Test Resource Optimization Method, Device, Medium and Equipment Based on Bill Inspection

Abstract

An embodiment of the present application provides a method, device, medium and equipment for optimizing test resources based on bill inspection. The method includes: performing accuracy test operations on the same sampling inspection rule to be tested in a first region and a second region respectively to obtain a first test result and a second test result; comparing and analyzing the first test result and the second test result, and judging whether to adjust the sampling inspection rule to be tested according to the comparison and analysis result, so as to optimize the size of test resources corresponding to multiple sampling inspection rules. By pre-creating multiple sampling inspection rules for triggering bill data inspection operations, and performing accuracy test operations on each sampling inspection rule in different regions respectively, and judging whether to adjust the sampling inspection rule according to the comparison and analysis result of the first test result and the second test result, the sampling inspection rules for triggering bill data inspection operations are reasonably allocated, so that the sampling inspection rules can play their roles to the greatest extent and avoid waste of test resources.

Description

Technical Field

[0001] This application relates to the field of electronic communication technologies, and in particular, to a test resource optimization technology based on bill verification, and particularly to a test resource optimization method, device, medium, and equipment based on bill verification. Background Art

[0002] Credit card bills record various transactions, expenses, the amount due on the bill, the minimum repayment amount, the bill date, the repayment date, and installment plans, etc. of the user during the current billing period. From the user's perspective, a correct credit card bill is crucial for maintaining a good credit score of the user. From the bank's perspective, it is equally important to ensure that the credit card bills sent to users are correct to reduce user complaints and disputes. In order to improve the accuracy of bills, it is usually necessary to regularly sample and inspect a large number of bills generated in a certain area, estimate the accuracy rate of the bills based on the verification work of the sampled bills, and when the accuracy rate is significantly too low, the staff can check whether there are abnormalities in each key link during the bill generation process in a timely manner, so as to facilitate the staff to investigate problems in a timely manner. The current sampling methods mostly randomly sample from a large number of bills, which not only has low work efficiency but also weak pertinence. Since the number of user populations in different regions is different, when the number of user populations in a certain area is large, the different needs of different users result in more data dimensions included in the bills generated in this area, such as credit card types, cities, primary and secondary cards, single and dual currencies, foreign exchange purchase, installment plans, etc. When the data dimensions increase, the probability of bill data anomalies will increase. If there is no targeted matching of appropriate sampling rules for the self-triggering of bill data verification operations according to the characteristics of the region, the same sampling rule may have low or even no effect in some regions, resulting in affecting the expected effect of the bill accuracy estimation work in actual operations. Summary of the Invention

[0003] The embodiments of this application provide a test resource optimization method, device, medium, and equipment based on bill verification. By using the test resource optimization method based on bill verification provided by the embodiments of this application, by pre-creating multiple sampling rules for triggering bill data verification operations, and performing accuracy test operations on each sampling rule in different regions respectively, obtaining the first test result and the second test result, and judging whether to adjust the sampling rules according to the comparison and analysis results of the first test result and the second test result, rationally allocate the sampling rules for triggering bill data verification operations, so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources.

[0004] On the one hand, the embodiments of this application provide a test resource optimization method based on bill verification. The test resource optimization method based on bill verification includes:

[0005] Create multiple sampling inspection rules for triggering the bill data inspection operation in advance in the database;

[0006] Take the same sampling inspection rule to be tested and perform accuracy test operations in the first region and the second region respectively to obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region;

[0007] Compare and analyze the first test result and the second test result, and judge whether to adjust the sampling inspection rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling inspection rules.

[0008] In the test resource optimization method based on bill inspection described in the embodiments of the present application, the step of taking the same sampling inspection rule to be tested and performing accuracy test operations in the first region and the second region respectively to obtain a first test result and a second test result includes:

[0009] Take the sampling inspection rule to be tested and perform an accuracy test operation in the first region, record the total number of times that the sampling inspection rule to be tested triggers the bill data inspection operation and the inspection result is abnormal within a preset time period, and use the total number of times as the first test result;

[0010] Take the sampling inspection rule to be tested and perform an accuracy test operation in the second region, record the total number of times that the sampling inspection rule to be tested triggers the bill data inspection operation and the inspection result is abnormal within a preset time period, and use the total number of times as the second test result.

[0011] In the test resource optimization method based on bill inspection described in the embodiments of the present application, before respectively recording the total number of times that each sampling inspection rule triggers the bill data inspection operation and the inspection result is abnormal within a preset time period, the method further includes:

[0012] Perform keyword extraction operations on each bill to be inspected for data, and select target bills containing preset keywords;

[0013] Determine the sampling inspection rule corresponding to the target bill by the sampling inspection rule to which the preset keyword belongs.

[0014] In the test resource optimization method based on bill inspection described in the embodiments of the present application, the step of performing keyword extraction operations on each bill to be inspected for data includes:

[0015] Input each bill to be inspected for data into a pre-trained keyword extraction model for keyword extraction operations.

[0016] In the test resource optimization method based on bill inspection according to the embodiments of the present application, before inputting each piece of the to-be-data-inspected bill into the pre-trained keyword extraction model for keyword extraction operation, the method further includes:

[0017] Obtain training samples of the to-be-trained keyword extraction model, where the training samples include text data with labels;

[0018] Extract features of the text data in the training samples through the to-be-trained keyword extraction model to obtain text feature vectors corresponding to the text data;

[0019] Based on the text feature vectors, identify keywords of the text data in the training samples through the to-be-trained keyword extraction model to obtain the recognition results of the text data;

[0020] Adjust the parameters of the to-be-trained keyword extraction model based on the recognition results and the labels of the text data to obtain the pre-trained keyword extraction model.

[0021] In the test resource optimization method based on bill inspection according to the embodiments of the present application, the comparison and analysis of the first test result and the second test result, and judging whether to adjust the to-be-tested sampling rule according to the comparison and analysis result include:

[0022] Calculate the difference value between the first test result and the second test result;

[0023] Judge whether to adjust the to-be-tested sampling rule according to the difference value.

[0024] In the test resource optimization method based on bill inspection according to the embodiments of the present application, the method further includes:

[0025] If the first test result is greater than the first preset threshold and the second test result is less than the second preset threshold, cancel the bill data inspection operation triggered by the to-be-tested sampling rule in the second region;

[0026] If the second test result is greater than the first preset threshold and the first test result is less than the second preset threshold, cancel the bill data inspection operation triggered by the to-be-tested sampling rule in the first region;

[0027] The first preset threshold is greater than the second preset threshold.

[0028] Correspondingly, another aspect of the embodiments of the present application further provides a test resource optimization device based on bill inspection. The test resource optimization device based on bill inspection includes:

[0029] A creation module, configured to pre-create multiple sampling rules in a database for triggering bill data verification operations;

[0030] A testing module, configured to perform accuracy testing operations on the same sampling rule to be tested in a first region and a second region respectively, to obtain a first test result and a second test result, wherein the number of user populations in the first region is greater than that in the second region;

[0031] An analysis module, configured to perform comparison and analysis on the first test result and the second test result, and determine whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules.

[0032] Correspondingly, another aspect of the embodiments of the present application further provides a storage medium, which stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the test resource optimization method based on bill verification as described above.

[0033] Correspondingly, another aspect of the embodiments of the present application further provides a terminal device, including a processor and a memory, where the memory stores multiple instructions, and the processor loads the instructions to execute the test resource optimization method based on bill verification as described above.

[0034] The embodiments of the present application provide a test resource optimization method, device, medium and device based on bill verification. This method pre-creates multiple sampling rules for triggering bill data verification operations in a database; performs accuracy testing operations on the same sampling rule to be tested in a first region and a second region respectively, to obtain a first test result and a second test result, wherein the number of user populations in the first region is greater than that in the second region; performs comparison and analysis on the first test result and the second test result, and determines whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules. By using the test resource optimization method based on bill verification provided by the embodiments of the present application, multiple sampling rules for triggering bill data verification operations are pre-created, and each sampling rule is respectively subjected to accuracy testing operations in different regions to obtain a first test result and a second test result. Whether to adjust the sampling rule is determined according to the comparison and analysis result of the first test result and the second test result, and the sampling rules for triggering bill data verification operations are reasonably allocated, so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources. Description of the Drawings

[0035] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0036] Figure 1 It is a schematic flowchart of a test resource optimization method based on bill verification provided by an embodiment of the present application.

[0037] Figure 2 It is a schematic structural diagram of a test resource optimization device based on bill verification provided by an embodiment of the present application.

[0038] Figure 3 It is another schematic structural diagram of a test resource optimization device based on bill verification provided by an embodiment of the present application.

[0039] Figure 4 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present application.

[0041] The embodiments of the present application provide a test resource optimization method based on bill verification. The test resource optimization method based on bill verification can be applied to a terminal device. The terminal device can be a device such as a smart phone or a computer.

[0042] It should be noted that the following content is a simple introduction to the background of this solution:

[0043] This solution mainly focuses on the technical problem of "how to reasonably allocate the sampling rules for triggering the bill data verification operation so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources". The bill specifically refers to a credit card bill. It can be understood that the credit card bill records various transactions, expenses, the amount due on the bill, the minimum repayment amount, the bill date, the repayment date, and the installment plan, etc. of the user during the current billing period. From the user's perspective, a correct credit card bill is crucial for maintaining the user's good credit score. From the bank's perspective, it is also crucial to ensure that the credit card bill sent to the user is correct to reduce user complaints and disputes.

[0044] In order to improve the accuracy of bills, it is usually necessary to regularly sample and inspect a large number of bills generated in a certain area, estimate the accuracy rate of the bills according to the verification work on the sampled bills, and when the accuracy rate is significantly too low, the staff can timely check whether there are abnormalities in each key link in the bill generation process, so as to facilitate the staff to quickly identify problems. Most of the current sampling methods are randomly sampling from a large number of bills, which not only has low work efficiency but also weak pertinence. Since the number of user populations in different regions is different, when the number of user populations in a certain region is large, different users have different needs, resulting in more data dimensions in the bills generated in this region, such as credit card types, cities, primary and secondary cards, single and double currencies, foreign exchange purchase, installment plans, etc. When the number of data dimensions increases, the probability of bill data anomalies will increase. If there is no targeted matching of appropriate sampling rules for the self-triggering of bill data inspection operations according to the characteristics of the region, the same sampling rule may have low or even ineffective benefits in some regions, resulting in affecting the expected effect of the bill accuracy estimation work in actual operations.

[0045] To solve the above technical problems, the embodiment of the present application provides a test resource optimization method based on bill inspection. Using the test resource optimization method based on bill inspection provided by the embodiment of the present application, by pre-creating multiple sampling rules for triggering bill data inspection operations, the sampling rules can be set according to preset keywords, such as different credit card types, cities, primary and secondary cards, single and double currencies, foreign exchange purchase, installment plans, etc. When a certain bill in the database triggers a keyword, it is considered to meet the requirements of the preset sampling rule. And perform accuracy test operations on each sampling rule in different regions respectively, obtain the first test result and the second test result, and judge whether to adjust the sampling rule according to the comparison and analysis result of the first test result and the second test result, and rationally allocate the sampling rules for triggering bill data inspection operations, so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources.

[0046] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of the test resource optimization method based on bill inspection provided by the embodiment of the present application. The test resource optimization method based on bill inspection is applied to a terminal device.

[0047] In one embodiment, the method may include the following steps:

[0048] Step 101, pre-create multiple sampling rules for triggering bill data inspection operations in the database.

[0049] In this embodiment, the bill may include bill information output to the user. For example, a credit card bill, etc. The sampling inspection rules can be set according to preset keywords. For example, according to different credit card types, cities, primary and secondary cards, single and double currencies, foreign exchange purchase, installment plan, etc. The keywords are determined according to the bills that need to be monitored key points. When a certain bill in the database triggers the keyword, it is considered to meet the requirements of the preset sampling inspection rules. In one example, bills that meet the preset sampling inspection rules can be regularly extracted from the database storing the bills according to the preset sampling inspection rules for verification.

[0050] When the terminal device or server running the test resource optimization method based on bill inspection provided by this solution monitors that there is a target bill in the database storing the bills that meets the preset sampling inspection rules, it automatically obtains the target bill for data verification.

[0051] Step 102, perform accuracy test operations on the same sampling inspection rule to be tested in the first region and the second region respectively, and obtain a first test result and a second test result, where the number of user populations in the first region is greater than the number of user populations in the second region.

[0052] In order to calculate the benefits generated by each sampling inspection rule in the work of verifying the accuracy of bills, and further verify the applicability of each sampling inspection rule. In this embodiment, by performing an accuracy test operation on a sampling inspection rule to be tested in the first region, record the first total number of times that the sampling inspection rule to be tested triggers a bill data verification operation and the verification result is abnormal within a preset time period (for example, 1 month), and take the first total number as the first test result. Perform an accuracy test operation on the same sampling inspection rule to be tested in the second region, record the second total number of times that the sampling inspection rule to be tested triggers a bill data verification operation and the verification result is abnormal within the preset time period, and take the second total number as the second test result. Compare and analyze the first test result and the second test result to determine the applicability of the sampling inspection rule and perform corresponding processing operations.

[0053] It should be noted that since the test resource optimization method provided by this solution mainly focuses on the technical problem of "how to reasonably allocate the sampling inspection rules used to trigger bill data verification operations, so that the sampling inspection rules can play their roles to the greatest extent and avoid waste of test resources", it is necessary to judge the specific applicable application scenarios of the same sampling inspection rule, specifically manifested as being applicable to regions with a large or small number of user populations. In order to highlight the technical problem that this solution wants to solve, it is necessary to limit the first region and the second region with a large difference in the number of user populations.

[0054] In some embodiments, before respectively recording the total number of times that each sampling inspection rule triggers a bill data verification operation and the verification result is abnormal within the preset time period, the method further includes:

[0055] Perform keyword extraction operations on each bill to be tested for data, and select the target bills that contain the preset keywords; determine the sampling rules corresponding to the target bills based on the sampling rules to which the preset keywords belong.

[0056] Further, the specific operation of performing keyword extraction operations on each bill to be tested for data is as follows:

[0057] Input each bill to be tested for data into the pre-trained keyword extraction model for keyword extraction operations.

[0058] It should be noted that the keyword extraction model can be trained based on a neural network, such as a convolutional neural network. The specific training process includes:

[0059] Obtain the training samples of the keyword extraction model to be trained, and the training samples include text data with labels;

[0060] Extract features from the text data in the training samples through the keyword extraction model to be trained, and obtain the text feature vectors corresponding to the text data;

[0061] Through the keyword extraction model to be trained, identify the keywords of the text data in the training samples based on the text feature vectors, and obtain the recognition results of the text data;

[0062] Based on the recognition results and the labels of the text data, adjust the parameters of the keyword extraction model to be trained to obtain the pre-trained keyword extraction model.

[0063] Step 103: Compare and analyze the first test result and the second test result, and determine whether to adjust the to-be-tested sampling rule according to the comparison and analysis result, so as to optimize the test resource size corresponding to the multiple sampling rules.

[0064] In this embodiment, by calculating the difference value between the first test result and the second test result, it is determined whether to adjust the to-be-tested sampling rule according to the difference value. If the difference between the first test result and the second test result is large, it means that the to-be-tested sampling rule cannot be applied to different user populations in different regions at the same time, and the to-be-tested sampling rule needs to be adjusted to optimize the test resource size corresponding to the multiple sampling rules, reasonably allocate the sampling rules for triggering the bill data inspection operation, so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources.

[0065] If the first test result is greater than the first preset threshold (e.g., 30), and the second test result is less than the second preset threshold (e.g., 1), it indicates that the sampling inspection rule to be tested is applicable to the first region with a large user population, but not to the second region with a small user population. If the sampling inspection rule to be tested is not adjusted, it will cause a waste of test resources. Therefore, the billing data inspection operation triggered by the sampling inspection rule to be tested in the second region is cancelled to avoid waste of test resources and maximize the role of the sampling inspection rule to be tested. If the second test result is greater than the first preset threshold, and the first test result is less than the second preset threshold, it indicates that the sampling inspection rule to be tested is applicable to the second region with a small user population, but not to the first region with a large user population. If the sampling inspection rule to be tested is not adjusted, it will cause a waste of test resources. Therefore, the billing data inspection operation triggered by the sampling inspection rule to be tested in the first region is cancelled.

[0066] It should be explained that when the user population in a certain region is large, the data dimensions in the bills generated in this region will be more complex than those in the region with a small user population. There may be some that only appear frequently in the region with a large user population. For example, the data dimension "installment plan" usually appears in the region with more young people, that is, in the region with a large user population. For the region with a small user population, there are usually fewer young people and less demand for installment plans. At this time, if the sampling inspection rule carrying the keyword "installment plan" is applied in the region with a small user population, it will not be able to play its role and cause waste of test resources.

[0067] All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be elaborated here one by one.

[0068] In specific implementation, the present application is not limited by the execution order of the described steps. Without conflict, some steps can also be performed in other orders or simultaneously.

[0069] As can be seen from the above, the test resource optimization method based on bill inspection provided by the embodiments of the present application pre-creates multiple sampling rules in the database for triggering bill data inspection operations; performs accuracy test operations on the same sampling rule to be tested in the first region and the second region respectively to obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region; compares and analyzes the first test result and the second test result, and determines whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules. By using the test resource optimization method based on bill inspection provided by the embodiments of the present application, multiple sampling rules for triggering bill data inspection operations are pre-created, and each sampling rule is respectively subjected to accuracy test operations in different regions to obtain a first test result and a second test result. Whether to adjust the sampling rule is determined according to the comparison and analysis result of the first test result and the second test result, and the sampling rules for triggering bill data inspection operations are reasonably allocated, so that the sampling rules can play their roles to the greatest extent and avoid waste of test resources.

[0070] The embodiments of the present application further provide a test resource optimization device based on bill inspection, and the test resource optimization device based on bill inspection can be integrated in a terminal device. The terminal device can be a smart phone, a tablet computer or other devices.

[0071] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of the test resource optimization device based on bill inspection provided by the embodiments of the present application. The test resource optimization device 30 based on bill inspection may include:

[0072] A creation module 31, configured to pre-create multiple sampling rules in the database for triggering bill data inspection operations;

[0073] A test module 32, configured to perform accuracy test operations on the same sampling rule to be tested in the first region and the second region respectively to obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region;

[0074] An analysis module 33, configured to compare and analyze the first test result and the second test result, and determine whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules.

[0075] In some embodiments, the test module 32 is configured to perform an accuracy test operation on the sampling inspection rule to be tested in a first region, record a first total number of times that the sampling inspection rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and use the first total number as a first test result; perform an accuracy test operation on the sampling inspection rule to be tested in a second region, record a second total number of times that the sampling inspection rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and use the second total number as a second test result.

[0076] In some embodiments, the device further includes an extraction module, configured to perform keyword extraction operations on each bill to be inspected for data, and select a target bill containing a preset keyword; determine the sampling inspection rule corresponding to the target bill based on the sampling inspection rule to which the preset keyword belongs.

[0077] In some embodiments, the extraction module is configured to input each bill to be inspected for data into a pre-trained keyword extraction model for keyword extraction operations.

[0078] In some embodiments, the device further includes a training module, configured to obtain training samples for a keyword extraction model to be trained, where the training samples include text data with labels; perform feature extraction on the text data in the training samples through the keyword extraction model to be trained to obtain text feature vectors corresponding to the text data; identify keywords of the text data in the training samples based on the text feature vectors through the keyword extraction model to be trained to obtain an identification result of the text data; and adjust parameters of the keyword extraction model to be trained based on the identification result and the label of the text data to obtain the pre-trained keyword extraction model.

[0079] In some embodiments, the device further includes a judgment module, configured to calculate a difference value between the first test result and the second test result; and determine whether to adjust the sampling inspection rule to be tested based on the difference value.

[0080] In some embodiments, the device further includes a cancellation module, configured to cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the second region if the first test result is greater than a first preset threshold and the second test result is less than a second preset threshold; cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the first region if the second test result is greater than the first preset threshold and the first test result is less than the second preset threshold; and the first preset threshold is greater than the second preset threshold.

[0081] In specific implementation, each of the above modules can be implemented as an independent entity, or can be combined arbitrarily and implemented as the same or several entities.

[0082] As can be seen from the above, the test resource optimization device 30 based on bill verification provided by the embodiment of the present application creates multiple sampling inspection rules for triggering bill data verification operations in advance in the database through the creation module 31; the test module 32 takes the same sampling inspection rule to be tested and performs accuracy test operations in the first region and the second region respectively to obtain a first test result and a second test result, where the number of user groups in the first region is greater than the number of user groups in the second region; the analysis module 33 compares and analyzes the first test result and the second test result, and determines whether to adjust the sampling inspection rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling inspection rules.

[0083] Please refer to Figure 3 , Figure 3 FIG. is another structural schematic diagram of the test resource optimization device based on bill verification provided by the embodiment of the present application. The test resource optimization device 30 based on bill verification includes a memory 120, one or more processors 180, and one or more application programs, where the one or more application programs 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 test module 32, and an analysis module 33. For example, the structures and connection relationships of the above components can be as follows:

[0084] The memory 120 can be used to store application programs and data. The application programs stored in the memory 120 contain executable codes. The application programs can form various functional modules. The processor 180 executes various functional applications and data processing by running the application programs stored in the memory 120. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 120 may further include a memory controller to provide the processor 180 with access to the memory 120.

[0085] The processor 180 is the control center of the device, connects various parts of the entire terminal through various interfaces and lines, executes various functions of the device and processes data by running or executing the application programs stored in the memory 120, and calling the data stored in the memory 120, so as to perform overall monitoring of the device. Optionally, the processor 180 may include one or more processing cores; preferably, the processor 180 may integrate an application processor and a modulation and demodulation processor, where the application processor mainly processes the operating system, user interface, and application programs, etc.

[0086] Specifically, in this embodiment, the processor 180 will load the executable code corresponding to the processes of one or more application programs into the memory 120 according to the following instructions, and the processor 180 will run the application programs stored in the memory 120 to implement various functions:

[0087] A creation module 31 is configured to pre-create multiple sampling rules in the database for triggering the bill data verification operation;

[0088] A test module 32 is configured to perform accuracy test operations on the same sampling rule to be tested in a first region and a second region respectively, and obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region;

[0089] An analysis module 33 is configured to compare and analyze the first test result and the second test result, and determine whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules.

[0090] In some embodiments, the test module 32 is configured to perform an accuracy test operation on the sampling rule to be tested in the first region, record the first total number of times that the sampling rule to be tested triggers the bill data verification operation and the verification result is abnormal within a preset time period, and use the first total number as the first test result; perform an accuracy test operation on the sampling rule to be tested in the second region, record the second total number of times that the sampling rule to be tested triggers the bill data verification operation and the verification result is abnormal within a preset time period, and use the second total number as the second test result.

[0091] In some embodiments, the apparatus further includes an extraction module, configured to perform keyword extraction operations on each bill to be verified, and select a target bill containing a preset keyword; determine the sampling rule corresponding to the target bill as the sampling rule to which the preset keyword belongs.

[0092] In some embodiments, the extraction module is configured to input each bill to be verified into a pre-trained keyword extraction model for keyword extraction operations.

[0093] In some embodiments, the device further includes a training module, configured to obtain training samples for a keyword extraction model to be trained, where the training samples include text data with labels; extract features from the text data in the training samples through the keyword extraction model to be trained to obtain text feature vectors corresponding to the text data; identify keywords of the text data in the training samples based on the text feature vectors through the keyword extraction model to be trained to obtain an identification result of the text data; and adjust parameters of the keyword extraction model to be trained based on the identification result and the labels of the text data to obtain the pre-trained keyword extraction model.

[0094] In some embodiments, the device further includes a judgment module, configured to calculate a difference value between the first test result and the second test result; and determine whether to adjust the sampling inspection rule to be tested according to the difference value.

[0095] In some embodiments, the device further includes a cancellation module, configured to cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the second region if the first test result is greater than a first preset threshold and the second test result is less than a second preset threshold; cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the first region if the second test result is greater than the first preset threshold and the first test result is less than the second preset threshold; and the first preset threshold is greater than the second preset threshold.

[0096] An embodiment of the present application further provides a terminal device. The terminal device may be a device such as a smart phone, a computer, or a tablet computer.

[0097] Please refer to Figure 4 , Figure 4 which shows a schematic structural diagram of the terminal device provided by an embodiment of the present application. The terminal device can be used to implement the test resource optimization method based on bill inspection provided in the above embodiments. The terminal device 1200 may be a television, a smart phone, or a tablet computer.

[0098] As Figure 4 shown, the terminal device 1200 may include an RF (Radio Frequency) circuit 110, a memory 120 including one or more (only one is shown in the figure) computer-readable storage media, 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 (only one is shown in the figure) processing cores, and a power supply 190 and other components. Those skilled in the art can understand, Figure 4The structure of the terminal device 1200 shown does not constitute a limitation on the terminal device 1200, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0099] The RF circuit 110 is used to receive and transmit electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. The RF circuit 110 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity module (SIM) cards, memories, and so on. The RF circuit 110 can communicate with various networks such as the Internet, enterprise intranets, wireless networks, or communicate with other devices through a wireless network.

[0100] The memory 120 can be used to store software programs and modules, such as the program instructions / modules corresponding to the test resource optimization method based on bill verification in the above embodiments. The processor 180 executes various functional applications and data processing by running the software programs and modules stored in the memory 120, and can automatically select a vibration reminder mode to perform test resource optimization based on bill verification according to the current scenario where the terminal device is located. This can not only ensure that scenarios such as meetings are not disturbed, but also ensure that the user can perceive incoming calls, improving the intelligence of the terminal device. The memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 120 may further include a memory remotely set relative to the processor 180, and these remote memories can be connected to the terminal device 1200 through a network. Examples of the above networks include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and their combinations.

[0101] The input unit 130 can be used to receive input numerical or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. Specifically, the input unit 130 can include a touch-sensitive surface 131 and other input devices 132. The touch-sensitive surface 131, also known as a touch display screen or a touchpad, can collect touch operations of a user thereon or nearby (such as operations of the user using any suitable object or accessory such as a finger or a stylus on or near the touch-sensitive surface 131), and drive corresponding connection devices according to a preset program. Optionally, the touch-sensitive surface 131 can include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the touch orientation of the user, detects signals brought by the touch operation, and transmits the signals to the touch controller; the touch controller receives touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 180, and can also receive and execute commands sent by the processor 180. In addition, various types such as resistive, capacitive, infrared, and surface acoustic wave can be used to implement the touch-sensitive surface 131. In addition to the touch-sensitive surface 131, the input unit 130 can also include other input devices 132. Specifically, the other input devices 132 can include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power on / off keys, etc.), trackballs, mice, joysticks, etc.

[0102] The display unit 140 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the terminal device 1200. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. The display unit 140 can include a display panel 141. Optionally, the display panel 141 can be configured in forms such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode). Further, the touch-sensitive surface 131 can cover the display panel 141. After the touch-sensitive surface 131 detects a touch operation thereon or nearby, it transmits the operation to the processor 180 to determine the type of touch event. Subsequently, the processor 180 provides corresponding visual output on the display panel 141 according to the type of touch event. Although in Figure 4 the touch-sensitive surface 131 and the display panel 141 are implemented as two independent components to perform input and output functions, in some embodiments, the touch-sensitive surface 131 and the display panel 141 can be integrated to implement input and output functions.

[0103] The terminal device 1200 may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. Among them, the ambient light sensor can adjust the brightness of the display panel 141 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 141 and / or the backlight when the terminal device 1200 is moved to the ear. As a kind of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used in applications for identifying the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors that the terminal device 1200 may also be configured with, they will not be elaborated here.

[0104] The audio circuit 160, the speaker 161, and the microphone 162 can provide an audio interface between the user and the terminal device 1200. The audio circuit 160 can transmit the electrical signal converted from the received audio data to the speaker 161, and the speaker 161 converts it into a sound signal for output; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, which is received by the audio circuit 160 and then converted into audio data. After the audio data is output to the processor 180 for processing, it is sent through the RF circuit 110 to, for example, another terminal, or the audio data is output to the memory 120 for further processing. The audio circuit 160 may also include an earphone jack to provide communication between the peripheral earphone and the terminal device 1200.

[0105] The terminal device 1200 can help the user send and receive emails, browse the web, and access streaming media, etc. through the transmission module 170 (such as a Wi-Fi module), which provides the user with wireless broadband Internet access. Although Figure 4 the transmission module 170 is shown, it can be understood that it does not belong to the essential components of the terminal device 1200 and can be completely omitted within the scope of not changing the essence of the invention according to needs.

[0106] The processor 180 is the control center of the terminal device 1200, connecting various parts of the entire mobile phone through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 120, and by invoking data stored in the memory 120, it executes various functions of the terminal device 1200 and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor 180 may include one or more processing cores; in some embodiments, the processor 180 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 180 either.

[0107] The terminal device 1200 further includes a power supply 190 for powering each component. In some embodiments, the power supply may be logically connected to the processor 180 through a power management system, so as to implement functions such as management of discharging and power consumption management through the power management system. The power supply 190 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc.

[0108] Although not shown, the terminal device 1200 may also include a camera (such as a front camera, a rear camera), a Bluetooth module, etc., which will not be elaborated here. Specifically, in this embodiment, the display unit 140 of the terminal device 1200 is a touch screen display. The terminal device 1200 also includes a memory 120, and one or more programs, where one or more programs are stored in the memory 120 and are configured to be executed by one or more processors 180. The one or more programs include instructions for performing the following operations:

[0109] Creation instruction, used to pre-create multiple sampling inspection rules in the database for triggering the bill data inspection operation;

[0110] Testing instruction, used to perform accuracy testing operations on the same sampling inspection rule to be tested in the first region and the second region respectively, to obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region;

[0111] Analysis instruction, used to compare and analyze the first test result and the second test result, and judge whether to adjust the sampling inspection rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling inspection rules.

[0112] In some embodiments, the test instruction is used to perform an accuracy test operation on the sampling inspection rule to be tested in a first region, record the total number of times that the sampling inspection rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and use the total number of times as a first test result; perform an accuracy test operation on the sampling inspection rule to be tested in a second region, record the total number of times that the sampling inspection rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and use the total number of times as a second test result.

[0113] In some embodiments, the program further includes an extraction instruction, which is used to perform a keyword extraction operation on each bill to be inspected for data, and select a target bill containing a preset keyword; determine the sampling inspection rule corresponding to the target bill according to the sampling inspection rule to which the preset keyword belongs.

[0114] In some embodiments, the extraction instruction is used to input each bill to be inspected for data into a pre-trained keyword extraction model for keyword extraction operation.

[0115] In some embodiments, the program further includes a training instruction, which is used to obtain a training sample of a keyword extraction model to be trained, and the training sample includes text data with labels; perform 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; identify the keyword 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; adjust the parameters of the keyword extraction model to be trained based on the identification result and the label of the text data to obtain the pre-trained keyword extraction model.

[0116] In some embodiments, the program further includes a judgment instruction, which is used to calculate the difference value between the first test result and the second test result; judge whether to adjust the sampling inspection rule to be tested according to the difference value.

[0117] In some embodiments, the program further includes a cancellation instruction, which is used to cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the second region if the first test result is greater than a first preset threshold and the second test result is less than a second preset threshold; cancel the bill data inspection operation triggered by the sampling inspection rule to be tested in the first region if the second test result is greater than a first preset threshold and the first test result is less than a second preset threshold; the first preset threshold is greater than the second preset threshold.

[0118] An embodiment of the present application further provides a terminal device. The terminal device may be a device such as a smart phone or a computer.

[0119] As can be seen from the above, the embodiments of the present application provide a terminal device 1200, and the terminal device 1200 performs the following steps:

[0120] Pre-create multiple sampling rules in the database for triggering the bill data verification operation;

[0121] Take the same sampling rule to be tested and perform accuracy test operations in the first region and the second region respectively to obtain a first test result and a second test result, where the number of user populations in the first region is greater than that in the second region;

[0122] Compare and analyze the first test result and the second test result, and determine whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to the multiple sampling rules.

[0123] The embodiments of the present application also provide a storage medium, in which a computer program is stored. When the computer program runs on a computer, the computer executes the test resource optimization method based on bill verification described in any of the above embodiments.

[0124] It should be noted that for the test resource optimization method based on bill verification of the present application, those of ordinary skill in the art can understand that all or part of the processes of implementing the test resource optimization method based on bill verification described in the embodiments of the present application can be completed by controlling relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, such as stored in the memory of the terminal device and executed by at least one processor in the terminal device. During the execution process, it can include the processes of the embodiments of the test resource optimization method based on bill verification. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), etc.

[0125] For the test resource optimization device based on bill verification in the embodiments of the present application, its various functional modules can be integrated in a processing chip, or each module can exist physically alone, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk, etc.

[0126] The above has introduced in detail the method, apparatus, medium and device for optimizing test resources based on bill inspection provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A test resource optimization method based on bill inspection, characterized in that, it includes: Pre - create multiple sampling rules in the database for triggering bill data inspection operations; Perform keyword extraction operations on each bill to be inspected for data, and select target bills containing preset keywords; Determine the sampling rule to which the preset keyword belongs as the sampling rule corresponding to the target bill; Conduct an accuracy test operation on the sampling rule to be tested in the first region, record the total number of times the sampling rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and take the total number of times as the first test result; Conduct an accuracy test operation on the sampling rule to be tested in the second region, record the total number of times the sampling rule to be tested triggers a bill data inspection operation and the inspection result is abnormal within a preset time period, and take the total number of times as the second test result; Compare and analyze the first test result and the second test result, and judge whether to adjust the sampling rule to be tested according to the comparison and analysis result, so as to optimize the size of the test resources corresponding to multiple sampling rules.

2. The test resource optimization method according to claim 1, characterized in that, The operation of performing keyword extraction on each bill to be inspected for data includes: Input each bill to be inspected for data into a pre - trained keyword extraction model for keyword extraction operation.

3. The test resource optimization method according to claim 2, characterized in that, Before the operation of inputting each bill to be inspected for data into a pre - trained keyword extraction model for keyword extraction operation, the method further includes: Obtain training samples of the keyword extraction model to be trained, where the training samples include text data with labels; Extract features of the text data in the training samples through the keyword extraction model to be trained, and obtain text feature vectors corresponding to the text data; Based on the text feature vectors, identify the keywords of the text data in the training samples through the keyword extraction model to be trained, and obtain the recognition result of the text data; Based on the recognition result and the label of the text data, adjust the parameters of the keyword extraction model to be trained to obtain the pre - trained keyword extraction model.

4. The test resource optimization method according to claim 1, characterized in that, The comparison and analysis of the first test result and the second test result, and judging whether to adjust the sampling rule to be tested according to the comparison and analysis result includes: Calculate the difference value between the first test result and the second test result; Judge whether to adjust the sampling rule to be tested according to the difference value.

5. The test resource optimization method according to claim 4, characterized in that, The method further includes: If the first test result is greater than a first preset threshold and the second test result is less than a second preset threshold, cancel the operation of the sampling rule to be tested triggering bill data inspection in the second region; If the second test result is greater than the first preset threshold and the first test result is less than the second preset threshold, cancel the bill data verification operation triggered by the sampling inspection rule to be tested in the first region; The first preset threshold is greater than the second preset threshold.

6. A test resource optimization device based on bill verification, Characterized in that, The test resource optimization device based on bill verification includes: A creation module for pre-creating multiple sampling inspection rules in the database for triggering bill data verification operations; A test module for performing keyword extraction operations on each bill to be verified, selecting a target bill containing a preset keyword; determining the sampling inspection rule to which the preset keyword belongs as the sampling inspection rule corresponding to the target bill; performing an accuracy test operation on the sampling inspection rule to be tested in the first region, recording the total number of times the sampling inspection rule to be tested triggers a bill data verification operation and the inspection result is abnormal within a preset time period, and using the total number of times as the first test result; performing an accuracy test operation on the sampling inspection rule to be tested in the second region, recording the total number of times the sampling inspection rule to be tested triggers a bill data verification operation and the inspection result is abnormal within a preset time period, and using the total number of times as the second test result; An analysis module for comparing and analyzing the first test result and the second test result, and judging whether to adjust the sampling inspection rule to be tested according to the comparison and analysis result to optimize the size of the test resources corresponding to the multiple sampling inspection rules.

7. A computer-readable storage medium, Characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the test resource optimization method based on bill verification according to any one of claims 1 to 5.

8. A terminal device, Characterized in that, It includes a processor and a memory, the memory stores multiple instructions, and the processor loads the instructions to execute the test resource optimization method based on bill verification according to any one of claims 1 to 5.

Images