Flow identification method for operating loan and related device

Abstract

The invention discloses a flow identification method and a related device for business loan, and relates to the technical field of computers, and the method comprises the steps: obtaining a to-be-screened flow file and a target flow analysis template matched with a key identifier in the to-be-screened flow file, analyzing a flow detail set from the to-be-screened flow file based on the target flow analysis template, generating a first flow rule at least based on a preset first keyword, and matching the flow detail set with the first flow rule to screen out a first flow detail from the flow detail set. According to the method and the device, the first flow detail which can be used as an operation type loan auditing basis in the to-be-screened flow file can be identified based on the target flow analysis template and the first flow rule, so that the identification efficiency of the first flow detail is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a transaction flow identification method and related device for operating loans. Background Art

[0002] Many products in the personal loan business require self-employed users to provide business flow in recent years to prove their income. Currently, the account manager can only manually outline the business income flow information that meets the requirements from the paper materials provided by the self-employed users, and then enter it into the spreadsheet for calculation.

[0003] However, the paper materials provided by self-employed users usually contain a large amount of transaction information, which results in a manual method of outlining the required income transaction information, which consumes a lot of human resources and is extremely inefficient. Summary of the invention

[0004] In view of the above problems, the present application provides a method and a related device for identifying operating loan flow, so as to realize the purpose of automatically and quickly screening out the income flow details that meet the requirements from the flow files to be screened. The specific scheme is as follows:

[0005] The first aspect of the present application provides a method for identifying flow of operating loans, comprising:

[0006] Obtaining a transaction file to be screened and a target transaction parsing template that matches a key identifier in the transaction file to be screened, wherein the transaction file to be screened refers to a transaction file generated based on the income and expenditure behavior of the target user in the financial software, and the key identifier is related to the financial software;

[0007] Parsing a flow detail set from the flow file to be screened based on the target flow parsing template;

[0008] Generate a first flow rule based on at least a preset first keyword, wherein the preset first keyword refers to a keyword that can be used as a basis for reviewing business loans;

[0009] The transaction detail set is matched with the first transaction rule to filter out the first transaction detail from the transaction detail set.

[0010] In a possible implementation, matching the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set includes:

[0011] generating a second flow rule based at least on a preset second keyword, wherein the preset second keyword refers to a keyword that cannot be used as a basis for reviewing the operating loan;

[0012] The transaction detail set is matched with the first transaction rule and the second transaction rule respectively to filter out the first transaction detail, the second transaction detail and the third transaction detail from the transaction detail set, wherein the second transaction detail refers to the transaction detail filtered out based on the second transaction rule, and the third transaction detail refers to the transaction detail in the transaction detail set excluding the first transaction detail and the second transaction detail.

[0013] In a possible implementation, obtaining a target pipeline parsing template that matches a key identifier in the pipeline file to be screened includes:

[0014] Based on the pre-established correspondence between the identifier and the pipeline parsing template and the key identifier in the pipeline file to be screened, the target pipeline parsing template is obtained;

[0015] The generation process of the pipeline parsing template in the corresponding relationship includes:

[0016] Obtain historical transaction files from various financial institutions;

[0017] For each of the financial institutions, the historical bank statements:

[0018] According to whether the historical transaction files of the financial institution contain table borders, the historical transaction files of the financial institution are classified as transaction files with borders or transaction files without borders;

[0019] If the historical transaction file of the financial institution is the transaction file with frame lines, the historical transaction file of the financial institution is segmented by columns according to the frame lines using the pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated, and the transaction parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position;

[0020] If the historical transaction file of the financial institution is the transaction file without frame lines, frame lines are generated for the historical transaction file of the financial institution, the historical transaction file of the financial institution is segmented by column according to the frame lines using the pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated, and a transaction parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position;

[0021] The transaction analysis templates corresponding to the financial institutions are obtained as the transaction analysis templates in the corresponding relationship.

[0022] In a possible implementation, before parsing the flow detail set from the flow file to be screened based on the target flow parsing template, the method further includes:

[0023] Using the target pipeline parsing template to read each character in the pipeline file to be screened, calculating the inclination slope of each character read, screening characters whose inclination slope is greater than a preset slope threshold, and removing the screened characters from the pipeline file to be screened;

[0024] and / or,

[0025] Detect whether there is an XObject object of a picture in a preset format in the pipeline file to be filtered. If so, remove the XObject object from the pipeline file to be filtered.

[0026] In a possible implementation, matching the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set includes:

[0027] Determining an income transaction detail set from the transaction detail set according to the transaction type contained in each transaction detail in the transaction detail set;

[0028] splicing the transaction notes, transaction remarks and relevant information of the counterparty contained in each transaction detail in the set of income transaction details to obtain splicing information corresponding to each transaction detail in the set of income transaction details;

[0029] The first transaction detail is filtered out from the income transaction detail set according to the splicing information corresponding to each transaction detail in the income transaction detail set.

[0030] In a possible implementation, the key identifier is an identifier of the financial institution to which the financial software belongs, or a digital string encoded for the financial institution to which the financial software belongs.

[0031] A second aspect of the present application provides a flow identification device for operating loans, comprising:

[0032] A data acquisition module, used to acquire a flow file to be screened and a target flow parsing template that matches a key identifier in the flow file to be screened, wherein the flow file to be screened refers to a flow file generated based on the income and expenditure behavior of the target user in the financial software, and the key identifier is related to the financial software;

[0033] A file parsing module, used for parsing a flow detail set from the flow file to be screened based on the target flow parsing template;

[0034] A rule generation module, configured to generate a first flow rule based at least on a preset first keyword, wherein the preset first keyword refers to a keyword that can be used as a basis for reviewing business loans;

[0035] A rule matching module is used to match the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set.

[0036] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the transaction flow identification method for operating loans according to the first aspect or any implementation method of the first aspect.

[0037] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0038] The memory is used to store computer programs;

[0039] The processor is used to execute the computer program so that the electronic device can implement the transaction flow identification method for operating loans according to the first aspect or any implementation method of the first aspect.

[0040] The fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the transaction identification method for operating loans according to the above-mentioned first aspect or any implementation method of the first aspect.

[0041] By means of the above technical solution, the transaction flow identification method for operating loans provided by the present application obtains a transaction flow file to be screened and a target transaction flow parsing template that matches a key identifier in the transaction flow file to be screened, parses a transaction flow detail set from the transaction flow file to be screened based on the target transaction flow parsing template, generates a first transaction flow rule based on at least a preset first keyword, matches the transaction flow detail set with the first transaction flow rule, and screens out the first transaction flow detail from the transaction flow detail set. The present application can identify the first transaction flow detail in the transaction flow file to be screened that can be used as the basis for the review of operating loans based on the target transaction flow parsing template and the first transaction flow rule, thereby improving the recognition efficiency of the first transaction flow detail and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0043] Figure 1 A schematic diagram of a system architecture provided for this application;

[0044] Figure 2A schematic diagram of an optional hardware structure of the terminal 100 provided in this application;

[0045] Figure 3 A schematic diagram of the structure of a server 200 provided in this application;

[0046] Figure 4 A flow chart of a method for identifying the flow of operating loans provided in this application;

[0047] Figure 5 A schematic diagram of the structure of a flow identification device for operating loans provided in this application;

[0048] Figure 6 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0050] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0051] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] See also Figure 1 , Figure 1 A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0053] Among them, an application can be installed on the terminal 100, and the above application and web page can provide an interface. The terminal 100 can receive relevant parameters entered by the user on the interface and send the above parameters to the server 200. The server 200 can obtain processing results based on the received parameters and return the processing results to the terminal 100.

[0054] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the cooperation of the server, and the embodiments of the present application are not limited to this.

[0055] Next describe Figure 1 The product form of the mid-terminal 100;

[0056] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any restrictions on this.

[0057] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0058] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0059] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0060] Among them, the input device 132 can receive input data and the like.

[0061] The display unit 140 may be used to display information input by the user or provided to the user, various menus of the terminal 100, interactive interfaces, file display, and / or playback of any multimedia file. In the embodiment of the present application, the display unit 140 may be used to display an interface indicating whether the loan application is successful, intermediate processing results (such as the total amount of the loan reference income flow, the number of flows, etc.), etc.

[0062] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0063] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0064] Among them, the memory 120 can be used to store software codes related to the cash flow identification method for operating loans, the processor 170 can execute the steps of the cash flow identification method for operating loans, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to achieve corresponding functions.

[0065] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (Global System of Mobile Communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0066] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0067] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0068] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0069] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0070] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0071] Next describe Figure 1 The product form of the server 200;

[0072] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0073] The bus 201 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0074] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0075] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0076] Among them, the memory 204 can be used to store software codes related to the cash flow identification method for operating loans, the processor 202 can execute the steps of the cash flow identification method for operating loans of the chip, and can also schedule other units to realize corresponding functions.

[0077] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), general-purpose processors, DSPs, microprocessors or microcontrollers, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0078] The present application provides a method for identifying bank flow for operating loans. The following is a detailed introduction to the method for identifying bank flow for operating loans in accordance with an embodiment of the present application in conjunction with the accompanying drawings.

[0079] Reference Figure 4 , Figure 4 A flow chart of a method for cash flow identification for operating loans provided in an embodiment of the present application is provided. The method for cash flow identification for operating loans can be applied to a cash flow identification system for operating loans (hereinafter referred to as the cash flow identification system or system).

[0080] Specifically, the flow identification method for operating loans may include:

[0081] Step S401: Obtain a pipeline file to be screened and a target pipeline parsing template that matches a key identifier in the pipeline file to be screened.

[0082] The transaction files to be screened refer to transaction files in Portable Document Format (PDF) generated based on the income and expenditure behaviors of target users in financial software.

[0083] The above-mentioned financial software may be software developed by a bank, such as bank mobile banking, or software developed by a non-bank financial group.

[0084] Optionally, the transaction file to be screened may be a transaction file provided by the target user to the account manager, which is then uploaded to the system by the account manager, so that this application can obtain the transaction file to be screened.

[0085] Considering that the bank transaction files provided by the target user to the account manager may be falsified, if the operating loan review is based on the falsified files, the review results will be inaccurate. In order to avoid falsification, in a better implementation, this embodiment can establish a channel for interacting with the financial software, and obtain the bank transaction files to be screened from the financial software through the channel. In this way, the bank transaction files to be screened do not have to pass through the target user and the account manager, which saves labor costs on the one hand, and prevents the bank transaction files to be screened from being tampered with by humans on the other.

[0086] Optionally, the method for establishing an interactive channel with financial software may include: obtaining the version number and system version number of the financial software, inputting the version number and system version number of the financial software into a preset channel generation component, so that the channel generation component splices the version number of the financial software with the system version number, calculating a hash value for the spliced ​​version number, and then calculating the sum of the number of historical versions of the financial software and the number of historical versions of the flow identification system provided by the present application, taking the remainder of the hash value according to the sum, searching for a data transmission channel numbered as the remainder from multiple established data transmission channels, configuring between the financial software and the flow identification system based on the found data transmission channel, and obtaining an interactive channel between the financial software and the flow identification system.

[0087] Optionally, the method for obtaining the flow file to be screened from the financial software through the above-mentioned interactive channel includes: generating a flow acquisition request, which includes the identification of the target user and the public key in the key pair pre-generated for the target user; transmitting the flow acquisition request to the financial software through the interactive channel, so that the financial software encrypts the flow file of the target user based on the public key, and then transmits the flow ciphertext through the interactive channel, and this embodiment (i.e., the flow identification system) then decrypts the flow ciphertext based on the private key in the key pair to obtain the decrypted flow file, i.e., the flow file to be screened obtained by this embodiment.

[0088] Optionally, in order to avoid the risk of pipeline transmission leakage caused by the leakage of key pairs, this embodiment can generate random numbers through a random number generator on the one hand, and on the other hand collect videos for target users, and generate key pairs based on the personalized characteristics of the target users in the video and random numbers.

[0089] Optionally, the personalized feature includes one or more of the following features: the target user's hairstyle, hair color, lip color, eyebrow shape, personalized gestures and personalized postures. Here, personalized gestures and personalized postures refer to one or more gestures and postures that the target user deliberately makes in order to avoid leakage of the key pair.

[0090] The above-mentioned pipeline file to be screened is set with a key identifier. By parsing the pipeline file to be screened, the key identifier in the pipeline file to be screened can be obtained, and then based on the pre-established correspondence between the identifier and the pipeline parsing template, the target pipeline parsing template matching the key identifier in the pipeline file to be screened is obtained.

[0091] In this embodiment, the key identifier is related to the financial software that generates the transaction file to be screened.

[0092] Optionally, the key identifier may be an identifier of the financial institution to which the financial software belongs, such as the name or Chinese and English abbreviations of the financial institution.

[0093] Preferably, the key identifier may also be a digital string encoded based on the financial institution to which the financial software belongs, for example, a digital string obtained by hashing the name of the financial institution. By encoding the financial institution, the financial institution may not be directly displayed in the flow file, thereby better protecting customer privacy.

[0094] In this embodiment, the key identifier can be added to the transaction file in the form of a watermark, or the key identifier can be directly written into the transaction file, for example, the name of the financial institution is written into the title of the transaction file, such as the title "xx bank transaction flow".

[0095] Step S402: parse a transaction detail set from the transaction file to be screened based on the target transaction parsing template.

[0096] In this embodiment, the positions of the basic elements that constitute the flow details are marked in the target flow parsing template, so that based on the positions of the marked basic elements, the basic elements respectively contained in the flow details can be parsed from the flow file to be screened, and then the flow details contained in the flow file to be screened are composed based on the parsed basic elements as a flow detail set.

[0097] Optionally, the basic elements include but are not limited to the following elements: target user's account name, target user's account number, counterparty's account name, counterparty's account number, transaction amount, transaction time, transaction type, transaction remarks and transaction remarks. Among them, transaction type includes income and expenditure. Among them, the specific expression of transaction type can be the positive and negative sign of the amount, or it can be direct text, such as income type and expenditure type.

[0098] Step S403: Generate a first flow rule based at least on a preset first keyword.

[0099] Among them, the preset first keyword refers to the keyword that can be used as the basis for the review of operating loans.

[0100] In this embodiment, some first keywords can be initialized when developing the transaction flow recognition system. At the same time, the account manager can also configure some new first keywords based on his own experience. The first keywords initialized by the system and the first keywords personalized configured by the account manager are both the above-mentioned preset first keywords.

[0101] Optionally, this step can generate the first flow rule based only on the preset first keyword. Specifically, the initialization income rule is generated based on the first keyword initialized by the system, and the personalized income rule is generated based on the first keyword personalized configured by the account manager. The initialization income rule and the personalized income rule are used as the above-mentioned first flow rule.

[0102] Optionally, a first flow rule may be generated based on a preset first keyword.

[0103] In an optional embodiment, taking into account that the initialized first keyword and the first keyword personalized by the account manager may be incomplete, in order to avoid missing the first transaction details (here, the first transaction details refer to the transaction details that can be used as the basis for the review of operating loans) based on the first transaction rule due to incomplete first keywords, this embodiment can input the training transaction details marked with the first transaction details label and the first keywords related to the training transaction details (including the above-mentioned initialized first keywords and the first keywords personalized by the account manager) into the big model, so that the big model expands the first keywords related to the training transaction details based on the input data, and then generates the first transaction rule based on the expanded first keywords and the first keywords input into the big model.

[0104] Optionally, in order to enable the big model to generate the first flow rule that meets the requirements, the present embodiment may also pre-customize the flow rule template for the big model, for example, "the revenue of the counterparty is XX". The subsequent big model may fill in the customized flow rule template with keywords based on the expanded first keyword and the first keyword input into the big model to obtain the first flow rule.

[0105] In another possible implementation, in order to enable the large model to generate more accurate, comprehensive and more satisfactory first flow rules, a small number of first flow rules can be manually configured in advance or a small number of first flow rules can be pre-generated based on a rule generator. Then, the training flow details marked with the first flow detail labels, the first keywords related to the training flow details and a small number of first flow rules are input into the large model together, so that the large model can learn the user requirements based on a small number of first flow rules, and then generate more satisfactory and comprehensive first flow rules.

[0106] Here, the first keyword input into the large model (i.e., the preset first keyword) may include, for example, the following keywords: loan, material payment, project payment, QR code payment, XX Service Co., Ltd. (UnionPay deposit), XX Payment Co., Ltd., and XX Technology Co., Ltd.

[0107] Of course, the first keyword may also be other keywords, and this application does not specifically limit this.

[0108] Step S404: Match the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set.

[0109] As mentioned above, the transaction file to be screened refers to the transaction file generated based on the income and expenditure behavior of the target user in the financial software, and the transaction detail set includes the transaction details of the income type and the transaction details of the expenditure type. In order to match more quickly, optionally, the income transaction detail set can be screened from the transaction detail set based on the transaction type, and then the income transaction detail set can be matched with the first transaction rule to obtain the screened first transaction details.

[0110] Optionally, "matching the income flow detail set with the first flow rule to obtain the filtered first flow details" may specifically include: splicing the transaction notes, transaction remarks and relevant information of the counterparty contained in each flow detail in the income flow detail set to obtain the splicing information corresponding to each flow detail in the income flow detail set; based on the splicing information corresponding to each flow detail in the income flow detail set, filtering the first flow detail from the income flow detail set.

[0111] It should be noted that the above direct rule matching method is only an example. In addition, this step can also use other methods to filter out the first flow details. For example, each flow detail contained in the flow detail set can be converted into a vector form, and the first flow rule can be converted into a vector form. For example, the BERT (Bidirectional Encoder Representations from Transformers) model can be used to convert each flow detail into a first vector, and the first flow rule can be converted into a second vector, and then a preset similarity algorithm (such as Euclidean distance) is used to calculate the similarity between the first vector and the second vector, and the flow detail corresponding to the first vector whose similarity is greater than the preset similarity threshold is used as the first flow detail.

[0112] The flow identification method for operating loans provided by the present application obtains a flow file to be screened and a target flow parsing template that matches a key identifier in the flow file to be screened, parses a flow detail set from the flow file to be screened based on the target flow parsing template, generates a first flow rule based on at least a preset first keyword, matches the flow detail set with the first flow rule, and screens out the first flow detail from the flow detail set. The present application can identify the first flow detail in the flow file to be screened that can be used as the basis for the review of operating loans based on the target flow parsing template and the first flow rule, thereby improving the recognition efficiency of the first flow detail and reducing labor costs.

[0113] In some embodiments of the present application, the process of step S404 "matching the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set" is introduced.

[0114] In this embodiment, in addition to generating the above-mentioned first flow rule, a second flow rule can also be generated based on a preset second keyword. Here, the preset second keyword refers to a keyword that cannot be used as a basis for review of operating loans.

[0115] Corresponding to the first keyword in the foregoing text, the second keyword in this embodiment includes the second keyword initialized when the transaction identification system is developed and the second keyword personalized configured by the customer manager.

[0116] Optionally, the second keyword includes but is not limited to the following keywords: loan keywords, operating income keywords and fund allocation keywords.

[0117] Optionally, keywords related to lending include but are not limited to the following words: borrow, repay, interest and turnover; keywords related to non-operating income include but are not limited to the following words: medical insurance, provident fund and claims; keywords related to fund allocation include but are not limited to the following words: offset and cash back.

[0118] Furthermore, the transaction detail set can be matched with the first transaction rule and the second transaction rule respectively to filter out the first transaction detail, the second transaction detail and the third transaction detail from the transaction detail set, wherein the second transaction detail refers to the transaction detail filtered out based on the second transaction rule, and the third transaction detail refers to the transaction detail in the transaction detail set except the first transaction detail and the second transaction detail.

[0119] In this embodiment, the process of generating the second flow rule and the rule matching is the same as that in the previous embodiment, and the details can be referred to the previous description, which will not be repeated here.

[0120] Through this embodiment, the first transaction details that can definitely be used as the basis for the review of operating loans, the second transaction details that cannot be used as the basis for the review of operating loans, and the third transaction details that are uncertain whether they can be used as the basis for the review of operating loans can be distinguished. The third transaction details can be manually distinguished later, that is, it can be determined whether to apply for an operating loan for the target user based on the manually distinguished third transaction details and the first transaction details. Compared with the method of directly manually screening all transaction details, this embodiment can only manually distinguish the third transaction details, which improves efficiency and makes the review results more accurate.

[0121] Further to the above description, the process of step S401 of obtaining the target pipeline parsing template matching the key identifier in the pipeline file to be screened specifically refers to obtaining the target pipeline parsing template based on the pre-established correspondence between the identifier and the pipeline parsing template and the key identifier in the pipeline file to be screened.

[0122] In the present embodiment, an optional generation process of a flow parsing template in a corresponding relationship is provided. Optionally, the process may include: obtaining historical flow files of each financial institution; for each historical flow file of a financial institution, classifying the historical flow file of the financial institution as a flow file with a frame line or a flow file without a frame line according to whether the historical flow file of the financial institution contains a table frame line; if the historical flow file of the financial institution is a flow file with a frame line, using a pre-written semantic understanding code to segment the historical flow file of the financial institution by column according to the frame line, and calculating the semantic meaning of the content of each segmented column, based on the semantic meaning of the content of each column The transaction flow parsing template corresponding to the financial institution is generated based on the semantic meaning and column position. If the historical transaction flow file of the financial institution is a transaction flow file without frame lines, a frame line is generated for the historical transaction flow file of the financial institution. The historical transaction flow file of the financial institution is segmented by column according to the frame lines using a pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated. The transaction flow parsing template corresponding to the financial institution is generated based on the semantic meaning and column position of the content of each column. The above process is executed for the historical transaction flow files of all financial institutions, and the transaction flow parsing templates corresponding to each financial institution can be obtained, that is, the transaction flow parsing templates in the corresponding relationship are obtained.

[0123] Optionally, the above-mentioned process of "generating frame lines for the historical transaction files of the financial institution" may include: generating frame lines based on the text positions in the historical transaction files of the financial institution, or outputting the historical transaction files of the financial institution to drawing software, manually adding frame lines to the historical transaction files of the financial institution in the drawing software, and the drawing software then returning the historical transaction files with added frame lines to the transaction recognition system, thereby obtaining the historical transaction files of the financial institution with added frame lines.

[0124] In view of the different formats of transaction files of different financial institutions, this embodiment sets a transaction parsing template for each financial institution, and subsequently the transaction details in the transaction file can be quickly parsed based on the transaction parsing template, thereby improving the parsing efficiency of the transaction details.

[0125] In some other embodiments of the present application, since the pipeline file to be screened contains a lot of noise information that is not pipeline details, this noise information may affect the accuracy and efficiency of the target pipeline parsing template in parsing the pipeline file to be screened.

[0126] To this end, it is necessary to remove the noise information in the pipeline file to be screened before parsing the pipeline detail set from the pipeline file to be screened based on the target pipeline parsing template in step S402.

[0127] In a possible implementation, considering that in the flow file to be screened, the flow details are usually located in a table, and there are usually some oblique texts containing information such as time and user name outside the table, these oblique texts are usually irrelevant to the flow details, and if they are not removed, the accuracy of the subsequent flow details will be affected. In addition, in the flow file to be screened, a watermark is usually stamped, and the watermark may also be an oblique text containing information such as time and user name, which also needs to be removed from the flow file to be screened. For this reason, this embodiment can use the target flow parsing template to read each word in the flow file to be screened before using the flow parsing template to parse the flow details set from the flow file to be screened, calculate the inclination slope of each word read, screen the words whose inclination slope is greater than the preset slope threshold, and remove the screened words from the flow file to be screened.

[0128] In another possible implementation, considering that there may be a watermark in the image format in the flow file to be screened, such as a business-specific seal, in order to avoid the watermark in the image format affecting the subsequent parsing results of the flow details, before using the flow parsing template to parse the flow details set from the flow file to be screened, it is possible to detect whether there is an XObject object in the flow file to be screened, and if so, detect whether the XObject object is a picture in a preset format, and if so, remove the XObject object from the flow file to be screened. Here, the preset format refers to a format that can be represented as an image, such as various image formats such as JPG and PNG.

[0129] Through the noise information elimination process of this embodiment, the accuracy and efficiency of subsequent transaction details analysis results can be improved, thereby improving the accuracy and efficiency of screening out the first transaction details that meet the requirements.

[0130] In another optional embodiment of the present application, in order to avoid obtaining other people's transaction files, after using the transaction parsing template to read the text in the transaction file to be screened, a regular expression can be used to intercept the name field in the text, and the parsed name field can be compared with the name indicated by the name identifier in the transaction acquisition request and / or the pre-input name of the target user. If they are consistent, the transaction parsing template is used to parse the transaction details set from the transaction file to be screened.

[0131] Through the processing of this embodiment, it is possible to avoid adverse effects on the target user's operating loan review results caused by obtaining other people's bank statement files, thereby improving the target user's experience of using the bank statement identification system.

[0132] A method for identifying bank flow of operating loans provided in an embodiment of the present application is introduced above. A device for executing the method for identifying bank flow of operating loans will be introduced below.

[0133] See also Figure 5 , Figure 5 This is a schematic diagram of a structure of a flow identification device for operating loans provided in an embodiment of the present application. Figure 5 As shown, the device may include:

[0134] Data acquisition module 501, used to acquire a transaction file to be screened and a target transaction parsing template that matches a key identifier in the transaction file to be screened, wherein the transaction file to be screened refers to a transaction file generated based on the income and expenditure behavior of the target user in the financial software, and the key identifier is related to the financial software;

[0135] The file parsing module 502 is used to parse the flow details set from the flow file to be screened based on the target flow parsing template;

[0136] A rule generation module 503, configured to generate a first flow rule based at least on a preset first keyword, wherein the preset first keyword refers to a keyword that can be used as a basis for reviewing business loans;

[0137] The rule matching module 504 is used to match the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set.

[0138] In a possible implementation, the process in which the rule matching module matches the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set may include:

[0139] generating a second flow rule based at least on a preset second keyword, wherein the preset second keyword refers to a keyword that cannot be used as a basis for review of operating loans;

[0140] The transaction detail set is matched with the first transaction rule and the second transaction rule respectively to filter out the first transaction detail, the second transaction detail and the third transaction detail from the transaction detail set, wherein the second transaction detail refers to the transaction detail filtered out based on the second transaction rule, and the third transaction detail refers to the transaction detail in the transaction detail set except the first transaction detail and the second transaction detail.

[0141] In a possible implementation, the process of the above-mentioned data acquisition module acquiring the target pipeline parsing template that matches the key identifier in the pipeline file to be screened may include: obtaining the target pipeline parsing template based on the pre-established correspondence between the identifier and the pipeline parsing template and the key identifier in the pipeline file to be screened.

[0142] The generation process of the pipeline parsing template in the corresponding relationship may include:

[0143] Obtain historical transaction files from various financial institutions;

[0144] For each financial institution's historical transaction files:

[0145] According to whether the historical transaction files of the financial institution contain table borders, the historical transaction files of the financial institution are classified as transaction files with borders or transaction files without borders;

[0146] If the historical bank flow file of the financial institution is a bank flow file with frame lines, the pre-written semantic understanding code is used to segment the historical bank flow file of the financial institution by columns according to the frame lines, and the semantic meaning of the content of each segmented column is calculated, and the bank flow parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position;

[0147] If the historical transaction file of the financial institution is a transaction file without frame lines, a frame line is generated for the historical transaction file of the financial institution, and the historical transaction file of the financial institution is segmented by column according to the frame line using the pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated, and the transaction parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position;

[0148] The transaction flow parsing templates corresponding to each financial institution are obtained as the transaction flow parsing templates in the corresponding relationship.

[0149] In a possible implementation, the transaction flow identification device for operating loans provided in the embodiment of the present application may also include: a noise removal module.

[0150] The noise removal module is used to read each character in the pipeline file to be filtered using the target pipeline parsing template before parsing the pipeline detail set from the pipeline file to be filtered based on the target pipeline parsing template, calculate the inclination slope of each read character, filter out the characters with inclination slope greater than a preset slope threshold, remove the filtered characters from the pipeline file to be filtered, and / or detect whether there is an XObject object of a picture in a preset format in the pipeline file to be filtered, and if so, remove the XObject object from the pipeline file to be filtered.

[0151] In a possible implementation, the process in which the rule matching module matches the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set may include:

[0152] According to the transaction type contained in each transaction detail in the transaction detail set, an income transaction detail set is determined from the transaction detail set;

[0153] The transaction notes, transaction remarks and relevant information of the counterparty contained in each transaction detail in the income transaction detail set are spliced ​​together to obtain the splicing information corresponding to each transaction detail in the income transaction detail set;

[0154] According to the splicing information corresponding to each flow detail in the income flow detail set, the first flow detail is filtered out from the income flow detail set.

[0155] In a possible implementation, the key identifier is the identifier of the financial institution to which the financial software belongs, or a digital string encoded for the financial institution to which the financial software belongs.

[0156] The transaction flow identification device for operating loans provided in the embodiment of the present application corresponds to the transaction flow identification method for operating loans described above. The detailed processing process can be referred to the above introduction and will not be repeated here.

[0157] The present application also provides an electronic device in an embodiment. Figure 6 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0158] like Figure 6As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0159] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0160] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the transaction flow identification methods for operating loans provided in the embodiments of the present application.

[0161] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any one of the transaction flow identification methods for operating loans provided in the embodiments of the present application.

[0162] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0163] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0164] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0165] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for identifying business loan flow, characterized in that: include: Obtaining a transaction file to be screened and a target transaction parsing template that matches a key identifier in the transaction file to be screened, wherein the transaction file to be screened refers to a transaction file generated based on the income and expenditure behavior of the target user in the financial software, and the key identifier is related to the financial software; Parsing a flow detail set from the flow file to be screened based on the target flow parsing template; Generate a first flow rule based on at least a preset first keyword, wherein the preset first keyword refers to a keyword that can be used as a basis for reviewing business loans; The transaction detail set is matched with the first transaction rule to filter out the first transaction detail from the transaction detail set.

2. The method for identifying business loan transactions according to claim 1, characterized in that: The step of matching the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set includes: generating a second flow rule based at least on a preset second keyword, wherein the preset second keyword refers to a keyword that cannot be used as a basis for reviewing the operating loan; The transaction detail set is matched with the first transaction rule and the second transaction rule respectively to filter out the first transaction detail, the second transaction detail and the third transaction detail from the transaction detail set, wherein the second transaction detail refers to the transaction detail filtered out based on the second transaction rule, and the third transaction detail refers to the transaction detail in the transaction detail set excluding the first transaction detail and the second transaction detail.

3. The method for identifying business loan flow according to claim 1, characterized in that: Obtaining a target pipeline parsing template that matches the key identifier in the pipeline file to be screened, including: Based on the pre-established correspondence between the identifier and the pipeline parsing template and the key identifier in the pipeline file to be screened, the target pipeline parsing template is obtained; The generation process of the pipeline parsing template in the corresponding relationship includes: Obtain historical transaction files from various financial institutions; For each of the financial institutions, the historical bank statements: According to whether the historical transaction files of the financial institution contain table borders, the historical transaction files of the financial institution are classified as transaction files with borders or transaction files without borders; If the historical transaction file of the financial institution is the transaction file with frame lines, the historical transaction file of the financial institution is segmented by columns according to the frame lines using the pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated, and the transaction parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position; If the historical transaction file of the financial institution is the transaction file without frame lines, frame lines are generated for the historical transaction file of the financial institution, the historical transaction file of the financial institution is segmented by column according to the frame lines using the pre-written semantic understanding code, and the semantic meaning of the content of each segmented column is calculated, and a transaction parsing template corresponding to the financial institution is generated based on the semantic meaning of the content of each column and the column position; The transaction analysis templates corresponding to the financial institutions are obtained as the transaction analysis templates in the corresponding relationship.

4. The method for identifying business loan flow according to claim 1, characterized in that: Before parsing the flow detail set from the flow file to be screened based on the target flow parsing template, the method further includes: Using the target pipeline parsing template to read each character in the pipeline file to be screened, calculating the inclination slope of each character read, screening characters whose inclination slope is greater than a preset slope threshold, and removing the screened characters from the pipeline file to be screened; and / or, Detect whether there is an XObject object of a picture in a preset format in the pipeline file to be filtered. If so, remove the XObject object from the pipeline file to be filtered.

5. The method for identifying business loan flow according to claim 1, characterized in that: The step of matching the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set includes: Determining an income transaction detail set from the transaction detail set according to the transaction type contained in each transaction detail in the transaction detail set; splicing the transaction notes, transaction remarks and relevant information of the counterparty contained in each transaction detail in the set of income transaction details to obtain splicing information corresponding to each transaction detail in the set of income transaction details; The first transaction detail is filtered out from the income transaction detail set according to the splicing information corresponding to each transaction detail in the income transaction detail set.

6. The method for identifying business loan flow according to any one of claims 1 to 5, characterized in that: The key identifier is the identifier of the financial institution to which the financial software belongs, or a digital string encoded for the financial institution to which the financial software belongs.

7. A flow identification device for operating loans, characterized in that: include: A data acquisition module, used to acquire a flow file to be screened and a target flow parsing template that matches a key identifier in the flow file to be screened, wherein the flow file to be screened refers to a flow file generated based on the income and expenditure behavior of the target user in the financial software, and the key identifier is related to the financial software; A file parsing module, used for parsing a flow detail set from the flow file to be screened based on the target flow parsing template; A rule generation module, configured to generate a first flow rule based at least on a preset first keyword, wherein the preset first keyword refers to a keyword that can be used as a basis for reviewing business loans; A rule matching module is used to match the transaction detail set with the first transaction rule to filter out the first transaction detail from the transaction detail set.

8. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the transaction flow identification method for operating loans as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the transaction flow identification method for operating loans as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the transaction identification method for operating loans as described in any one of claims 1 to 6.

Images