CN115344613A

CN115344613A - Accuracy optimization method, apparatus, medium, and device based on bill data inspection

Info

Publication number: CN115344613A
Application number: CN202210951407.7A
Authority: CN
Inventors: 徐彬
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-08-09
Filing date: 2022-08-09
Publication date: 2022-11-15

Abstract

The embodiment of the application provides a method, a device, a medium and equipment for optimizing accuracy based on bill data inspection, wherein the method comprises the following steps: pre-creating a plurality of spot check rules for triggering bill data checking operation in a database; respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each sampling inspection rule in a preset time period; judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value or not; and marking the sampling inspection rule with the total times less than or equal to a first preset threshold value as an abnormal rule, and adjusting the abnormal rule. According to the method and the device, a plurality of spot check rules used for triggering bill data checking operation are created in advance, benefits generated by each spot check rule in bill accuracy checking work are calculated in a timing or real-time mode, validity of the spot check rules is verified, corresponding processing is carried out according to verification results, the spot check rules are specifically deleted or modified, and the fact that invalid spot check rules occupy internal memory is avoided.

Description

Accuracy optimization method, device, medium and equipment based on bill data inspection

Technical Field

The present application relates to the field of electronic communications technologies, and in particular, to a method, an apparatus, a medium, and a device for optimizing accuracy based on bill data inspection.

Background

The credit card bill records information of various transactions, expenses, bill amount to be paid, minimum repayment amount, bill date, repayment date, staging plan and the like of the user in the current account period. From the user level, it is important to maintain a good credit score for the user that a correct credit card bill is issued, and from the bank level, it is also important to ensure that the credit card bill issued to the user is correct to reduce complaints and dispute problems for the user. In order to improve the accuracy of bills, a large number of bills are usually required to be subjected to regular spot check, the accuracy of the bills is estimated according to the check work of the randomly checked bills, when the accuracy is obviously too low, a worker can check whether each key link in the bill generation process is abnormal or not in time, and one stroke is that you check in time. Most of the current spot check modes are random spot checks from a large number of bills, so that the working efficiency is low, the pertinence is weak, part of bills which are easy to be abnormal lack important monitoring, and bills which are difficult to make mistakes are mixed in a spot check sample so that the sample base number is increased, the probability that the bills which need important monitoring are spot checked is reduced, and the expected effect of bill accuracy estimation work can be influenced in actual operation.

Disclosure of Invention

The method for optimizing the accuracy based on the bill data inspection comprises the steps of creating a plurality of spot check rules used for triggering bill data inspection operation in advance, calculating benefits generated by each spot check rule in bill accuracy inspection work in a timing or real-time mode, verifying the effectiveness of the spot check rules and correspondingly processing according to verification results, specifically deleting or modifying, and avoiding the situation that invalid spot check rules occupy a memory.

An embodiment of the present application provides an accuracy optimization method based on bill data inspection, where the accuracy optimization method based on bill data inspection includes:

pre-creating a plurality of spot check rules for triggering bill data checking operation in a database;

respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each sampling inspection rule in a preset time period;

judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value or not;

and marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold as abnormal rules, and adjusting the abnormal rules to optimize the accuracy of the plurality of sampling inspection rules on triggering bill data inspection operation.

In the method for optimizing accuracy based on bill data inspection according to the embodiment of the present application, before the step of respectively recording the total times that each of the spot check rules triggers bill data inspection operation within a preset time period and an inspection result is abnormal, the method further includes:

carrying out keyword extraction operation on each bill to be subjected to data inspection, and selecting a target bill containing preset keywords;

and determining the spot-check rule corresponding to the target bill according to the spot-check rule to which the preset keyword belongs.

In the method for optimizing accuracy based on bill data inspection according to the embodiment of the present application, the performing a keyword extraction operation on each bill to be subjected to data inspection includes:

and inputting each bill to be subjected to data inspection into a pre-trained keyword extraction model to perform keyword extraction operation.

In the method for optimizing accuracy based on bill data inspection according to the embodiment of the present application, before the step of inputting each bill to be data inspected into a pre-trained keyword extraction model for keyword extraction, the method further includes:

acquiring a training sample of a keyword extraction model to be trained, wherein the training sample comprises text data provided with labels;

performing feature extraction on the text data in the training sample through the keyword extraction model to be trained to obtain a text feature vector corresponding to the text data;

identifying keywords of the text data in the training sample based on the text feature vector through the keyword extraction model to be trained to obtain an identification result of the text data;

and adjusting parameters of the keyword extraction model to be trained based on the recognition result and the label of the text data to obtain the pre-trained keyword extraction model.

In the method for optimizing accuracy based on bill data inspection according to the embodiment of the present application, the method further includes:

judging whether the total times corresponding to each sampling inspection rule is less than or equal to a second preset threshold value, wherein the second preset threshold value is less than a first preset threshold value;

and marking the sampling inspection rule with the total times less than or equal to the second preset threshold value as an invalid rule, and deleting the invalid rule.

In the method for optimizing accuracy based on bill data verification according to the embodiment of the present application, after the sampling rule whose total number of times is less than or equal to the second preset threshold is marked as an invalid rule, the method further includes:

and generating notification information containing the invalidation rule and the invalidation reason thereof.

In the accuracy optimization method based on bill data inspection according to the embodiment of the present application, the method further includes:

judging whether the total times corresponding to each sampling inspection rule is larger than a third preset threshold value, wherein the third preset threshold value is larger than the first preset threshold value;

marking the sampling inspection rule of which the total times is greater than the third preset threshold value as a high-frequency rule;

and performing statement enhancement operation based on the high-frequency rule to obtain a plurality of similar rules imitating the expansion of the high-frequency rule, and supplementing the plurality of similar rules into the database.

Correspondingly, another aspect of the embodiments of the present application further provides an accuracy optimization device based on bill data verification, where the accuracy optimization device based on bill data verification includes:

the system comprises a creating module, a checking module and a checking module, wherein the creating module is used for creating a plurality of spot check rules for triggering bill data checking operation in advance in a database;

the recording module is used for respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each spot inspection rule in a preset time period;

the judging module is used for judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value or not;

and the adjusting module is used for marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold as abnormal rules and adjusting the abnormal rules so as to optimize the accuracy of the plurality of sampling inspection rules on triggering bill data inspection operation.

Accordingly, another aspect of the embodiments of the present application further provides a storage medium storing a plurality of instructions, which are suitable for being loaded by a processor to perform the method for optimizing accuracy based on bill data verification as described above.

Correspondingly, another aspect of the embodiments of the present application further provides a terminal device, which includes a processor and a memory, where the memory stores multiple instructions, and the processor loads the instructions to execute the method for optimizing accuracy based on the bill data inspection as described above.

The embodiment of the application provides a method, a device, a medium and equipment for optimizing accuracy based on bill data inspection, wherein the method comprises the steps of pre-creating a plurality of spot inspection rules for triggering bill data inspection operation in a database; respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each sampling inspection rule in a preset time period; judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value or not; and marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold as abnormal rules, and adjusting the abnormal rules to optimize the accuracy of the plurality of sampling inspection rules on triggering bill data inspection operation. By means of the bill data inspection-based accuracy optimization method provided by the embodiment of the application, a plurality of spot check rules for triggering bill data inspection operation are created in advance, the spot check rules can be set according to preset keywords, for example, according to different credit card types, cities, main cards, auxiliary cards, single or double coins, money purchasing, staging plans or not and the like, and the keywords are determined according to bills needing to be monitored in a key mode. When a certain bill in the database triggers the keyword, the bill is determined to meet the requirement of the preset sampling inspection rule. And the benefit generated by each sampling rule in the bill accuracy checking work is calculated in real time or at regular time, so that the validity of the sampling rule is verified and corresponding processing is carried out according to the verification result, specifically, the sampling rule is deleted or modified, and the invalid sampling rule is prevented from occupying the memory.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can also be derived from them without inventive effort.

Fig. 1 is a schematic flowchart of an accuracy optimization method based on bill data inspection according to an embodiment of the present application.

Fig. 2 is a schematic structural diagram of an accuracy optimization device based on bill data verification according to an embodiment of the present application.

Fig. 3 is another schematic structural diagram of an accuracy optimization device based on bill data verification according to an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present application.

The embodiment of the application provides an accuracy optimization method based on bill data inspection, and the accuracy optimization method based on bill data inspection can be applied to terminal equipment. The terminal equipment can be equipment such as a smart phone and a computer.

It should be noted that the following is a brief introduction to the background of the present solution:

the scheme is mainly developed around the technical problem of how to improve the effectiveness of the spot check rule for triggering the bill data checking operation and avoid the invalid spot check rule from occupying the memory, and the bill specifically refers to a credit card bill. As will be appreciated, the credit card bill records the transaction, charge, amount of the bill to be paid, minimum amount of the payment, date of the bill, date of the payment, and schedule of the installment that occurred during the current account period. From the user level, it is important to maintain a good credit score for the user that a correct credit card bill is issued, and from the bank level, it is also important to ensure that the credit card bill issued to the user is correct to reduce complaints and dispute problems for the user.

In order to improve the accuracy of the bill, a large amount of bills are usually required to be subjected to regular spot check inspection, the accuracy of the bill is estimated according to the check work of the randomly checked bills, when the accuracy is obviously too low, a worker can check whether each key link in the bill generation process is abnormal or not in time, and one time is you check in time. Most of the current spot check modes are random spot checks from a large number of bills, so that the working efficiency is low, the pertinence is weak, part of bills which are easy to be abnormal lack important monitoring, and bills which are difficult to make mistakes are mixed in a spot check sample so that the sample base number is increased, the probability that the bills which need important monitoring are spot checked is reduced, and the expected effect of bill accuracy estimation work can be influenced in actual operation.

In order to solve the above technical problem, an embodiment of the present application provides an accuracy optimization method based on bill data inspection. By utilizing the bill data inspection-based accuracy optimization method provided by the embodiment of the application, a plurality of spot check rules for triggering bill data inspection operation are created in advance, the spot check rules can be set according to preset keywords, for example, according to different credit card types, cities, major and minor cards, single or double currencies, money buying, staging plans and the like, and the keywords are determined according to bills needing to be monitored in a key manner. When a certain bill in the database triggers the keyword, the bill is determined to meet the requirement of the preset sampling inspection rule. And the benefits generated by each sampling inspection rule in the bill accuracy checking work are calculated in a timing or real-time manner, so that the validity of the sampling inspection rules is verified and corresponding processing is carried out according to the verification result, specifically, the sampling inspection rules are deleted or modified, and the invalid sampling inspection rules are prevented from occupying a memory.

Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an accuracy optimization method based on bill data verification according to an embodiment of the present disclosure. The accuracy optimization method based on bill data inspection is applied to terminal equipment.

In an embodiment, the method may comprise the steps of:

in step 101, a plurality of spot check rules for triggering bill data checking operations are created in advance in a database.

In this embodiment, the bill may include bill information output to the user. Such as credit card billing, etc. The spot check rule can be set according to preset keywords, for example, according to different credit card types, cities, major and minor cards, single or double currencies, money purchases, whether to schedule by stages, and the like, wherein the keywords are determined according to bills needing to be monitored in a key mode. When a certain bill in the database triggers the keyword, the bill is determined to meet the requirement of the preset sampling inspection rule. In one example, bills meeting preset spot check rules can be extracted from a bill storage database periodically according to the preset spot check rules for check.

When the terminal equipment or the server which operates the bill data inspection-based accuracy optimization method provided by the scheme monitors that the target bill which meets the preset spot check rule exists in the bill storage database, the target bill is automatically acquired for data verification.

And step 102, respectively recording the total times of triggering bill data checking operation and abnormal checking results of each sampling check rule in a preset time period.

In order to calculate the benefit of each sampling rule in the work of checking the bill accuracy and further verify the validity of each sampling rule, in this embodiment, the total number of times that each sampling rule triggers the bill data checking operation within a preset time period (for example, 1 month) and the checking result is abnormal is recorded, and the validity of the sampling rule is determined and corresponding processing operation is executed according to the value corresponding to the total number of times.

In some embodiments, before separately recording the total number of times each of the spot check rules triggers the bill data checking operation within the preset time period and the checking result is abnormal, the method further comprises:

performing keyword extraction operation on each bill to be subjected to data inspection, and selecting a target bill containing preset keywords; and determining the selective examination rule corresponding to the target bill according to the selective examination rule to which the preset keyword belongs.

Specifically, each bill to be subjected to data inspection is input into a pre-trained keyword extraction model to perform keyword extraction operation.

It should be noted that the keyword extraction model may be obtained based on neural network training, for example, convolutional neural network training, and the specific training process includes:

performing feature extraction on the text data in the training sample through a keyword extraction model to be trained to obtain a text feature vector corresponding to the text data;

identifying keywords of the text data in the training sample based on the text characteristic vector through a keyword extraction model to be trained to obtain an identification result of the text data;

and adjusting parameters of the keyword extraction model to be trained based on the recognition result and the label of the text data to obtain a pre-trained keyword extraction model.

Step 103, judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value.

In this embodiment, in order to determine the validity of the sampling rule according to the total number of times corresponding to the sampling rule, it is specifically determined whether the total number of times corresponding to each sampling rule is less than or equal to a first preset threshold, for example, 3 times, specifically, three times a month, and the frequency belongs to a lower range, so that the function of the sampling rule cannot be effectively exerted, and possibly, the cited keyword lacks pertinence, and needs to be adjusted so that the sampling rule can better assist in determining the bill accuracy.

And step 104, marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold as abnormal rules, and adjusting the abnormal rules to optimize the accuracy of the plurality of sampling inspection rules on triggering bill data inspection operation.

In this embodiment, the sampling rule whose total number of times is less than or equal to the first preset threshold is marked as an abnormal rule, and the abnormal rule is adjusted, for example, a keyword in the abnormal rule is modified or the keyword is added, so as to optimize the accuracy of the plurality of sampling rules on triggering the bill data inspection operation.

In some embodiments, to screen out invalid spot check rules, the method further comprises:

judging whether the total times corresponding to each sampling inspection rule is smaller than or equal to a second preset threshold value, wherein the second preset threshold value is smaller than the first preset threshold value, for example, the second preset threshold value is zero, and when the sampling inspection rules with the total times smaller than or equal to zero exist, determining that the sampling inspection rules cannot detect and mention the accuracy of the bill;

and marking the sampling inspection rule with the total times less than or equal to a second preset threshold as an invalid rule, and deleting the invalid rule.

In some embodiments, after marking as invalid rules the sampling rules whose total number of times is less than or equal to the second preset threshold, the method further comprises:

and generating notification information containing the invalid rule and the invalid reason thereof to assist the staff to formulate a more reasonable sampling inspection rule.

In some embodiments, the method further comprises:

judging whether the total times corresponding to each sampling inspection rule is greater than a third preset threshold value, wherein the third preset threshold value is greater than the first preset threshold value;

In this embodiment, to frequently triggering bill inspection operation and the corresponding inspection result is unusual for a great number of times, can expand this spot check rule and obtain more similar rules, can play the effect that promotes bill accuracy inspection efficiency equally to increase the effective number of times that triggers of bill data inspection operation. It should be noted that sentence enhancement based on the high-frequency rule can be obtained through a semantic enhancement model, which belongs to the technology known by those skilled in the art and is not described herein.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described in detail herein.

In particular implementation, the present application is not limited by the execution sequence of the described steps, and some steps may be performed in other sequences or simultaneously without conflict.

As can be seen from the above, the accuracy optimization method based on bill data inspection provided by the embodiment of the present application creates a plurality of spot check rules in advance in a database for triggering bill data inspection operations; respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each sampling inspection rule in a preset time period; judging whether the total times corresponding to each sampling inspection rule is less than or equal to a first preset threshold value or not; and marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold value as abnormal rules, and adjusting the abnormal rules to optimize the accuracy of the plurality of sampling inspection rules on the triggering bill data inspection operation. By means of the bill data inspection-based accuracy optimization method, a plurality of spot check rules for triggering bill data inspection operation are created in advance, the spot check rules can be set according to preset keywords, for example, according to different credit card types, cities, main cards, auxiliary cards, single coins, double coins, money buying, staging plans and the like, and the keywords are determined according to bills needing to be monitored in a key mode. When a certain bill in the database triggers the keyword, the bill is determined to meet the requirement of the preset sampling inspection rule. And the benefit generated by each sampling rule in the bill accuracy checking work is calculated in real time or at regular time, so that the validity of the sampling rule is verified and corresponding processing is carried out according to the verification result, specifically, the sampling rule is deleted or modified, and the invalid sampling rule is prevented from occupying the memory.

The embodiment of the application also provides an accuracy optimization device based on bill data inspection, and the accuracy optimization device based on bill data inspection can be integrated in the terminal equipment. The terminal equipment can be equipment such as a smart phone and a tablet personal computer.

Referring to fig. 2, fig. 2 is a schematic structural diagram of an accuracy optimization device based on bill data verification according to an embodiment of the present disclosure. The accuracy optimizing device 30 based on the bill data verification may include:

a creating module 31, configured to create in advance a plurality of spot check rules for triggering a bill data checking operation in a database;

the recording module 32 is configured to record the total times that each of the spot check rules triggers the bill data inspection operation within a preset time period and the inspection result is abnormal;

the judging module 33 is configured to judge whether the total number of times corresponding to each of the sampling inspection rules is less than or equal to a first preset threshold;

and the adjusting module 34 is configured to mark the sampling rule whose total number of times is less than or equal to the first preset threshold as an abnormal rule, and adjust the abnormal rule to optimize the accuracy of the plurality of sampling rules for triggering the bill data checking operation.

In some embodiments, the device further comprises an extraction module, configured to perform a keyword extraction operation on each bill to be subjected to data inspection, and select a target bill containing a preset keyword; and determining the selective examination rule corresponding to the target bill according to the selective examination rule to which the preset keyword belongs.

In some embodiments, the extraction module is configured to input each bill to be subjected to data inspection into a pre-trained keyword extraction model to perform a keyword extraction operation.

In some embodiments, the apparatus further includes a training module, configured to obtain a training sample of a keyword extraction model to be trained, where the training sample includes text data provided with a label; performing feature extraction on the text data in the training sample through the keyword extraction model to be trained to obtain a text feature vector corresponding to the text data; identifying keywords of the text data in the training sample based on the text feature vector through the keyword extraction model to be trained to obtain an identification result of the text data; and adjusting parameters of the keyword extraction model to be trained based on the recognition result and the label of the text data to obtain the pre-trained keyword extraction model.

In some embodiments, the apparatus further includes a deletion module, configured to determine whether a total number of times corresponding to each of the sampling rules is less than or equal to a second preset threshold, where the second preset threshold is less than a first preset threshold; and marking the sampling inspection rule with the total times less than or equal to the second preset threshold value as an invalid rule, and deleting the invalid rule.

In some embodiments, the apparatus further comprises a notification module configured to generate notification information including the invalidation rule and its invalidation reason.

In some embodiments, the apparatus further includes a supplement module, configured to determine whether a total number of times corresponding to each of the sampling rules is greater than a third preset threshold, where the third preset threshold is greater than the first preset threshold; marking the sampling inspection rule of which the total times is greater than the third preset threshold value as a high-frequency rule; and performing statement enhancement operation based on the high-frequency rule to obtain a plurality of similar rules imitating the expansion of the high-frequency rule, and supplementing the plurality of similar rules into the database.

In specific implementation, the modules may be implemented as independent entities, or may be combined arbitrarily and implemented as one or several entities.

As can be seen from the above, the accuracy optimization device 30 based on bill data verification provided in the embodiment of the present application creates a plurality of spot check rules in advance in the database through the creation module 31 for triggering the bill data verification operation; the recording module 32 records the total times of triggering bill data inspection operation and abnormal inspection result of each sampling inspection rule in a preset time period; the judging module 33 judges whether the total number of times corresponding to each of the sampling inspection rules is less than or equal to a first preset threshold; the adjustment module 34 marks the spot check rules with the total number of times less than or equal to the first preset threshold as abnormal rules, and adjusts the abnormal rules to optimize the accuracy of the spot check rules for triggering the bill data checking operation.

Referring to fig. 3, fig. 3 is another structural diagram of an accuracy optimization device based on bill data verification according to an embodiment of the present application, in which the accuracy optimization device 30 based on bill data verification includes a memory 120, one or more processors 180, and one or more applications, where the one or more applications are stored in the memory 120 and configured to be executed by the processor 180; the processor 180 may include a creation module 31, a recording module 32, a determination module 33, and an adjustment module 34. For example, the structures and connection relationships of the above components may be as follows:

the memory 120 may be used to store applications and data. The memory 120 stores applications containing executable code. The application programs may constitute various functional modules. The processor 180 executes various functional applications and data processing by running the application programs stored in the memory 120. Further, the memory 120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 120 may also include a memory controller to provide the processor 180 with access to the memory 120.

The processor 180 is a control center of the device, connects various parts of the entire terminal using various interfaces and lines, performs various functions of the device and processes data by running or executing an application program stored in the memory 120 and calling data stored in the memory 120, thereby monitoring the entire device. Optionally, processor 180 may include one or more processing cores; preferably, the processor 180 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, and the like.

Specifically, in this embodiment, the processor 180 loads the executable code corresponding to the process of one or more application programs into the memory 120 according to the following instructions, and the processor 180 runs the application programs stored in the memory 120, thereby implementing various functions:

the recording module 32 is configured to record the total number of times that each of the spot check rules triggers a bill data checking operation within a preset time period and a checking result is abnormal;

and the adjusting module 34 is configured to mark the sampling inspection rules with the total times smaller than or equal to the first preset threshold as abnormal rules, and adjust the abnormal rules to optimize the accuracy of the plurality of sampling inspection rules on triggering the bill data inspection operation.

In some embodiments, the apparatus further includes a deletion module, configured to determine whether a total number of times corresponding to each of the sampling inspection rules is less than or equal to a second preset threshold, where the second preset threshold is less than a first preset threshold; and marking the sampling inspection rule with the total times less than or equal to the second preset threshold as an invalid rule, and deleting the invalid rule.

In some embodiments, the apparatus further includes a supplement module, configured to determine whether a total number of times corresponding to each of the sampling inspection rules is greater than a third preset threshold, where the third preset threshold is greater than the first preset threshold; marking the sampling inspection rule of which the total times is greater than the third preset threshold value as a high-frequency rule; and performing statement enhancement operation based on the high-frequency rule to obtain a plurality of similar rules imitating the expansion of the high-frequency rule, and supplementing the plurality of similar rules into the database.

The embodiment of the application also provides the terminal equipment. The terminal equipment can be equipment such as a smart phone, a computer and a tablet computer.

Referring to fig. 4, fig. 4 is a schematic structural diagram of a terminal device provided in the embodiment of the present application, where the terminal device may be used to implement the accuracy optimization method based on the bill data verification provided in the foregoing embodiment. The terminal device 1200 may be a television, a smart phone, or a tablet computer.

As shown in fig. 4, the terminal device 1200 may include an RF (Radio Frequency) circuit 110, a memory 120 including one or more computer-readable storage media (only one shown in the figure), an input unit 130, a display unit 140, a sensor 150, an audio circuit 160, a transmission module 170, a processor 180 including one or more processing cores (only one shown in the figure), and a power supply 190. Those skilled in the art will appreciate that the terminal device 1200 configuration shown in fig. 4 does not constitute a limitation of terminal device 1200, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components. Wherein:

the RF circuit 110 is used for receiving and transmitting electromagnetic waves, and implementing interconversion between the electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. The RF circuitry 110 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The RF circuitry 110 may communicate with various networks such as the internet, an intranet, a wireless network, or with other devices over a wireless network.

The memory 120 may be configured to store a software program and a module, such as a program instruction/module corresponding to the accuracy optimization method based on bill data inspection in the above embodiment, and the processor 180 executes various functional applications and data processing by operating the software program and the module stored in the memory 120, and may automatically select a vibration reminding mode according to a current scene where the terminal device is located to perform accuracy optimization based on bill data inspection, so as to ensure that scenes such as a conference and the like are not disturbed, ensure that a user can perceive an incoming call, and improve intelligence of the terminal device. Memory 120 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 120 may further include memory located remotely from the processor 180, which may be connected to the terminal device 1200 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input unit 130 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, input unit 130 may include a touch-sensitive surface 131 as well as other input devices 132. Touch-sensitive surface 131, also referred to as a touch-sensitive display screen or touch pad, may collect touch operations by a user on or near it (e.g., operations by a user on touch-sensitive surface 131 or near touch-sensitive surface 131 using a finger, a stylus, or any other suitable object or attachment), and actuate the corresponding connection device according to a predetermined program. Alternatively, the touch-sensitive surface 131 may comprise two parts, a touch detection device and a touch controller. The touch detection device detects a touch direction of a user, detects a signal brought by touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 180, and receives and executes commands sent by the processor 180. Additionally, the touch-sensitive surface 131 may be implemented using various types of resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch-sensitive surface 131, the input unit 130 may also include other input devices 132. In particular, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 140 may be used to display information input by a user or information provided to the user and various graphic user interfaces of the terminal apparatus 1200, which may be configured by graphics, text, icons, video, and any combination thereof. The Display unit 140 may include a Display panel 141, and optionally, the Display panel 141 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Further, the touch-sensitive surface 131 may cover the display panel 141, and when a touch operation is detected on or near the touch-sensitive surface 131, the touch operation is transmitted to the processor 180 to determine the type of the touch event, and then the processor 180 provides a corresponding visual output on the display panel 141 according to the type of the touch event. Although in FIG. 4, touch-sensitive surface 131 and display panel 141 are shown as two separate components to implement input and output functions, in some embodiments, touch-sensitive surface 131 may be integrated with display panel 141 to implement input and output functions.

The terminal device 1200 may also include at least one sensor 150, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 141 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 141 and/or the backlight when the terminal device 1200 is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of identifying the gesture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration identification related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which may be further configured in the terminal device 1200, detailed descriptions thereof are omitted.

The audio circuitry 160, speaker 161, microphone 162 may provide an audio interface between the user and the terminal device 1200. The audio circuit 160 may transmit the electrical signal converted from the received audio data to the speaker 161, and convert the electrical signal into a sound signal for output by the speaker 161; on the other hand, the microphone 162 converts the collected sound signal into an electric signal, converts the electric signal into audio data after being received by the audio circuit 160, and then outputs the audio data to the processor 180 for processing, and then to the RF circuit 110 to be transmitted to, for example, another terminal, or outputs the audio data to the memory 120 for further processing. The audio circuitry 160 may also include an earbud jack to provide communication of peripheral headphones with the terminal device 1200.

The terminal device 1200, which may assist the user in sending and receiving e-mails, browsing web pages, accessing streaming media, etc., through the transmission module 170 (e.g., wi-Fi module), provides the user with wireless broadband internet access. Although fig. 4 shows the transmission module 170, it is understood that it does not belong to the essential constitution of the terminal device 1200, and may be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 180 is a control center of the terminal device 1200, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the terminal device 1200 and processes data by running or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120, thereby performing overall monitoring of the mobile phone. Optionally, processor 180 may include one or more processing cores; in some embodiments, the processor 180 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 180.

Terminal device 1200 also includes a power supply 190 for powering the various components, which in some embodiments may be logically coupled to processor 180 via a power management system to manage power discharge and power consumption via the power management system. The power supply 190 may also include any component including one or more of a dc or ac power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

Although not shown, the terminal device 1200 may further include a camera (e.g., a front camera, a rear camera), a bluetooth module, and the like, which are not described in detail herein. Specifically, in this embodiment, the display unit 140 of the terminal device 1200 is a touch screen display, and the terminal device 1200 further includes a memory 120, and one or more programs, wherein the one or more programs are stored in the memory 120, and the one or more programs are configured to be executed by the one or more processors 180, and include instructions for:

creating instructions for creating in advance in the database a plurality of spot check rules for triggering bill data checking operations;

the recording instruction is used for respectively recording the total times of triggering bill data inspection operation and abnormal inspection results of each sampling inspection rule in a preset time period;

a judgment instruction, configured to judge whether a total number of times corresponding to each of the sampling inspection rules is less than or equal to a first preset threshold;

and the adjusting instruction is used for marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold value as abnormal rules and adjusting the abnormal rules so as to optimize the accuracy of the plurality of sampling inspection rules on triggering bill data inspection operation.

In some embodiments, the program further comprises an extracting instruction for performing a keyword extraction operation on each bill to be subjected to data inspection, and selecting a target bill containing a preset keyword; and determining the selective examination rule corresponding to the target bill according to the selective examination rule to which the preset keyword belongs.

In some embodiments, the extracting instructions are configured to input each bill to be subjected to data inspection into a pre-trained keyword extraction model to perform a keyword extraction operation.

In some embodiments, the program further includes a training instruction for obtaining a training sample of the keyword extraction model to be trained, where the training sample includes text data provided with a label; performing feature extraction on the text data in the training sample through the keyword extraction model to be trained to obtain a text feature vector corresponding to the text data; identifying keywords of the text data in the training sample based on the text feature vector through the keyword extraction model to be trained to obtain an identification result of the text data; and adjusting parameters of the keyword extraction model to be trained based on the recognition result and the label of the text data to obtain the pre-trained keyword extraction model.

In some embodiments, the program further includes a deletion instruction for determining whether the total number of times corresponding to each of the sampling inspection rules is less than or equal to a second preset threshold, where the second preset threshold is less than the first preset threshold; and marking the sampling inspection rule with the total times less than or equal to the second preset threshold as an invalid rule, and deleting the invalid rule.

In some embodiments, the program further comprises notification instructions for generating notification information containing the invalidation rules and their invalidation reasons.

In some embodiments, the program further includes a supplementary instruction for determining whether a total number of times corresponding to each of the sampling rules is greater than a third preset threshold, where the third preset threshold is greater than the first preset threshold; marking the sampling inspection rule of which the total times is greater than the third preset threshold value as a high-frequency rule; and performing statement enhancement operation based on the high-frequency rule to obtain a plurality of similar rules imitating the expansion of the high-frequency rule, and supplementing the plurality of similar rules into the database.

The embodiment of the application also provides the terminal equipment. The terminal equipment can be equipment such as a smart phone and a computer.

As can be seen from the above, an embodiment of the present application provides a terminal device 1200, where the terminal device 1200 executes the following steps:

the embodiment of the present application further provides a storage medium, where a computer program is stored, and when the computer program runs on a computer, the computer executes the method for optimizing accuracy based on the bill data inspection according to any one of the above embodiments.

It should be noted that, for the accuracy optimization method based on the billing data verification described in this application, it can be understood by those skilled in the art that all or part of the process of implementing the accuracy optimization method based on the billing data verification described in the embodiments of this application may be implemented by controlling the relevant hardware through a computer program, where the computer program may be stored in a computer readable storage medium, such as a memory of the terminal device, and executed by at least one processor in the terminal device, and during the execution process, the process of the embodiment of the accuracy optimization method based on the billing data verification described in this application may be included. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.

For the accuracy optimization device based on bill data verification in the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist alone physically, or two or more modules may be integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.

The method, apparatus, medium, and device for optimizing accuracy based on billing data inspection provided in the embodiments of the present application are described in detail above. The principle and the implementation of the present application are explained herein by applying specific examples, and the above description of the embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An accuracy optimization method based on bill data inspection is characterized by comprising the following steps:

2. The accuracy optimization method of claim 1, wherein before said separately recording a total number of times each of said spot check rules triggers a bill data checking operation within a preset time period and a checking result is abnormal, said method further comprises:

performing keyword extraction operation on each bill to be subjected to data inspection, and selecting a target bill containing preset keywords;

3. The accuracy optimization method of claim 2, wherein the performing the keyword extraction operation on each bill to be subjected to data inspection comprises:

4. The accuracy optimization method of claim 3, wherein before the step of inputting each bill for data inspection into a pre-trained keyword extraction model for keyword extraction, the method further comprises:

5. The accuracy optimization method of claim 1, further comprising:

judging whether the total times corresponding to each sampling inspection rule is smaller than or equal to a second preset threshold value, wherein the second preset threshold value is smaller than a first preset threshold value;

and marking the sampling inspection rule with the total times less than or equal to the second preset threshold as an invalid rule, and deleting the invalid rule.

6. The accuracy optimization method of claim 5, wherein after marking the snapshot rules having a total number of times less than or equal to the second preset threshold as invalid rules, the method further comprises:

7. The accuracy optimization method of claim 1, further comprising:

8. An accuracy optimization apparatus based on bill data verification, characterized in that the accuracy optimization apparatus based on bill data verification comprises:

and the adjusting module is used for marking the sampling inspection rules of which the total times are less than or equal to the first preset threshold value as abnormal rules and adjusting the abnormal rules so as to optimize the accuracy of the plurality of sampling inspection rules on the triggering of the bill data inspection operation.

9. A computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the method for bill data inspection based accuracy optimization of claims 1 to 7.

10. A terminal device comprising a processor and a memory, the memory storing a plurality of instructions, the processor loading the instructions to perform the method of accuracy optimization based on billing data verification of any of claims 1 to 7.