Account identification method and device and computer device

Abstract

The application relates to an account identification method, device and computer equipment. The method comprises the following steps: obtaining a to-be-identified public bank account of a target bank; traversing pre-stored bank information, matching the public bank account and the bank information, selecting a bank as a candidate bank when the public bank account hits the coding rule of the bank; calculating the sum of weight values of the hit coding rules in each candidate bank; selecting the candidate bank corresponding to the highest sum of weight values as an identification result. According to the pre-acquired coding rule, the public bank account to be identified can be identified, and the bank information to which the public bank account belongs can be inferred. In the case that the account information cannot be provided by a remitter, data support can be provided for a remittance agency, the work difficulty of the remittance agency is reduced, and the query time is saved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer communication, in particular to an account identification method and device and computer equipment. BACKGROUND

[0002] The public bank account refers to the account opened in the bank on behalf of the company. When performing remittance operation, the remitter must provide the account information of the opposite party, including the account information of the account, such as the account of the account, the account number, the account name and the like. The remittance agency verifies and completes the transaction after successful verification.

[0003] At present, the public bank account of each bank in China has its own coding rule, and there is intersection and conflict between each coding rule. In the case that the remitter fails to provide the account information, the remittance agency cannot analyze the coding rule of the public bank account, and cannot identify the account information of the account, which brings inconvenience to the remittance work. SUMMARY

[0004] Therefore, it is necessary to provide an account identification method, device and computer equipment to solve the problem that the remittance agency cannot analyze the coding rule of the public bank account and cannot identify the account information of the account in the case that the remitter fails to provide the account information, which brings inconvenience to the remittance work.

[0005] In a first aspect, the present application provides an account identification method. The method comprises:

[0006] Obtaining a public bank account of a target bank to be identified;

[0007] Traversing the pre-stored bank information, matching the public bank account and the bank information, when the public bank account hits the coding rule of a bank, selecting the bank as a candidate bank; wherein the bank information comprises the coding rule of each bank and the weight value corresponding to each coding rule, and the coding rule is obtained by analyzing the historical public bank account of the target bank in advance;

[0008] Calculating the sum of the weight values of the coding rules hit in each candidate bank;

[0009] Selecting the candidate bank corresponding to the highest weight value as the identification result.

[0010] In one of the embodiments, the bank information further comprises the account length information of each bank;

[0011] The matching of the public bank account and the bank information further comprises:

[0012] Based on the length of the corporate bank account, query the account length information of each of the aforementioned banks;

[0013] Banks with the same length as the corporate bank account number are selected as alternative banks;

[0014] Match the corporate bank account number with the coding rules of each of the candidate banks.

[0015] In one embodiment, the encoding rules are obtained in advance based on the historical corporate bank account information of the target bank, including:

[0016] Obtain multiple historical corporate bank accounts of the target bank, wherein the length of each historical corporate bank account is the same as the length of the target account to be parsed;

[0017] For each digit of the aforementioned historical corporate bank account, the category information of that digit is statistically analyzed, and the category information of that digit is used as the category information of the same position in the target account. The category information includes the type of occurrence of each digit in that digit and the frequency of occurrence of that type.

[0018] Based on the various categories of information of the target account, the target account is segmented to obtain multiple combinations;

[0019] Extract the categories from each combination and use them as the encoding rules for the target account.

[0020] In one embodiment, the step of segmenting the target account based on its various categories of information to obtain multiple combinations includes:

[0021] For each bit of the target account, when the category information of that bit meets the first preset condition, that bit is reserved.

[0022] When a reserved bit has adjacent reserved bits, the multiple consecutive adjacent reserved bits are marked as a group;

[0023] When a reserved bit does not have any adjacent reserved bits, the reserved bit is marked as a combination;

[0024] The aforementioned combinations of markers constitute multiple combinations of the target account.

[0025] In one embodiment, the method for determining the first preset condition includes:

[0026] For each digit of the target account, calculate the first cumulative value of each frequency from largest to smallest until the first cumulative value is greater than or equal to the first value, and at this time the sum of the number of each type is less than or equal to the second value, then the first preset condition is considered to be satisfied.

[0027] In one of the embodiments, the extracting the category in each combination before the encoding rule of the target account is further comprising:

[0028] The category information of each combination is counted, and when the category information of the combination meets a second preset condition, the corresponding category meeting the second preset condition is reserved as the category of the combination.

[0029] In one of the embodiments, the judging manner of the second preset condition comprises:

[0030] The second accumulated values of each frequency are calculated from large to small until the second accumulated value is greater than or equal to a third value;

[0031] The categories corresponding to each frequency when the second accumulated value is greater than or equal to the third value are subjected to uniformity verification;

[0032] If a category meets the uniformity verification, it is considered to meet the second preset condition.

[0033] In one of the embodiments, the method further comprises:

[0034] Based on the number of the encoding rules of the target account and the preset weight values of each encoding rule, the weight values of each encoding rule are calculated.

[0035] In a second aspect, the present application further provides an account identification device. The device comprises:

[0036] An acquisition module is configured to acquire a public bank account of a target bank to be identified;

[0037] An identification module is configured to traverse pre-stored bank information, match the public bank account and the bank information, and select a bank as a candidate bank when the public bank account hits the encoding rule of the bank; wherein the bank information comprises the encoding rules of each bank and the weight values corresponding to each encoding rule, and the encoding rules are obtained by analyzing the historical public bank accounts of the target bank in advance;

[0038] A screening module is configured to calculate the sum of the weight values of the encoding rules in each candidate bank, and select the candidate bank corresponding to the highest sum of weight values as the identification result.

[0039] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method steps of any one of the first aspect when executing the computer program.

[0040] The account identification method, device and computer device have at least the following advantages:

[0041] The application analyzes the historical public bank account of the target bank in advance, obtains the coding rule of the target bank, matches the received public bank account to be identified with the coding rule, and if the matching is successful, the target bank is taken as a candidate bank, and the weight value of each candidate bank is calculated, and the target bank with the highest weight value is taken as the bank to which the public bank account to be identified belongs. The application can identify the public bank account to be identified according to the coding rule obtained in advance, and obtain the bank information of the public bank account, so as to provide data support for the remittance agency in the case that the account information cannot be provided by the remittance party, reduce the work difficulty of the remittance agency, and save the query time. BRIEF DESCRIPTION OF DRAWINGS

[0042] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application, and are incorporated in and constitute a part of this application. The embodiments of the application illustrated in the drawings, and their description thereto, are presented to provide the practitioner with a thorough and enabling disclosure of the application, and are included as a part of this application to convey the scope of the application to practitioners in the art.

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the application, the accompanying drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0044] Figure 1 An application environment diagram of the account identification method in an embodiment;

[0045] Figure 2 A flowchart diagram of the account identification method in an embodiment;

[0046] Figure 3 A flowchart diagram of the step of matching the public bank account and the bank information in another embodiment;

[0047] Figure 4 A flowchart diagram of obtaining the coding rule of the target bank in an embodiment;

[0048] Figure 5 A statistical result diagram of the types of the public bank account of bank A in an embodiment;

[0049] Figure 6 A statistical result diagram of the combination of the public bank account of bank A in an embodiment;

[0050] Figure 7 A structure block diagram of the account identification device in an embodiment;

[0051] Figure 8 An internal structure diagram of the computer device in an embodiment. DETAILED DESCRIPTION

[0052] Other advantages and benefits of the present application will become apparent to those skilled in the art, upon reading the following description of embodiments of the application, in conjunction with the accompanying drawings. The application can be implemented or applied in other different embodiments and with various modifications not departing from the spirit of the application. It is to be understood that the following examples and features of the examples can be combined with each other, if not incompatible.

[0053] Some example embodiments of the application are described for illustrative purposes, it is to be understood that the application can be implemented in other ways not specifically shown in the drawings.

[0054] The account identification method provided by the embodiments of the present application can be applied to the application environment as shown in the figure. Figure 1 The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0055] The terminal 102 can send the public bank account to be identified to the server 104, so that the server 104 processes the public bank account to be identified. For example, the server 104 traverses the bank information in the pre-stored bank list, matches the public bank account and the bank information, and selects the bank as the candidate bank when the public bank account hits all the coding rules of the bank. The sum of the weight values of the coding rules in each candidate bank is calculated. The candidate bank corresponding to the highest weight value is selected as the recognition result. In this way, the server 104 feeds back the recognition result to the terminal 102.

[0056] The above account identification method analyzes the historical public bank account of the target bank in advance to obtain the coding rules of the target bank. The received public bank account to be identified is matched with the coding rules. If the matching is successful, the target bank is selected as the candidate bank, and the weight value of each candidate bank is calculated. The target bank with the highest weight value is selected as the bank to which the public bank account to be identified belongs. The application can identify the public bank account to be identified according to the pre-obtained coding rules, and infer the bank information of the public bank account. In the case that the account information cannot be provided by the remitter, the application provides data support for the remittance agency, reduces the work difficulty of the remittance agency, and saves the query time.

[0057] The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by a stand-alone server or a server cluster composed of multiple servers.

[0058] In a feasible embodiment, the embodiment of the present application provides an account identification method. The following takes the server in Figure 1 as an example for illustration.

[0059] Please refer to Figure 2 , Figure 2 , which is a flowchart of an account identification method of the embodiment, and specifically includes the following steps:

[0060] Step S202: Obtain a public bank account of a target bank to be identified.

[0061] Step S204: Traverse the pre-stored bank information, match the public bank account and the bank information, and select a bank as a candidate bank when the public bank account hits the coding rule of the bank.

[0062] Step S206: Calculate the sum of the weight values of the coding rules that hit in each candidate bank, and select the candidate bank corresponding to the highest sum of weight values as the identification result.

[0063] Specifically, the public bank account refers to an account opened in the bank on behalf of a company. At present, the public bank accounts of various banks in China have their own coding rules, and there are also intersections and conflicts between the coding rules. For example, the 19-digit public bank account of the Bank of Communications has a coding rule from left to right: 4-digit region code, 4-digit network point number, 2-digit application number, 7-digit account sequence number, and 2-digit check code. However, the 19-digit public bank account of the CITIC Bank has a coding rule from left to right: 6-digit account opening network point number, 2-digit currency code, 3-digit business code, 6-digit account sequence number, and 2-digit verification code. In addition, even the same length of public bank account of the same bank has completely different coding rules, for example, another type of 19-digit public bank account of the CITIC Bank, which starts with 7, has 1-3 digits representing the account opening network point information and 6-7 digits representing the currency column; the public bank account starting with 8 has 1-5 digits representing the account opening network point information and 7-8 digits representing the currency column.

[0064] To this end, the account identification method provided in the embodiments of the present application compares the public bank account to be identified with pre-stored bank information after receiving the public bank account to be identified, wherein the bank information pre-stores the name of each target bank, the coding rule corresponding to the target bank, and the weight value corresponding to the coding rule. It should be understood that the coding rule of each target bank is multiple, and is obtained according to the historical public bank account of the target bank. When the public bank account hits the coding rule of a bank, the bank is recorded as a candidate bank, and the public bank account is matched with the coding rule of the next target bank. If the matching is successful, the bank is recorded as a candidate bank, and the matching of all banks is completed. Through the above scheme, at least one candidate bank can be finally obtained. In the case of only one candidate bank, the candidate bank is taken as the identification result. If the number of candidate banks obtained is multiple, at this time, the sum of the weight values of each coding rule in each candidate bank is calculated, and the candidate bank corresponding to the highest weight value is selected as the identification result, and the remaining candidate banks are taken as candidate results. For example, the present application sets a strict mode when traversing the pre-stored bank information. If the user selects the strict mode, when the public bank account hits all the coding rules of a bank, the bank is recorded as a candidate bank; otherwise, when the public bank account hits one coding rule of a bank, the bank is also recorded as a candidate bank.

[0065] The above account identification method analyzes the historical public bank account of the target bank in advance to obtain the coding rule of the target bank; matches the received public bank account to be identified with the coding rule, and takes the target bank as a candidate bank if the matching is successful, and calculates the weight value of each candidate bank, and takes the target bank with the highest weight value as the bank to which the public bank account to be identified belongs. The present application can identify the public bank account to be identified according to the pre-obtained coding rule, and obtain the bank information to which the public bank account belongs. In the case that the account information cannot be provided by the remitter, the present application provides data support for the remitting institution, reduces the work difficulty of the remitting institution, and saves the query time.

[0066] Please refer to Figure 3 Optionally, in a feasible embodiment, the bank information further includes the account length information of each target bank.

[0067] Matching the public bank account and the bank information further includes:

[0068] Step S302, querying the account length information of each bank according to the length of the public bank account;

[0069] Step S304, taking each bank with the same length as the public bank account as a candidate bank;

[0070] Step S306, match the public bank account number with the coding rules of each candidate bank.

[0071] Specifically, the account length information is the length of the public bank account number included in a bank. The length of the public bank account number of each bank can be one or multiple. For example, the length of the public bank account number of the Industrial and Commercial Bank of China is 19 bits, the length of the public bank account number of the Agricultural Bank of China is 15 bits and 17 bits, and the length of the public bank account number of the Savings Bank is 9 bits and 18 bits. The account length information of each bank is pre-acquired and stored. When the public bank account number to be identified is received, the length is queried from the pre-stored account length information. If the length of the public bank account number included in a bank is the same as the length, the bank is selected as a candidate bank, and then the next bank is queried, until all banks in the pre-stored account length information are completed, and multiple candidate banks are obtained.

[0072] In the above embodiment, before matching the coding rules, the length of the public bank account number to be identified is identified, and the banks with the same length are screened out as candidate banks according to the identification result, so as to reduce the identification range and reduce the data processing amount.

[0073] Please refer to Figure 4 Optionally, the coding rules are obtained by pre-analyzing the historical public bank account numbers of the target bank, including:

[0074] Step S402, acquire multiple historical public bank account numbers of the target bank, wherein the length of each historical public bank account number is the same as the length of the target account number to be parsed.

[0075] Step S404, for each digit of each historical public bank account number, count the category information of the digit, and take the category information of the digit as the category information of the same position of the target account number, wherein the category information includes the type of each digit on the digit and the frequency of the type.

[0076] Step S406, according to the category information of the target account number, the target account number is segmented to obtain multiple combinations.

[0077] Step S408, extract the type in each combination as the coding rule of the target account number.

[0078] Specifically, for a target bank to be parsed, n account numbers of different lengths are selected from the historical public bank account numbers of the bank as a training set. It should be understood that the lengths of the account numbers in each training set are the same.

[0079] Please refer to Figure 5For each historical bank account number in the training set, the number of types and the corresponding frequency of each digit are counted in sequence from left to right. For example, for a 17-digit bank account number of bank A, by counting n bank account numbers of the bank A, the statistical results are shown in Table 1 as follows: Figure 5 Figure 5 The digits appearing on some bits and the frequency of each digit are shown in Table 1. First, the frequency of each digit appearing on the first bit is counted in sequence, where the digit "0" appears 15302 times and the digit "1" appears 57563 times, obtaining the frequency of each digit appearing on the first bit. Then, the frequency of each digit appearing on the second bit to the seventeenth bit is counted in sequence, finally obtaining the frequency of each digit appearing on each bit of the 17-digit bank account number of bank A.

[0080] Optionally, the target account is divided according to the category information of the target account to obtain a plurality of combinations, including:

[0081] For each bit of the target account, if the category information of the bit meets a first preset condition, the bit is regarded as a reserved bit. If a reserved bit has adjacent reserved bits, a plurality of adjacent reserved bits are marked as a combination. If a reserved bit does not have adjacent reserved bits, the reserved bit is marked as a combination. The combinations obtained by the above marking constitute a plurality of combinations of the target account.

[0082] Optionally, the first preset condition is determined in the following manner:

[0083] For each bit of the target account, a first cumulative value of each frequency is calculated from large to small, until the first cumulative value is greater than or equal to a first numerical value, and at this time the number of each type is less than or equal to a second numerical value, then it is considered that the first preset condition is met.

[0084] Please continue to refer to Figure 5 ​In particular, for the 17-digit target account number belonging to bank A, according to the category information of the first digit, it is determined whether it can be used as a reserved digit. The determination step includes: sorting the frequencies of various categories in the first digit in descending order, and calculating the first cumulative value of each frequency. Assuming that in this embodiment, the first value is set to 97.5%, and the second value is set to 3, according to the above sorting method, the frequency of the category of the first digit is sorted in descending order as {1, 2, 3, 4, 0, 9, 6, 7, 5, 8}, and the sum of the frequencies of the top five numbers is 97.75%. At this time, the number of categories is 5, so it is considered that the first preset condition is not met, and it is not reserved. The category of the third digit is sorted in descending order as {0, 1, 5, 2, 4, 8, 9, 3, 6, 7}, and the probability of {0, 1, 5} is in the top three in the sorting, and the probability sum of the three categories at this time is 97.65%. It is considered that the first digit meets the first preset condition and is used as a reserved digit. According to the above method, it is determined in turn whether each digit can be used as a reserved digit, wherein {0, 1, 2} of the ninth digit is in the top three, and the probability sum of the three categories is 98.22%, which is reserved. {9, 1, 8} of the tenth digit is in the top three, and the probability sum of the three categories is 98.3%, which is reserved. Thus, three reserved digits are obtained. It should be noted that the first cumulative value can be calculated at the same time as the sorting, or after the sorting is completed, the calculation is performed in the order from front to back.

[0085] Further, according to the three reserved digits obtained in the above step, it is determined whether each reserved digit has adjacent reserved digits. If so, the adjacent multiple reserved digits are marked as a combination, otherwise, the reserved digit itself is marked as a combination. For example, the third digit of the 17-digit target account number belonging to bank A is a reserved digit, and the adjacent first digit and second digit are not reserved digits, so the third digit is marked as the first combination. If the ninth digit and the tenth digit are both reserved digits, the ninth digit and the tenth digit are marked as the second combination. According to the above method, two combinations of the 17-digit target account number are obtained.

[0086] In the above embodiment, by counting the category of each digit and the frequency of the category of each digit on each digit of the target account number, the category information of each digit of the target account number is obtained. For each digit of the target account number, the digit whose category information meets the first preset condition is selected as a reserved digit, and according to the position correlation of the reserved digits, multiple combinations are marked as the segmentation result of the target account number, and the categories in each combination are extracted as the encoding rule of the target account number. Through the above screening method, the irrelevant categories with large information quantity can be deleted from the numerous categories, and the selected categories meeting the requirements are reserved as the encoding rule, thereby improving the accuracy of the analysis.

[0087] Optionally, before the category in each combination is used as the encoding rule of the target account number, it further includes:

[0088] The category information of each combination is counted, and when the category information of the combination satisfies a second preset condition, the category corresponding to the second preset condition is reserved as the category of the combination. The judgment manner of the second preset condition includes:

[0089] The second accumulated values of each frequency are calculated from large to small, and until the second accumulated value is greater than or equal to a third value, it is considered to satisfy the second preset condition.

[0090] Please refer to Figure 6 . Specifically, in order to further improve the analysis accuracy, the plurality of combinations of the target account obtained in the above embodiment are further processed, and the processing steps include: for each reserved bit in each combination, counting the category information of the reserved bit to obtain the category information of the combination; according to the category information of the combination, the frequencies corresponding to each category in the combination are sorted in descending order, and the second accumulated value of each frequency is calculated. Assuming that the third value is also set to 97.5% in this embodiment, the first combination of the 17 target accounts belonging to the A bank is the third, which has 10 categories, and after the categories are arranged in descending order according to the corresponding frequencies, the sum of the frequencies of the first three categories {0, 1} is 97.65%, which is greater than the third value 97.5%, so the first two categories {0, 1} in the first combination are reserved as the final reserved categories of the combination. The second combination is the ninth and the tenth, and the possible digits of the ninth and the tenth are continued to be counted, as well as the frequency of each digit. In order to save space, Figure 6 , the second combination in the table only shows the digits with the frequency in the top ten, and the sum of the frequencies of {09, 19, 29, 39, 01, 38} is 97.85%, so the categories reserved by the second combination are {09, 19, 29, 39, 01, 38}.

[0091] Optionally, the judgment manner of the second preset condition further includes:

[0092] The categories corresponding to each frequency when the second accumulated value is greater than or equal to the third value are subjected to uniformity verification; if a category meets the uniformity verification, it is considered to satisfy the second preset condition.

[0093] Specifically, the uniformity verification is used to describe the spatial distribution characteristics of the standard sample, and the purpose of the uniformity verification on the reserved categories in this embodiment is to remove the possible random number segments, because the distribution of the digits of the random number segments should be close to the average in theory.

[0094] In this embodiment, the following formula is used to calculate the difference of the distribution of each category:

[0095] X = (x1, …, xn) n )

[0096] Y = (y1,..., y n )

[0097]

[0098] wherein X is a data set of various types of real distribution, Y is the average of X, and the calculated difference S can know whether the distribution data of this type is uniform, if S > 0.01, it is considered that the output is not uniform; if S≤0.01, the output is uniform.

[0099] In combination Figure 6 , the above manner can be used to calculate the similarity of various types in the first combination as 0.74, and the similarity of various types in the second combination as 0.94, which can be retained through uniformity verification.

[0100] In the above embodiment, the types in each combination obtained in the above embodiment are further screened by selecting the types in each combination that meet the second preset condition, and the screened types are subjected to uniformity verification, which further improves the analysis accuracy and the screened types are more consistent with the coding rules of the public bank account number.

[0101] Optionally, the account number identification method of the embodiment of the application further comprises:

[0102] Based on the number of coding rules of the target account number and the preset weight value of each coding rule, the weight value of each coding rule is calculated.

[0103] Specifically, by the above steps, the historical public bank account numbers of different lengths of each bank are analyzed to obtain the coding rules corresponding to the public bank account numbers of different lengths, which are denoted as the first rule. Further, the application also calculates the weight of each coding rule to facilitate subsequent account number identification.

[0104] In this embodiment, the following formula is used to calculate the weight value of each coding rule:

[0105]

[0106] wherein w new1 is the weight value of each coding rule in the target bank; w old1 is the preset weight value of each coding rule in the target bank, which is determined according to the frequency of occurrence of the coding rule; n1 is the total number of rules of the account number of the corresponding length in the target bank; k1 and k2 are adjustable parameters.

[0107] For example, for the 17-digit target account number of the above-mentioned bank A, the finally retained coding rules are {0, 1, 09, 19, 29, 39, 01, 38}. If one of the coding rules "09" is taken, k1 is 0.2, k2 is 3, w old1n1 is 7, n2 is 4, and k1 is 0.2, k2 is 3, k3 is 0.5, k4 is 1, w Optionally, the coding rule in the embodiment of the present application includes a second rule in addition to the first rule obtained by analyzing the historical public bank account numbers of the target bank, which is a coding rule disclosed by some banks. For example, the coding rule of a 20-digit public bank account number disclosed by the Construction Bank is: region code 3 + currency code 2 + exchange number and jurisdiction number 6 + account type 2 + account sequence number 6 + check code 1. The present application further combines the first rule and the second rule, and adjusts the weight of each coding rule according to the length of the rule.

[0108] Specifically, the weight value of each coding rule is recalculated by using the following formula:

[0109]

[0110] wherein w new2 is the weight value of each coding rule of the bank with known coding rules; w old1 is the preset weight value of each coding rule of the bank with known coding rules; n1 is the total number of rules of the account number with corresponding length in the bank with known coding rules; n2 is the controlled length in the bank with known coding rules, for example, the coding rule "09" corresponds to the ninth and tenth digits of the public bank account number, and the control length is 2; k1, k2, k3, and k4 are adjustable parameters.

[0111] For example, for the coding rule "09", k1 is 0.2, k2 is 3, k3 is 0.5, k4 is 1, w old2 is 1, n1 is 7, and n2 is 4 The final weight value of the coding rule "09" is 1.9005.

[0112] In the above manner, the weight value of each coding rule of the public account number of each bank with each length is calculated by combining the first rule obtained by the present application according to the historical public bank account numbers of different lengths of each bank, and the second rule disclosed by the bank for the length. It should be understood that the adjustable parameters in the above formula can be adjusted according to actual needs. In addition, the weight values of the above coding rules are obtained by multiple calculations in the above manner, and when the coding rules of a bank change, the method in the above embodiment can be used to update the coding rules and weight values. In order to enable those skilled in the art to fully understand the present application, the steps of the account number identification method of the present application are described in detail as follows:

[0113] The application parses the coding rules of the target bank in advance according to the historical accounts of the target bank, obtains the coding rules of the target bank, and calculates the weight values of the coding rules according to the number of the coding rules and the preset weight values of the coding rules. The application also updates the coding rules and the weight values when the coding rules change.

[0114] The coding rules are obtained by parsing the historical accounts of the target bank, including: obtaining a plurality of historical accounts of the target bank, wherein the lengths of the historical accounts are the same as the length of the target account to be parsed; for each digit of the historical accounts, the category information of the digit is counted, and the category information of the digit is taken as the category information of the same position of the target account, wherein the category information includes the type of each digit on the digit and the frequency of the type; the target account is segmented according to the category information of the target account to obtain a plurality of combinations; and the types in each combination are extracted as the coding rules of the target account.

[0115] Further, the target account is segmented according to the category information of the target account to obtain a plurality of combinations, including: for each digit of the target account, when the category information of the digit meets a first preset condition, the digit is taken as a reserved digit; when a reserved digit has adjacent reserved digits, a plurality of adjacent reserved digits are marked as a combination; when a reserved digit does not have adjacent reserved digits, the reserved digit is marked as a combination; and the marked combinations constitute the plurality of combinations of the target account. The judgment method of the first preset condition includes: for each digit of the target account, the first cumulative value of each frequency is calculated from large to small until the first cumulative value is greater than or equal to a first value, and at this time the number of each type is less than or equal to a second value, then it is considered that the first preset condition is met.

[0116] Further, before the types in each combination are extracted as the coding rules of the target account, the application further includes: counting the category information of each combination, and when the category information of the combination meets a second preset condition, the corresponding type that meets the second preset condition is reserved as the type of the combination. The judgment method of the second preset condition includes: calculating the second cumulative value of each frequency from large to small until the second cumulative value is greater than or equal to a third value; performing uniformity verification on the types corresponding to the frequencies when the second cumulative value is greater than or equal to the third value; and if a type meets the uniformity verification, it is considered that the second preset condition is met.

[0117] When the target bank's to-be-identified public bank account is received, the pre-stored bank information is traversed to match the public bank account and the bank information, wherein the bank information pre-stores the name of the target bank, the account length information of the target bank, the coding rule corresponding to the target bank, and the weight value corresponding to the coding rule; according to the length of the public bank account, the account length information of each bank is queried, and each bank with the same length as the public bank account is selected as a candidate bank, and the public bank account is matched with the coding rule of each candidate bank; when the public bank account hits the coding rule of a bank, the bank is selected as a candidate bank; the sum of the weight values of the coding rules in each candidate bank is calculated, and the candidate bank corresponding to the highest sum of weight values is selected as the identification result.

[0118] The above account identification method pre-analyzes the historical public bank account of the target bank to obtain the coding rule of the target bank; the received to-be-identified public bank account is matched with the coding rule, and the target bank is selected as a candidate bank when the matching is successful, and the weight value of each candidate bank is calculated, and the target bank with the highest weight value is selected as the bank to which the to-be-identified public bank account belongs. According to the pre-obtained coding rule, the to-be-identified public bank account can be identified, and the bank information of the public bank account is obtained. In the case that the account information cannot be provided by the remitter, the data support is provided for the remittance institution, the work difficulty of the remittance institution is reduced, and the query time is saved.

[0119] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0120] Based on the same inventive concept, the embodiments of the present application also provide an account identification device for implementing the above-mentioned account identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more account identification device embodiments provided below can refer to the limitations of the account identification method described above, which will not be described here again.

[0121] Please refer to Figure 7In one possible implementation, the account identification device provided by the embodiments of the present application comprises an obtaining module, an identification module and a screening module, wherein:

[0122] The obtaining module is configured to obtain a public bank account to be identified of a target bank.

[0123] The identification module is configured to traverse pre-stored bank information, match the public bank account and the bank information, and select a bank as a candidate bank when the public bank account hits the coding rule of the bank; wherein the bank information comprises the coding rule of each bank and the weight value corresponding to each coding rule, and the coding rule is obtained according to the historical public bank account of the target bank.

[0124] The screening module is configured to calculate the sum of the weight values of the coding rules in each candidate bank, and select the candidate bank corresponding to the highest sum of weight values as the identification result.

[0125] Optionally, the bank information further comprises the account length information of each target bank. The identification module is configured to match the public bank account and the bank information, and further comprises the following steps: querying the account length information of each bank according to the length of the public bank account; selecting each bank having the same length as the public bank account as a candidate bank; and matching the public bank account and the coding rule of each candidate bank.

[0126] Optionally, the account identification device provided by the embodiments of the present application further comprises a calculation module.

[0127] The calculation module is configured to calculate the coding rule of each bank and the weight value corresponding to each coding rule according to the historical public bank account of the target bank.

[0128] The calculation module is configured to obtain the coding rule according to the historical public bank account of the target bank, comprising the following steps: obtaining a plurality of historical public bank accounts of the target bank, wherein the length of each historical public bank account is the same as the length of the target account to be parsed. For each digit of each historical public bank account, the category information of the digit is counted and the category information of the digit is taken as the category information of the same position of the target account, wherein the category information comprises the type of each digit on the position and the frequency of the type. According to the category information of the target account, the target account is segmented to obtain a plurality of combinations. The type in each combination is extracted as the coding rule of the target account.

[0129] Optionally, the computing module is configured to split the target account according to the category information of the target account to obtain a plurality of combinations, including: for each bit of the target account, when the category information of the bit meets a first preset condition, the bit is regarded as a reserved bit; when a reserved bit is adjacent to another reserved bit, a plurality of continuously adjacent reserved bits are marked as a combination; when a reserved bit is not adjacent to another reserved bit, the reserved bit is marked as a combination; and the marked combinations constitute the plurality of combinations of the target account.

[0130] The judgment manner of the first preset condition includes:

[0131] For each bit of the target account, a first accumulated value of each frequency is calculated from large to small, until the first accumulated value is greater than or equal to a first numerical value, and at this time, the number of each category is less than or equal to a second numerical value, and it is considered that the first preset condition is met.

[0132] Optionally, before the computing module takes the category in each combination as the encoding rule of the target account, the computing module is further configured to, for each combination, count the category information of each bit in the combination, and when the category information in the combination meets a second preset condition, the category corresponding to the second preset condition is reserved as the category of the combination. The judgment manner of the second preset condition includes:

[0133] A second accumulated value of each frequency is calculated from large to small, until the second accumulated value is greater than or equal to a third numerical value, and it is considered that the second preset condition is met.

[0134] Optionally, the judgment manner of the second preset condition further includes:

[0135] The categories corresponding to each frequency when the second accumulated value is greater than or equal to the third numerical value are subjected to uniformity verification, and if one category meets the uniformity verification, it is considered that the second preset condition is met.

[0136] Optionally, the computing module is further configured to calculate a weight value corresponding to each encoding rule, including: based on the number of encoding rules of the target account and a preset weight value of each encoding rule, the weight value of each encoding rule is calculated. Wherein, the historical corporate bank account numbers of different lengths of each bank are analyzed to obtain the encoding rules corresponding to the corporate bank account numbers of different lengths, which are denoted as first rules.

[0137] Optionally, in addition to the first rules obtained by analyzing the historical corporate bank account numbers of the target bank in the above embodiments, the encoding rules in the embodiments of the present application further include the encoding rules of some banks which have been publicly disclosed, which are denoted as second rules. The computing module is further configured to adjust the weight of each encoding rule according to the length controlled by the rule in combination with the first rules and the second rules.

[0138] The account identification device can identify the public bank account to be identified according to the pre-acquired coding rule, and infer the bank information of the public bank account. In the case that the account information cannot be provided by the remitter, the data support is provided for the remittance agency, the work difficulty of the remittance agency is reduced, and the query time is saved.

[0139] Each module in the account identification device can be realized by software, hardware, and a combination thereof, in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0140] In a feasible embodiment, a computer device, which can be a terminal, has an internal structure as shown in Figure 8 The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication), or other technologies. The computer program is executed by the processor to implement an account identification method. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, a trackball, or a touchpad arranged on the shell of the computer device. The input device can also be an external keyboard, a touchpad, or a mouse, etc.

[0141] Those skilled in the art can understand that Figure 8The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] In a feasible embodiment, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor implements the method steps in the account identification disclosed in the above embodiments when executing the computer program.

[0143] In a feasible embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method steps in the account identification disclosed in the above embodiments.

[0144] In a feasible embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the method steps in the account identification disclosed in the above embodiments.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0146] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0147] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An account identification method, characterized in that, The method includes: Obtain the target bank's corporate account number to be identified; The system iterates through the pre-stored bank information, matches the corporate bank account with the bank information, and selects the bank as a candidate bank when the corporate bank account matches the coding rule of a bank. The bank information includes the coding rules of each bank and the weight value corresponding to each coding rule, and the coding rules are obtained in advance based on the historical corporate bank accounts of the target bank. Calculate the sum of the weight values ​​of the coding rules that are matched in each of the candidate banks; The candidate bank with the highest sum of weight values ​​is selected as the identification result; The encoding rules are obtained in advance based on the historical corporate bank account information of the target bank, including: Obtain multiple historical corporate bank accounts of the target bank, wherein the length of each historical corporate bank account is the same as the length of the target account to be parsed; For each digit of the aforementioned historical corporate bank account, the category information of that digit is statistically analyzed, and the category information of that digit is used as the category information of the same position in the target account. The category information includes the type of occurrence of each digit in that digit and the frequency of occurrence of that type. For each bit of the target account, when the category information of that bit meets the first preset condition, that bit is reserved. When a reserved bit has adjacent reserved bits, the multiple consecutive adjacent reserved bits are marked as a group; When a reserved bit does not have any adjacent reserved bits, the reserved bit is marked as a combination; The aforementioned combinations of markers constitute multiple combinations of the target account; Extract the categories from each combination and use them as the encoding rules for the target account; The method for determining the first preset condition includes: For each digit of the target account, calculate the first cumulative value of each frequency from largest to smallest until the first cumulative value is greater than or equal to the first value, and at this time the sum of the number of each type is less than or equal to the second value, then the first preset condition is considered to be satisfied.

2. The method according to claim 1, characterized in that, The bank information also includes the account length information of each bank; The matching of the corporate bank account and the bank information also includes: Based on the length of the corporate bank account, query the account length information of each of the aforementioned banks; Banks with the same length as the corporate bank account number are selected as alternative banks; Match the corporate bank account number with the coding rules of each of the candidate banks.

3. The method according to claim 1 or 2, characterized in that, Before extracting the categories from each combination as the encoding rules for the target account, the method further includes: The category information of each combination is statistically analyzed. When the category information of a combination meets the second preset condition, the category corresponding to the condition is retained as the category of the combination.

4. The method according to claim 3, characterized in that, The determination method for the second preset condition includes: Calculate the second accumulated value for each frequency from largest to smallest, until the second accumulated value is greater than or equal to the third value; Uniformity verification is performed on the types corresponding to each frequency when the second accumulated value is greater than or equal to the third value; If a species meets the uniformity check, it is considered to meet the second preset condition.

5. The method according to claim 1 or 2, characterized in that, The method further includes: Based on the number of encoding rules for the target account and the preset weight of each encoding rule, the weight value of each encoding rule is calculated.

6. An account recognition device, characterized in that, The device includes: The acquisition module is used to acquire the target bank's corporate bank account number to be identified; The identification module is used to traverse the pre-stored bank information, match the corporate bank account with the bank information, and select the bank as a candidate bank when the corporate bank account matches the coding rule of a bank. The bank information includes the coding rules of each bank and the weight value corresponding to each coding rule, and the coding rules are obtained in advance based on the historical corporate bank accounts of the target bank. The filtering module is used to calculate the sum of the weight values ​​of the coding rules in each candidate bank; and select the candidate bank with the highest sum of weight values ​​as the identification result. A calculation module is used to obtain multiple historical corporate bank accounts of the target bank, wherein the length of each historical corporate bank account is the same as the length of the target account to be parsed; for each digit of each historical corporate bank account, the category information of that digit is calculated, and the category information of that digit is used as the category information of the same position in the target account, wherein the category information includes the type of occurrence of each digit in that digit and the frequency of occurrence of that type; for each digit of the target account, when the category information of that digit meets a first preset condition, that digit is reserved; when a reserved digit has adjacent reserved digits, multiple consecutive adjacent reserved digits are marked as a group; when a reserved digit does not have adjacent reserved digits, that reserved digit is marked as a group; the above-marked groups constitute multiple groups of the target account; the categories in each group are extracted as the encoding rules of the target account; The method for determining the first preset condition includes: for each digit of the target account, calculating the first cumulative value of each frequency from largest to smallest, until the first cumulative value is greater than or equal to the first value, and at this time the sum of the number of each type is less than or equal to the second value, then the first preset condition is considered to be satisfied.

7. The apparatus according to claim 6, characterized in that, The bank information also includes the account length information of each bank; The identification module is further configured to query the account length information of each bank according to the length of the corporate bank account; select banks whose length is the same as the length of the corporate bank account as candidate banks; and match the corporate bank account with the coding rules of each candidate bank.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1-5.

10. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-5.

Images