Keyword positioning method and device for message

Abstract

The application discloses a kind of message keyword positioning method and device, it is related to artificial intelligence technical field, the method includes: original message keyword and original message are carried out text processing, obtain target message keyword and target message;The text processing includes symbol elimination processing, synonym conversion and input form conversion;The original message keyword is used to describe the keyword of the financial risk characteristic of bank;The target message keyword is matched with target message with text;When text matching is successful, determine the message field matched with the target message keyword in the target message;When text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated;The field of the text similarity exceeding preset value is determined as the message field and is marked processing.The application is used to improve the accuracy and efficiency of message keyword positioning.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a message keyword positioning method and device. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the application recited in the claims. The description herein does not constitute admission that the prior publication, square, or subject matter described herein and / or the material contained therein are prior art to the claimed application.

[0003] At present, the screening of the financial risk keyword list needs to identify the message, so as to realize the tracing of each financial risk keyword. At present, the content of the financial risk list that is hit is usually displayed in the form of highlighting in the original MT / FMT message during business processing.

[0004] The general processing process of the existing financial risk keyword list system is as follows: the original name of the hit keyword is matched in the original message, and the content of this block is highlighted if it is matched. However, the existing technology is only applicable to the case where the original keyword of the message is retained and the whole word matching can be performed in the original message. However, at present, due to the existence of special characters and synonymous words in the message text, or the error of the text, the original position cannot be matched in the original message, resulting in the problem of limitation of message keyword positioning, and also reducing the efficiency of message keyword positioning. SUMMARY

[0005] The embodiments of the present application provide a message keyword positioning method for improving the accuracy and efficiency of message keyword positioning, which comprises:

[0006] Text processing is performed on the original message keyword and the original message to obtain a target message keyword and a target message; the text processing includes symbol elimination processing, synonymous word conversion and input form conversion; the original message keyword is used to describe the keyword of the financial risk characteristics of the bank;

[0007] Text matching is performed on the target message keyword and the target message;

[0008] When the text matching is successful, the message field in the target message that matches the target message keyword is determined; when the text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; the field whose text similarity exceeds a preset value is determined as the message field in the target message that matches the target message keyword;

[0009] The field in the original message associated with the message field is marked

[0010] The embodiments of the present application also provide a message keyword positioning device for improving the accuracy and efficiency of message keyword positioning, which comprises:

[0011] a text processing module, configured to perform text processing on the original message keywords and the original message to obtain target message keywords and a target message; the text processing includes symbol elimination processing, synonym conversion and input form conversion; the original message keywords are used to describe the keywords of the financial risk characteristics of the bank;

[0012] a text matching module, configured to perform text matching on the target message keywords and the target message;

[0013] a message field determination module, configured to, when the text matching is successful, determine a message field in the target message that matches the target message keywords; when the text matching is unsuccessful, calculate a text similarity between each target message keyword and each field in the target message; and determine, as the message field in the target message that matches the target message keywords, a field whose text similarity exceeds a preset value.

[0014] a label processing module, configured to perform label processing on a field in the original message that is associated with the message field.

[0015] The embodiment of the present application further provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the keyword positioning method of the message when executing the computer program.

[0016] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the keyword positioning method of the message.

[0017] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the keyword positioning method of the message.

[0018] In the embodiment of the present application, the original message key and the original message are subjected to text processing to obtain a target message key and a target message; the text processing includes symbol elimination processing, synonym conversion and input form conversion; the original message key is used to describe the key of the financial risk characteristics of the bank; the target message key is subjected to text matching with the target message; when the text matching is successful, the message field in the target message that matches the target message key is determined; when the text matching is unsuccessful, the text similarity between each target message key and each field in the target message is calculated; the field with the text similarity exceeding a preset value is determined as the message field in the target message that matches the target message key; the field in the original message associated with the message field is subjected to marking processing; compared with the prior art that cannot accurately match the key when the message text is wrong, the text processing of the key and the message and the calculation of the text similarity between each target message key and each field in the target message solve the problem that the message cannot be accurately positioned due to the message text in the prior art, and improve the accuracy and efficiency of the message key positioning. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort. In the drawings:

[0020] Figure 1 A flowchart of a message key positioning method in the embodiment of the present application;

[0021] Figure 2 A structure example diagram of a message key positioning device in the embodiment of the present application;

[0022] Figure 3 A specific example diagram of a message key positioning device in the embodiment of the present application;

[0023] Figure 4 A specific example diagram of a message key positioning device in the embodiment of the present application;

[0024] Figure 5 A schematic diagram of a computer device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the embodiments of the present application are further described in detail below with reference to the drawings. Herein, the illustrative embodiments of the present application and the description thereof are used to explain the present application, but are not as a limitation of the present application.

[0026] The term "and / or", merely describes an associated relationship, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B and C, which means including any one or more elements selected from the set consisting of A, B and C.

[0027] In the description of the present application, "including", "containing", "having", "comprising", and the like are all open terms, which means including but not limited to. The description of the terms "one embodiment", "one specific embodiment", "some embodiments", "for example", and the like means that the specific features, structures or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. The order of steps involved in the embodiments is used to illustrate the embodiments of the present application, and the order of steps is not limited, which can be adjusted as needed.

[0028] In the technical scheme of the present application, the acquisition, storage, use, processing and the like of data comply with the relevant provisions of national laws and regulations.

[0029] At present, the screening of the financial risk keyword list needs to identify the message, so as to realize the tracing of each financial risk keyword. At present, the content of the financial risk list that is hit is generally displayed in the form of highlighting in the original MT / FMT message during business processing.

[0030] The general processing process of the existing financial risk keyword list system is as follows: the original name of the hit keyword is matched in the original message, and the content is highlighted if it is matched. However, the existing technology is only applicable to the case where the original keyword of the message is retained and the whole word matching can be performed in the original message. However, at present, due to the existence of special characters and synonymous words in the message text, or the error of the text, the original position cannot be matched in the original message, which leads to the problem of limitation of the positioning of the keyword of the message, and also reduces the efficiency of the positioning of the keyword of the message.

[0031] To address the aforementioned problems, embodiments of the present invention provide a method for keyword location in messages, thereby improving the accuracy and efficiency of message keyword location. See [link to relevant documentation]. Figure 1 The method may include:

[0032] Step 101: Perform text processing on the original message keywords and the original message to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank;

[0033] Step 102: Perform text matching between the target message keywords and the target message;

[0034] Step 103: When text matching is successful, determine the message field in the target message that matches the target message keyword; when text matching is unsuccessful, calculate the text similarity between each target message keyword and each field in the target message; determine the field whose text similarity exceeds a preset value as the message field in the target message that matches the target message keyword.

[0035] Step 104: Mark the fields in the original message associated with the message field.

[0036] In this embodiment of the invention, text processing is performed on the original message keywords and the original message to obtain target message keywords and target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank; the target message keywords are matched with the target message; when the text matching is successful, the message fields in the target message that match the target message keywords are determined; when the text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; Fields whose text similarity exceeds a preset value are identified as message fields in the target message that match the target message keyword. Fields in the original message associated with the message field are marked. Compared with the existing technology that cannot accurately match keywords when the message text is incorrect, this technology solves the problem of inaccurate message location due to message text issues by processing the text of keywords and messages, and calculating the text similarity between each target message keyword and each field in the target message, thereby improving the accuracy and efficiency of message keyword location.

[0037] In practice, the original message keywords and the original message are first processed to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank.

[0038] In this embodiment, special characters, including punctuation marks, are removed from the keywords, and English letters are converted to uppercase to obtain the preprocessed keywords. Similarly, special characters, including punctuation marks, are removed from the original message, and English letters are converted to uppercase to obtain the preprocessed message.

[0039] In practice, after processing the original message keywords and the original message to obtain the target message keywords and the target message, the target message keywords are matched with the target message.

[0040] In specific implementation, after matching the target message keyword with the target message, if the text matching is successful, the message field in the target message that matches the target message keyword is determined; if the text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; the field whose text similarity exceeds a preset value is determined as the message field in the target message that matches the target message keyword; and the fields in the original message associated with the message field are marked.

[0041] In one embodiment, it also includes:

[0042] When processing the original message to obtain the target message, record the mapping relationship between each field in the original message and each field in the target message;

[0043] The marking process for fields in the original message associated with the aforementioned message field includes:

[0044] Based on the mapping relationship, determine the fields in the original message associated with the message fields;

[0045] The fields in the original message associated with the message field are marked.

[0046] In this embodiment, when the original message is processed to obtain the target message, the mapping relationship between each field in the original message and each field in the target message is recorded. The position of each character in the original message can be recorded by traversing the preprocessed message, which is used to locate the string that needs to be highlighted in the original message later.

[0047] In this embodiment, strings of the same length as the preprocessed keywords are extracted from the preprocessed message, and their similarity is calculated. If the similarity exceeds a threshold (e.g., 0.6), the string is considered a potentially highlighted string and added to the result array.

[0048] Find the string with the highest score in the convenience result array, treat it as the matching string, obtain the start and end positions of the matching string, map them to the start and end positions in the original message, and highlight the message content within this range.

[0049] In one embodiment, fields whose text similarity exceeds a preset value are identified as message fields in the target message that match the keywords of the target message, including:

[0050] Fields whose text similarity exceeds a preset value are designated as fields to be processed.

[0051] The field with the highest text similarity among the fields to be processed is determined as the message field in the target message that matches the keyword of the target message.

[0052] In one embodiment, it also includes:

[0053] The message segment containing the field in the original message associated with the message field is subjected to secondary marking processing.

[0054] In this embodiment, the segment containing the field in the original message associated with the message field is subjected to secondary marking processing to determine the segment containing the matched message field, which helps staff to conduct further research on the message.

[0055] In one embodiment, marking the fields in the original message associated with the message field includes:

[0056] Segment the original message into multiple fields;

[0057] Under each field, the fields in the original message associated with the message field are determined in parallel;

[0058] The fields in the original message associated with the message field are marked.

[0059] In this embodiment, matching is performed based on the field. The definitions of each field in the MT / FMT message are different, and they are screened separately in the bank financial risk detection system. Therefore, keywords can segment the message according to the field they are in, reducing the comparison range, increasing matching accuracy, and improving matching efficiency.

[0060] In this embodiment of the invention, text processing is performed on the original message keywords and the original message to obtain target message keywords and target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank; the target message keywords are matched with the target message; when the text matching is successful, the message fields in the target message that match the target message keywords are determined; when the text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; Fields whose text similarity exceeds a preset value are identified as message fields in the target message that match the target message keyword. Fields in the original message associated with the message field are marked. Compared with the existing technology that cannot accurately match keywords when the message text is incorrect, this technology solves the problem of inaccurate message location due to message text issues by processing the text of keywords and messages, and calculating the text similarity between each target message keyword and each field in the target message, thereby improving the accuracy and efficiency of message keyword location.

[0061] This invention also provides a message keyword location device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the message keyword location method, the implementation of this device can refer to the implementation of the message keyword location method; repeated details will not be elaborated further.

[0062] This invention also provides a message keyword location device to improve the accuracy and efficiency of message keyword location, such as... Figure 2 As shown, the device includes:

[0063] The text processing module 201 is used to process the original message keywords and the original message to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank;

[0064] The text matching module 202 is used to perform text matching between the target message keywords and the target message;

[0065] The message field determination module 203 is used to determine the message field in the target message that matches the target message keyword when the text matching is successful; when the text matching is unsuccessful, calculate the text similarity between each target message keyword and each field in the target message; and determine the field whose text similarity exceeds a preset value as the message field in the target message that matches the target message keyword.

[0066] The tagging processing module 204 is used to tag fields in the original message associated with the message fields.

[0067] In one embodiment, such as Figure 3 As shown, it also includes:

[0068] Mapping relationship record module 301 is used for:

[0069] When processing the original message to obtain the target message, record the mapping relationship between each field in the original message and each field in the target message;

[0070] The tag processing module is specifically used for:

[0071] Based on the mapping relationship, determine the fields in the original message associated with the message fields;

[0072] The fields in the original message associated with the message field are marked.

[0073] In one embodiment, the message field determination module is specifically used for:

[0074] Fields whose text similarity exceeds a preset value are designated as fields to be processed.

[0075] The field with the highest text similarity among the fields to be processed is determined as the message field in the target message that matches the keyword of the target message.

[0076] In one embodiment, it also includes:

[0077] The secondary labeling processing module is used for:

[0078] The message segment containing the field in the original message associated with the message field is subjected to secondary marking processing.

[0079] In one embodiment, the tag processing module is specifically used for:

[0080] Segment the original message into multiple fields;

[0081] Under each field, the fields in the original message associated with the message field are determined in parallel;

[0082] The fields in the original message associated with the message field are marked.

[0083] The following is a specific embodiment to illustrate the specific application of the device of the present invention. In this embodiment, as shown in the example... Figure 4 As shown, the various modules of this device can be configured according to... Figure 4 The device may include:

[0084] 1. Data Processing Module

[0085] 1) Keyword preprocessing

[0086] Remove special characters from the keywords, including punctuation marks, and convert English letters to uppercase to obtain preprocessed keywords.

[0087] 2) Message preprocessing

[0088] The special characters, including punctuation marks, are removed from the original message, and English letters are converted to uppercase to obtain the preprocessed message.

[0089] 3) Message location mapping

[0090] Traverse the preprocessed message and record the position of each character in the original message, which will be used to locate the string that needs to be highlighted in the original message later.

[0091] 2. Message matching module

[0092] 1) Match preprocessing keywords in preprocessed messages

[0093] If a match is successful, the start and end positions of the matched string are obtained and mapped to the start and end positions in the original message, highlighting the message content within this range. If a match fails, the process proceeds to the next level of the matching algorithm.

[0094] 2) Similarity matching

[0095] Extract strings of the same length as the preprocessing keywords from the preprocessed message and calculate their similarity. The similarity calculation involves determining the edit distance between the two strings. Edit distance is calculated by determining the minimum number of character changes (additions, deletions, and modifications all count as one change) required to transform string A into string B. This minimum number of changes is then used as the edit distance, and the string length is adjusted to obtain the similarity score. Strings exceeding a threshold (0.6) are considered potentially highlighted and added to the results array.

[0096] Find the string with the highest score in the convenience result array, treat it as the matching string, obtain the start and end positions of the matching string, map them to the start and end positions in the original message, and highlight the message content within this range.

[0097] In this embodiment, the preprocessing of keywords and messages improves the accuracy of matching to the original location.

[0098] In addition, for keywords that cannot be matched precisely, the next level of semantic similarity matching is performed to filter out the string with the highest semantic similarity. This stage is relatively time-consuming, so this operation is only performed for keywords that cannot be matched precisely.

[0099] Matching is performed based on field definitions. Since the definitions of each field in the MT / FMT message are different, they are screened separately in the banking financial risk detection system. Therefore, keywords can be segmented according to their field to reduce the comparison range, increase matching accuracy, and improve matching efficiency.

[0100] Here is an example of packet segmentation:

[0101] According to the message specification, each field in the message is separated by a specific character, such as 50K:***. The content following this character belongs to the 50K field, and continues until the start marker of the next field. Based on this rule, the corresponding field content can be found by the field name, allowing for message segmentation.

[0102] This invention provides a scheme for displaying the results of a list screening. This scheme can more accurately find the list of financial risk keywords (pre-selected) by handling variations and synonym conversions. In other words, it finds the original position of the original MT / FMT message corresponding to the keyword to be corrected (e.g., a misspelled name) and highlights it in the original MT / FMT message, so that business personnel know which part of the message content contains the list of financial risk keywords.

[0103] Of course, it is understood that there may be other variations of the above detailed modules, and all such variations should fall within the protection scope of this invention.

[0104] This invention provides an embodiment of a computer device for implementing all or part of the keyword location method for the above-mentioned message. The computer device specifically includes the following components:

[0105] The computer device comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between related devices; the computer device can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the computer device can be implemented with reference to the embodiments for implementing the keyword location method for messages and the embodiments for implementing the keyword location device for messages, the contents of which are incorporated herein by reference, and repeated details will not be described again.

[0106] Figure 5 This is a schematic block diagram illustrating the system configuration of the computer device 1000 according to an embodiment of this application. Figure 5 As shown, the computer device 1000 may include a central processing unit 1001 and a memory 1002; the memory 1002 is coupled to the central processing unit 1001. It is worth noting that... Figure 5This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0107] In one embodiment, the message keyword location function can be integrated into the central processing unit 1001. The central processing unit 1001 can be configured to perform the following control:

[0108] Text processing is performed on the original message keywords and the original message to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank;

[0109] The target message keywords are matched with the target message text.

[0110] When text matching is successful, the message field in the target message that matches the target message keyword is determined; when text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; and the field whose text similarity exceeds a preset value is determined as the message field in the target message that matches the target message keyword.

[0111] The fields in the original message associated with the message field are marked.

[0112] In another embodiment, the message keyword location device can be configured separately from the central processing unit 1001. For example, the message keyword location device can be configured as a chip connected to the central processing unit 1001, and the message keyword location function can be implemented through the control of the central processing unit.

[0113] like Figure 5 As shown, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It is worth noting that the computer device 1000 does not necessarily need to include... Figure 5 All components shown; in addition, the computer device 1000 may also include Figure 5 For components not shown, please refer to existing technologies.

[0114] like Figure 5 As shown, the central processing unit 1001, sometimes also referred to as a controller or operation control, may include a microprocessor or other processor device and / or logic device. The central processing unit 1001 receives input and controls the operation of various components of the computer device 1000.

[0115] The memory 1002 may be, for example, one or more of a cache, flash memory, hard drive, removable medium, volatile memory, non-volatile memory, or other suitable device. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 1001 may execute the program stored in the memory 1002 to perform information storage or processing, etc.

[0116] Input unit 1004 provides input to central processing unit 1001. This input unit 1004 may be, for example, a keypad or touch input device. Power supply 1007 provides power to computer device 1000. Display 1006 displays images, text, and other display objects. This display may be, for example, an LCD display, but is not limited to this.

[0117] The memory 1002 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs, etc. The memory 1002 can also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 may include an application / function storage unit 1022 for storing application programs and function programs or processes for executing operations of the computer device 1000 via the central processing unit 1001.

[0118] The memory 1002 may also include a data storage unit 1023 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. The driver storage unit 1024 of the memory 1002 may include various drivers for the computer device for communication functions and / or for performing other functions of the computer device (such as messaging applications, address book applications, etc.).

[0119] The communication module 1003 is a transmitter / receiver 1003 that transmits and receives signals via the antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processing unit 1001 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0120] Based on different communication technologies, multiple communication modules 1003 can be configured in the same computer device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide audio output via the speaker 1009 and receive audio input from the microphone 1010, thereby realizing typical telecommunications functions. The audio processor 1005 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 1005 is also coupled to a central processing unit 1001, enabling on-device recording via the microphone 1010 and on-device playback of stored sound via the speaker 1009.

[0121] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned keyword location method for messages.

[0122] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned keyword location method for messages.

[0123] In this embodiment of the invention, text processing is performed on the original message keywords and the original message to obtain target message keywords and target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank; the target message keywords are matched with the target message; when the text matching is successful, the message fields in the target message that match the target message keywords are determined; when the text matching is unsuccessful, the text similarity between each target message keyword and each field in the target message is calculated; Fields whose text similarity exceeds a preset value are identified as message fields in the target message that match the target message keyword. Fields in the original message associated with the message field are marked. Compared with the existing technology that cannot accurately match keywords when the message text is incorrect, this technology solves the problem of inaccurate message location due to message text issues by processing the text of keywords and messages, and calculating the text similarity between each target message keyword and each field in the target message, thereby improving the accuracy and efficiency of message keyword location.

[0124] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 Figure 1 The steps of the function specified in one or more boxes.

[0128] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A keyword location method for a message, characterized in that, include: Text processing is performed on the original message keywords and the original message to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank; The target message keywords are matched with the target message text. When a text match is successful, determine the message field in the target message that matches the target message keyword; When text matching fails, calculate the text similarity between each target message keyword and each field in the target message; determine the fields whose text similarity exceeds a preset value as message fields in the target message that match the target message keyword; The fields in the original message associated with the aforementioned message field are marked. The marking process for fields in the original message associated with the message field includes: segmenting the original message into multiple fields; determining, in parallel, the fields in the original message associated with the message field under each field; marking the fields in the original message associated with the message field; wherein, matching is performed according to the fields, and screening is performed separately during the screening in the bank financial risk detection system; the fields are defined differently in MT / FMT messages.

2. The method as described in claim 1, characterized in that, Also includes: When processing the original message to obtain the target message, record the mapping relationship between each field in the original message and each field in the target message; The marking process for fields in the original message associated with the aforementioned message field includes: Based on the mapping relationship, determine the fields in the original message associated with the message fields; The fields in the original message associated with the message field are marked.

3. The method as described in claim 1, characterized in that, Fields whose text similarity exceeds a preset value are identified as message fields in the target message that match the keywords of the target message, including: Fields whose text similarity exceeds a preset value are designated as fields to be processed. The field with the highest text similarity among the fields to be processed is determined as the message field in the target message that matches the keyword of the target message.

4. The method as described in claim 1, characterized in that, Also includes: The message segment containing the field in the original message associated with the message field is subjected to secondary marking processing.

5. A message keyword location device, characterized in that, include: The text processing module is used to process the original message keywords and the original message to obtain the target message keywords and the target message; the text processing includes symbol removal, synonym conversion, and input format conversion; the original message keywords are keywords used to describe the financial risk characteristics of the bank; The text matching module is used to perform text matching between the target message keywords and the target message; The message field determination module is used to determine the message field in the target message that matches the target message keyword when the text matching is successful; when the text matching is unsuccessful, it calculates the text similarity between each target message keyword and each field in the target message; and determines the field whose text similarity exceeds a preset value as the message field in the target message that matches the target message keyword. A marking processing module is used to mark fields in the original message associated with the message field; The marking processing module is specifically used for: segmenting multiple fields of the original message; determining, in parallel, the fields in the original message associated with the message field under each field; and marking the fields in the original message associated with the message field. Specifically, matching is performed based on the fields, and screening is conducted separately during the screening process of the bank financial risk detection system. The fields are defined differently in MT / FMT messages.

6. The apparatus as claimed in claim 5, characterized in that, Also includes: The mapping relationship recording module is used for: When processing the original message to obtain the target message, record the mapping relationship between each field in the original message and each field in the target message; The tag processing module is specifically used for: Based on the mapping relationship, determine the fields in the original message associated with the message fields; The fields in the original message associated with the message field are marked.

7. The apparatus as claimed in claim 5, characterized in that, The message field determination module is specifically used for: Fields whose text similarity exceeds a preset value are designated as fields to be processed. The field with the highest text similarity among the fields to be processed is determined as the message field in the target message that matches the keyword of the target message.

8. The apparatus as claimed in claim 5, characterized in that, Also includes: The secondary labeling processing module is used for: The message segment containing the field in the original message associated with the message field is subjected to secondary marking processing.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images