term k. i The number of bank names.

[0062] Regarding the current bank name d j Preset indexing term k for calculation i The overall weight w ij ;

[0063] w ij =LocalWeight ij GlobalWeighti .

[0064] Inventory Vector

[0065] Where M represents the total number of predefined indexing terms, w Mj Indicates that for d j The calculated overall weight of the Mth index term.

[0066] Step 206: Obtain the vector representation corresponding to the bank name text to obtain the query vector.

[0067] Similar to the method for obtaining inventory vectors, the specific method for vectorizing bank name text can be as follows:

[0068] (1) Calculate the local weight and global weight of each preset indexing term for the bank name text. The local weight of each preset indexing term represents the frequency of occurrence of the corresponding indexing term in the bank name text, and the global weight of each preset indexing term represents the rarity of the corresponding indexing term in the bank name database.

[0069] (2) Multiply the local weight of each preset index term calculated for the bank name text with the global weight of the corresponding index term to obtain the comprehensive weight of each preset index term.

[0070] (3) The comprehensive weight of each preset index term calculated for the bank name text is used as the vector component corresponding to the bank name text, and the query vector corresponding to the bank name text is constructed based on each vector component corresponding to the bank name text.

[0071] For example, the bank name text is represented by q, and the query vector corresponding to the bank name text q is q. If it means:

[0072] Preset indexing term k calculated for bank name text q i Local weights

[0073] freq iq Indicates the predefined index term k i The frequency of occurrence in q, maxf q This represents the maximum number of occurrences of all preset index terms in q.

[0074] Preset indexing term k i global weight

[0075] Preset indexing term k calculated for bank name text q i The overall weight is w iq ;

[0076] wiq = (0.5 + 0.5 * LocalWeight) iq GlobalWeight i ;

[0077] The combined weights of all indexing terms are combined into a vector, i.e.

[0078] w Mq This represents the overall weight of the Mth index term calculated for q.

[0079] In this embodiment, by calculating the local and global weights of each indexing term and combining them into a comprehensive weight, the features of the text can be expressed more accurately. The local weights reflect the importance of the indexing term in the current text, while the global weights reflect the rarity of the indexing term in the database. This combination allows the vector to capture the semantic information of the text more comprehensively. The introduction of weights makes different texts exhibit more obvious differences in the vector space, thereby enabling more accurate differentiation of different bank names.

[0080] Step 207: Based on the similarity between the query vector and each inventory vector in the inventory vector set, select the inventory vector that matches the query vector from the inventory vector set to obtain the target vector.

[0081] Similarity refers to the degree of similarity between the query vector and the inventory vector, and is usually calculated using methods such as cosine similarity and Euclidean distance. Higher similarity indicates that the two vectors are closer, and the corresponding bank names are more similar. The target vector is the inventory vector selected from the set of inventory vectors that best matches the query vector; it represents the candidate bank name most similar to the user-input bank name text.

[0082] Step 208: Determine the candidate bank name corresponding to the target vector as the target bank name.

[0083] The target bank name is the bank name selected from the set of candidate bank names that matches the bank name text entered by the user, and is used to determine the bank name required for this interbank transaction.

[0084] Step 209: Identify whether the number of target bank names exceeds one. If it exceeds one, proceed to step 211; if it is one, proceed to step 210.

[0085] Step 210: Determine the target bank name as the bank name required for this interbank transaction.

[0086] If there is only one target bank name, then that unique target bank name will be selected as the bank name required for this interbank transaction.

[0087] Step 211: Display the target bank name for the user to select, and determine the target bank name selected by the user as the bank name required for this interbank transaction.

[0088] If more than one target bank name is identified, it means that there are multiple possible matching bank names. The specific bank name can be further determined by displaying multiple target bank names for the user to choose from.

[0089] Step 212: Associate and store the bank name text with the target bank name selected by the user.

[0090] If the matching results are not unique and the user selects the final result from multiple options, the bank name text can be associated with the user's selected target bank name to establish a relationship between the text and the bank name, and this relationship can be recorded in the database. This recorded data (customer language habits, dialect, and the final selected bank name) will be used as input variables for training a machine learning function. In subsequent operations, once a new customer input matches a record in the database, a corresponding bank name can be recommended to the customer based on the choices of the majority of previous users, thereby improving the user experience and the system's intelligence.

[0091] The following is for reference. Figure 3 The bank name recognition method of the present invention is explained by example.

[0092] After a user inputs the bank name via voice, the voice input is converted into text. The converted text undergoes preprocessing, including noise removal, word segmentation, and stop word removal. An existing database of common phrases is used to match the accurate bank name. If a matching bank name is found, it is used for the interbank transaction.

[0093] If no accurate and complete line name is found, the split terms are matched against terms in the system. The matched terms are then used to retrieve the line name database, resulting in a set of candidate line names. A matching line name is selected from this set. If only one line name is matched, that line name is used in this interbank transaction. If more than one line name is matched, these line names are displayed for the user to choose from, and the user-selected line name is used in this interbank transaction. Afterward, the user-selected line name can be associated with its corresponding text and stored for later use.

[0094] In this embodiment, intelligent recognition of bank names is achieved by utilizing technologies such as word segmentation and database matching. Users do not need specialized banking knowledge or to memorize a large number of bank names. The system's intelligent processing makes operation simpler and easier, allowing even users unfamiliar with banking systems to easily complete interbank transactions. Through efficient word segmentation and matching algorithms, the system can quickly filter target bank names from a vast database, significantly shortening the time for bank name recognition and matching, improving the overall efficiency of interbank transactions, and reducing transaction delays and failures caused by information errors. It is applicable to various forms of bank name input, whether manually entered by the user or obtained through other means. As long as the bank name text has undergone word segmentation, it can be accurately recognized and matched using the method of this invention, demonstrating strong flexibility and adaptability. Users do not need to manually enter complete and accurate bank names, nor do they need to search through lengthy drop-down menus. The system's automatic processing and recognition greatly simplifies the user's operation process and reduces the possibility of errors. Especially when faced with a large number of bank names, it can quickly locate the target bank, saving users time and effort. Furthermore, the bank name recognition method of the present invention is universal and is not affected by the differences in online banking or mobile banking systems of different banks. Users do not need to adapt to different operating interfaces and processes when conducting cross-bank transactions, which greatly reduces the learning cost and improves the convenience and smoothness of use.

[0095] Figure 4 This is a schematic diagram of a bank name recognition device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes:

[0096] The word segmentation module 401 is used to obtain the bank name text to be processed, and to perform word segmentation on the bank name text to obtain the first word set.

[0097] The filtering module 402 is used to filter bank name entries from the bank name database that match the original entries in the first entry set, and obtain the second entry set;

[0098] The retrieval module 403 is used to retrieve bank names from the bank name database using the bank name terms in the second term set, and obtain a candidate bank name set;

[0099] Matching module 404 is used to filter out bank names that match the bank name text from the candidate bank name set to obtain the target bank name.

[0100] In one embodiment, the word segmentation module 401 obtains the bank name text to be processed, including:

[0101] Get the bank name text entered by the user; or

[0102] Get the bank name input by the user in speech, and convert the speech of the bank name into the text of the bank name.

[0103] In one embodiment, the matching module 404 filters bank names that match the bank name text from the candidate bank name set to obtain the target bank name, including:

[0104] Obtain the vector representation of each candidate bank name in the candidate bank name set to obtain the inventory vector set;

[0105] Obtain the vector representation of the bank name text to get the query vector;

[0106] Based on the similarity between the query vector and each inventory vector in the inventory vector set, the inventory vector that matches the query vector is selected from the inventory vector set to obtain the target vector;

[0107] The candidate bank name corresponding to the target vector is determined as the target bank name.

[0108] In one embodiment, the inventory vector set includes the inventory vector corresponding to the current bank name, where the current bank name is any candidate bank name in the candidate bank name set. The inventory vector corresponding to the current bank name is obtained in the following way:

[0109] For the current bank name, calculate the local weight and global weight of each preset indexing term. The local weight of each preset indexing term represents the frequency of occurrence of the corresponding indexing term in the current bank name, and the global weight of each preset indexing term represents the rarity of the corresponding indexing term in the bank name database.

[0110] The local weight of each preset index term calculated for the current bank name is multiplied by the global weight of the corresponding index term to obtain the comprehensive weight of each preset index term;

[0111] The comprehensive weight of each preset index term calculated for the current bank name is used as the vector component corresponding to the current bank name, and the inventory vector corresponding to the current bank name is constructed based on each vector component corresponding to the current bank name.

[0112] In one embodiment, the matching module 404 obtains the vector representation corresponding to the bank name text to obtain the query vector, including:

[0113] For each preset indexing term in the bank name text, calculate the local weight and global weight. The local weight of each preset indexing term represents the frequency of occurrence of the corresponding indexing term in the bank name text, and the global weight of each preset indexing term represents the rarity of the corresponding indexing term in the bank name database.

[0114] The local weight of each preset indexing term calculated for the bank name text is multiplied by the global weight of the corresponding indexing term to obtain the comprehensive weight of each preset indexing term;

[0115] The comprehensive weight of each preset index term calculated for the bank name text is used as the vector component corresponding to the bank name text. The query vector corresponding to the bank name text is constructed based on each vector component corresponding to the bank name text.

[0116] In one embodiment, the device further includes a determining module, the determining module being configured to:

[0117] The number of target bank names identified;

[0118] If the number of target bank names is 1, the target bank name will be the bank name required for this interbank transaction.

[0119] If the number of target bank names is greater than 1, display the target bank names for the user to select, and determine the target bank name selected by the user as the bank name required for this interbank transaction.

[0120] In one embodiment, the device further includes:

[0121] The storage module is used to associate and store the bank name text with the target bank name selected by the user.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] The device of this invention, utilizing techniques such as word segmentation and database matching, achieves intelligent recognition of bank names. Users do not need specialized banking knowledge or to memorize a large number of bank names. The system's intelligent processing makes operation simpler and easier, allowing even users unfamiliar with banking systems to easily complete interbank transactions. Through efficient word segmentation and matching algorithms, the system can quickly filter target bank names from a vast database, significantly shortening the time for bank name recognition and matching, improving the overall efficiency of interbank transactions, and reducing transaction delays and failures caused by information errors. It is applicable to various forms of bank name input; whether manually entered by the user or obtained through other means, as long as word segmentation is performed, the method of this invention can accurately identify and match the bank name, demonstrating strong flexibility and adaptability. Users do not need to manually input complete and accurate bank names, nor do they need to search through lengthy drop-down menus. The system's automatic processing and recognition greatly simplifies the user's operation process and reduces the possibility of errors. Especially when faced with a large number of bank names, it can quickly locate the target bank, saving users time and effort. Furthermore, the bank name recognition method of the present invention is universal and is not affected by the differences in online banking or mobile banking systems of different banks. Users do not need to adapt to different operating interfaces and processes when conducting cross-bank transactions, which greatly reduces the learning cost and improves the convenience and smoothness of use.

[0124] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing an electronic device according to embodiments of the present invention. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0125] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computer system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0126] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0127] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0128] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0130] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including a word segmentation module, a filtering module, a retrieval module, and a matching module. The names of these modules do not necessarily limit the module itself.

[0131] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0132] Obtain the bank name text to be processed, and perform word segmentation on the bank name text to obtain a first term set; filter bank name terms that match the original terms in the first term set from the bank name database to obtain a second term set; use the bank name terms in the second term set to retrieve bank names from the bank name database to obtain a candidate bank name set; filter bank names that match the bank name text from the candidate bank name set to obtain the target bank name.

[0133] The technical solution of this invention, through word segmentation and database matching, achieves intelligent recognition of bank names. Users do not need professional banking knowledge or to memorize a large number of bank names. The system's intelligent processing makes operation simpler and easier, allowing even users unfamiliar with banking systems to easily complete cross-bank transactions. Through efficient word segmentation and matching algorithms, the system can quickly filter target bank names from a vast database, significantly shortening the time for bank name recognition and matching, improving the overall efficiency of cross-bank transactions, and reducing transaction delays and failures caused by information errors. It is applicable to various forms of bank name input, whether manually entered by the user or obtained through other means. As long as the bank name text has undergone word segmentation, it can be accurately recognized and matched using the method of this invention, demonstrating strong flexibility and adaptability. Users do not need to manually enter complete and accurate bank names, nor do they need to search through lengthy drop-down menus. The system's automatic processing and recognition greatly simplifies the user's operation process and reduces the possibility of errors. Especially when faced with a large number of bank names, it can quickly locate the target bank, saving users time and effort. Furthermore, the bank name recognition method of the present invention is universal and is not affected by the differences in online banking or mobile banking systems of different banks. Users do not need to adapt to different operating interfaces and processes when conducting cross-bank transactions, which greatly reduces the learning cost and improves the convenience and smoothness of use.

[0134] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the bank name recognition method as provided in any embodiment of this invention.

[0135] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0137] It should be noted that the collection, use, storage, sharing, and transfer of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations, and require notification to the user and obtaining the user's consent or authorization. Where applicable, user personal information has undergone de-identification and / or anonymization and / or encryption technical processing. In addition, a corresponding operation entry is provided for the user to choose to agree to or reject the automated decision result; if the user chooses to reject, the process proceeds to the expert decision-making process.

[0138] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for recognizing bank names, characterized in that, include: Obtain the bank name text to be processed, and perform word segmentation on the bank name text to obtain the first word set; The second set of terms is obtained by filtering bank name terms from the bank name database that match the original terms in the first term set; The bank name entries in the second term set are used to retrieve bank names from the bank name database to obtain a candidate bank name set. The target bank name is obtained by filtering out bank names that match the text of the bank name from the candidate bank name set.

2. The method according to claim 1, characterized in that, Obtain the text of the bank name to be processed, including: Get the bank name text entered by the user; or Get the bank name input by the user in speech, and convert the speech of the bank name into the text of the bank name.

3. The method according to claim 1, characterized in that, The target bank name is obtained by filtering the candidate bank name set to match the text of the bank name. Obtain the vector representation of each candidate bank name in the candidate bank name set to obtain the inventory vector set; Obtain the vector representation of the bank name text to get the query vector; Based on the similarity between the query vector and each inventory vector in the inventory vector set, the inventory vector that matches the query vector is selected from the inventory vector set to obtain the target vector; The candidate bank name corresponding to the target vector is determined as the target bank name.

4. The method according to claim 3, characterized in that, The inventory vector set includes the inventory vector corresponding to the current bank name. The current bank name is any candidate bank name in the candidate bank name set. The inventory vector corresponding to the current bank name is obtained in the following way: For the current bank name, calculate the local weight and global weight of each preset indexing term. The local weight of each preset indexing term represents the frequency of occurrence of the corresponding indexing term in the current bank name, and the global weight of each preset indexing term represents the rarity of the corresponding indexing term in the bank name database. The local weight of each preset index term calculated for the current bank name is multiplied by the global weight of the corresponding index term to obtain the comprehensive weight of each preset index term; The comprehensive weight of each preset index term calculated for the current bank name is used as the vector component corresponding to the current bank name, and the inventory vector corresponding to the current bank name is constructed based on each vector component corresponding to the current bank name.

5. The method according to claim 4, characterized in that, Obtain the vector representation of the bank name text to get the query vector, including: For each preset indexing term in the bank name text, calculate the local weight and global weight. The local weight of each preset indexing term represents the frequency of occurrence of the corresponding indexing term in the bank name text, and the global weight of each preset indexing term represents the rarity of the corresponding indexing term in the bank name database. The local weight of each preset indexing term calculated for the bank name text is multiplied by the global weight of the corresponding indexing term to obtain the comprehensive weight of each preset indexing term; The comprehensive weight of each preset index term calculated for the bank name text is used as the vector component corresponding to the bank name text. The query vector corresponding to the bank name text is constructed based on each vector component corresponding to the bank name text.

6. The method according to claim 1, characterized in that, The method further includes: The number of target bank names identified; If the number of target bank names is 1, the target bank name will be the bank name required for this interbank transaction. If the number of target bank names is greater than 1, display the target bank names for the user to select, and determine the target bank name selected by the user as the bank name required for this interbank transaction.

7. The method according to claim 6, characterized in that, After determining the target bank name selected by the user as the bank name required for this interbank transaction, the following is also included: Associate and store the bank name text with the target bank name selected by the user.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the bank name recognition method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the bank name recognition method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the bank name recognition method as described in any one of claims 1 to 7.

Images