A combination tag-based auditing model building method, device and medium

Abstract

The application discloses a kind of based on combination label's auditing model building method, equipment and medium, method includes: obtaining road network service data, and road network service data is decomposed into multiple characteristic data;Characteristic data is analyzed, and the auditing label corresponding to characteristic data is determined;Receive the model construction request from user, and according to model construction request, determine model building logic, and determine the required label in auditing label;According to model building logic, and the required label, establish auditing model.The data is split into the smallest characteristic data, each kind of characteristic data can be assembled, there is and, or, non-relation when each kind of characteristic data is combined, and according to the result data of fusion analysis that the assembly result outputs, can improve the working efficiency and enthusiasm of auditing personnel, improve auditing efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a combination label-based auditing model building method, device and medium. BACKGROUND

[0002] In recent years, the networking charging mode has changed a lot, and gantry charging systems are arranged in the road network for vehicle toll charging and later path fitting. The upgrade of the new mode brings a sharp increase in charging business data, which has a great impact on the processing of existing businesses.

[0003] After the change of the charging mode, the ways of evading tolls are diversified and hidden, which brings a great amount of auditing work to the auditing personnel of the operating unit, causes loss of tolls for the expressway, and seriously affects the normal business order.

[0004] The existing expressway auditing model covers a variety of data irrelevant to the auditing target, and cannot be combined automatically, which leads to a complex auditing model system and slow response, and the auditing efficiency of the auditing personnel is low. SUMMARY

[0005] In order to solve the above problems, the present application provides a combination label-based auditing model building method, device and medium, wherein the method comprises:

[0006] Obtaining road network business data and decomposing the road network business data into a plurality of feature data; analyzing the feature data to determine the auditing label corresponding to the feature data; receiving a model construction request from a user, and determining a model building logic according to the model construction request, and determining a required label in the auditing label; establishing an auditing model according to the model building logic and the required label.

[0007] In one example, the obtaining road network business data and decomposing the road network business data into a plurality of feature data specifically comprises: transmitting the road network business data to the center layer through the message queue; inputting the road network business data into the pre-trained classification model in the center layer for classification to decompose the road network business data into a plurality of feature data; the feature data at least includes entrance flow data, exit flow data, gantry flow data, and license plate recognition flow data; and storing the plurality of feature data in the storage database of the center layer.

[0008] In an example, the feature data is analyzed to determine the audit label corresponding to the feature data, specifically comprising: performing comparative analysis on the feature data to determine whether the feature data corresponds to abnormal audit data; determining the audit business corresponding to the abnormal audit data, the audit business comprising at least one of no entry but exit, no exit but entry, shielding of a passing medium, billing path but no license plate recognition path, license plate recognition path but no billing path, and timeout switching card; taking the name of the feature data as a first audit label corresponding to the feature data; and taking the name of the audit business as a second audit label corresponding to the abnormal audit data.

[0009] In an example, the model construction request from the user is received, and the model construction logic is determined according to the model construction request, and the required label is determined in the audit label, specifically comprising: determining the model construction request type, the model construction request type comprising at least one of a voice information request, a text information request, and a system instruction request; selecting a corresponding preprocessing type according to the model construction request type, preprocessing the model construction request to obtain a conjunction word and a label name in the model construction request; and determining the model construction logic corresponding to the conjunction word according to a preset reference table.

[0010] In an example, the audit model is established according to the model construction logic and the required label, specifically comprising: determining the corresponding audit label according to the label name of the required label, and extracting the feature data corresponding to the audit label as preliminary data; and performing logic processing on the preliminary data according to the model construction logic to obtain model data and an audit model.

[0011] In an example, after the audit model is established according to the model construction logic and the required label, the method further comprises: verifying the accuracy of the audit model; and if the accuracy is higher than a preset threshold, saving the audit model to a database.

[0012] In an example, the road network business data comprises at least one of entry flow data, overspeed flow data, gantry transaction flow data, gantry license plate recognition flow data, green pass verification flow data, issuance data, service area data, and vehicle type recognition data.

[0013] In an example, after the audit business corresponding to the abnormal audit data is determined, the method further comprises: issuing the abnormal data to an audit personnel through a business work order; if a target vehicle has a historical audit business, taking the feature data corresponding to the target vehicle as target data; and when performing comparative analysis on the feature data to determine whether the feature data corresponds to abnormal audit data, preferentially performing comparative analysis on the target data.

[0014] The application further provides a device for building an auditing model based on a combined label, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: acquiring road network service data and decomposing the road network service data into a plurality of feature data; analyzing the feature data to determine an auditing label corresponding to the feature data; receiving a model building request from a user and determining a model building logic according to the model building request and determining a required label in the auditing label; and building an auditing model according to the model building logic and the required label.

[0015] The application further provides a non-volatile computer storage medium storing computer executable instructions, which are configured to: acquire road network service data and decompose the road network service data into a plurality of feature data; analyze the feature data to determine an auditing label corresponding to the feature data; receive a model building request from a user and determine a model building logic according to the model building request and determine a required label in the auditing label; and build an auditing model according to the model building logic and the required label.

[0016] The method provided by the application can bring the following beneficial effects: by splitting data into the smallest feature data, each type of feature data can be assembled, each type of feature data has an and, or or not relationship when combined, and the result data of fusion analysis is output according to the assembly result, which can improve the working efficiency and enthusiasm of auditors and improve the auditing efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the application and constitute a part of this application, illustrate certain illustrative embodiments of the application and together with the description serve to explain the application. In the drawings:

[0018] Figure 1 FIG. 1 is a flowchart of a method for building an auditing model based on a combined label according to an embodiment of the application;

[0019] Figure 2 FIG. 2 is a structural diagram of a device for building an auditing model based on a combined label according to an embodiment of the application. DETAILED DESCRIPTION

[0020] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in combination with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0021] The technical solutions provided by the embodiments of the present application will be described in detail below in combination with the drawings.

[0022] Figure 1 A flowchart of a method for building a combination tag-based auditing model is provided for one or more embodiments of the present specification. The method can be applied to the field of highway auditing business, and the flowchart can be executed by a computing device in the corresponding field. Some input parameters or intermediate results in the flowchart allow manual intervention to adjust to help improve accuracy.

[0023] The implementation of the analysis method related to the embodiments of the present application can be a terminal device or a server, and the present application does not make special limitations thereon. For the convenience of understanding and description, the following embodiments are described in detail with the server as an example.

[0024] It should be noted that the server can be a single device, or a system composed of multiple devices, i.e., a distributed server, and the present application does not make specific limitations thereon.

[0025] As shown in Figure 1 The embodiments of the present application provide a method for building a combination tag-based auditing model, which comprises:

[0026] S101: Obtain road network business data and decompose the road network business data into multiple feature data.

[0027] First, the road network business data in the highway needs to be obtained, and then the road network business data is decomposed into multiple feature data. It should be noted that the feature data here refers to data about a single feature of a vehicle, such as vehicle entry time data, vehicle exit time data, etc.

[0028] In one embodiment, the road network business data includes at least one of entry flow data, super flow data, gantry transaction flow data, gantry license flow data, green pass verification flow data, issuance data, service area data, and vehicle type identification data. It can also include: lane snapshot image; gantry snapshot image; police checkpoint data; ETC issuance data; lane exit data; exit snapshot image, etc.

[0029] In one embodiment, when the road network service data is decomposed, the road network service data needs to be first transmitted to the center layer through the message queue, and then the road network service data is input into the pre-trained classification model in the center layer for classification to decompose the road network service data into multiple feature data. The feature data at least includes entrance flow data, exit flow data, gantry flow data, and license plate recognition flow data. Finally, the multiple feature data can be stored in the storage database of the center layer.

[0030] S102: analyzing the feature data to determine the audit label corresponding to the feature data.

[0031] In combination with the modular thinking, the feature data is analyzed, and all the feature data is labeled. Each vehicle passing will have its own corresponding audit label.

[0032] In one embodiment, when the audit label is determined, the feature data needs to be compared and analyzed to determine whether the feature data corresponds to abnormal audit data. Then, the audit business corresponding to the abnormal audit data is determined, which includes at least one of no exit after entry, no entry after exit, shielding passing medium, billing path without license plate recognition path, license plate recognition path without billing path, and timeout switching card. Then, the name of the feature data is taken as the first audit label corresponding to the feature data, and the name of the audit business is taken as the second audit label corresponding to the abnormal audit data.

[0033] Further, after determining the audit business corresponding to the abnormal audit data, the abnormal data is issued to the audit personnel for processing through the business work order to realize the closed-loop processing of the audit business. In addition, if the target vehicle has historical audit business, the feature data corresponding to the target vehicle is listed as target data. When the feature data is compared and analyzed to determine whether the feature data corresponds to abnormal audit data, the target data is preferentially compared and analyzed.

[0034] S103: receiving a model construction request from a user, and determining a model building logic according to the model construction request, and determining the required label in the audit label.

[0035] Receiving a model construction request from a user, then sequentially establishing a model building logic, and determining the required set label for building a model.

[0036] In one embodiment, when determining the model building logic and determining the audit label, first, the model building request type is determined, and the model building request type herein includes at least one of a voice information request, a text information request, and a system instruction request. It should be noted that the voice information request herein refers to a model building request of a voice type, and the system instruction request refers to dragging the audit label in the system and manually selecting the model building logic. Then, according to the model building request type, a corresponding preprocessing type is selected to preprocess the model building request to obtain the connecting words and the label name in the model building request. Taking the model building request of the voice information request type as an example, the preprocessing herein refers to text recognition of the voice information, and then according to a pre-established connecting word library and a label name library, the text recognition result is extracted to obtain the connecting words and the label name. Finally, according to a preset correspondence table, the model building logic corresponding to the connecting words is determined.

[0037] S104: Establishing an audit model according to the model building logic and the required label.

[0038] Each type of feature data can be assembled, and each type of label can be combined with and, or, and not relationships, and the result data of the fusion analysis is output according to the assembly result.

[0039] In one embodiment, when establishing the audit model, first, the corresponding audit label is determined according to the label name of the required label, and the feature data corresponding to the audit label is extracted as the preliminary data, and then the preliminary data is logically processed according to the model building logic to obtain the model data and the audit model. For example, when two audit labels of export timeout and existence of bottom-up charging are selected, and the model building logic is “and”, the combined data of the existence of the two labels can be queried.

[0040] In one embodiment, after the audit model is established, the output data of the self-built audit model needs to be verified to analyze the accuracy of the combined model, and detailed information can be viewed during the verification process, such as entry information, exit information, gantry information, path information, and related snapshot pictures. When the self-model data verification accuracy is high, the self-model can be saved for later retrieval, and the business relationship between the self-models can also be adjusted and modified. When the audit model data is verified to be correct, the self-model can be published, and the audit institution can audit the data pushed by the model.

[0041] As shown in FIG. 1, Figure 2 The embodiment of the present application also provides an audit model building device based on a combined label, which comprises:

[0042] at least one processor; and,

[0043] a memory in communication with the at least one processor; wherein

[0044] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0045] obtain road network service data, and decompose the road network service data into a plurality of feature data; analyze the feature data to determine an audit label corresponding to the feature data; receive a model construction request from a user, and determine a model building logic according to the model construction request, and determine a required label in the audit label; and establish an audit model according to the model building logic and the required label.

[0046] The embodiments of the present application also provide a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured to:

[0047] obtain road network service data, and decompose the road network service data into a plurality of feature data; analyze the feature data to determine an audit label corresponding to the feature data; receive a model construction request from a user, and determine a model building logic according to the model construction request, and determine a required label in the audit label; and establish an audit model according to the model building logic and the required label.

[0048] Each of the embodiments of the present application is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other, and each of the embodiments mainly describes the difference from other embodiments. Especially, the device and medium embodiments are described simply because they are basically similar to the method embodiments, and the related parts can be referred to the part of the description of the method embodiments.

[0049] The device and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the device and medium also have the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here.

[0050] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0051] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0052] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0053] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0054] In one typical configuration, the computing device includes one or more processors (CPU's), input / output interfaces, network interfaces, and memory.

[0055] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0056] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0057] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0058] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for building a combination tag-based auditing model, characterized in that, The method comprises the following steps: acquiring road network service data and decomposing the road network service data into multiple feature data; analyzing the feature data to determine the audit label corresponding to the feature data; receiving a model construction request from a user and determining a model construction logic according to the model construction request, and determining a required label in the audit label; establishing an audit model according to the model construction logic and the required label; the acquisition of road network service data and the decomposition of the road network service data into multiple feature data specifically comprises: transmitting the road network service data to the center layer through the message queue; inputting the road network service data into the pre-trained classification model in the center layer for classification to decompose the road network service data into multiple feature data; the feature data at least includes entrance flow data, exit flow data, gantry flow data, license plate recognition flow data; storing the multiple feature data in the storage database of the center layer; the analysis of the feature data to determine the audit label corresponding to the feature data specifically comprises: comparative analysis of the feature data to determine whether the feature data corresponds to abnormal audit data; determining the audit business corresponding to the abnormal audit data, the audit business including at least one of no exit after entry, no entry after exit, shielding passing medium, billing path without license plate recognition path, license plate recognition path without billing path, and timeout switching card; using the name of the feature data as the first audit label corresponding to the feature data; using the name of the audit business as the second audit label corresponding to the abnormal audit data; the receiving of a model construction request from a user and the determination of a model construction logic according to the model construction request, and the determination of a required label in the audit label specifically comprises: determining the model construction request type, the model construction request type including at least one of voice information request, text information request and system instruction request; according to the model construction request type, selecting a corresponding preprocessing type to preprocess the model construction request to obtain the conjunction words and label name in the model construction request; determining the model construction logic corresponding to the conjunction words according to the preset comparison table.

2. The method of claim 1, wherein, the establishment of an audit model according to the model construction logic and the required label specifically comprises: determining the corresponding audit label according to the label name of the required label, and extracting the feature data corresponding to the audit label as the preliminary data; according to the model construction logic, logically processing the preliminary data to obtain model data and an audit model.

3. The method of claim 1, wherein, after the establishment of an audit model according to the model construction logic and the required label, the method further comprises: verifying the accuracy of the audit model; if the accuracy is higher than a preset threshold, saving the audit model to a database.

4. The method of claim 1, wherein, The road network service data includes at least one of entrance flow data, overspeed flow data, gantry transaction flow data, gantry license plate flow data, green pass verification flow data, issuance data, service area data, and vehicle type identification data.

5. The method of claim 1, wherein, After determining the audit business corresponding to the abnormal audit data, the method further comprises: The abnormal data is issued to the audit personnel in the form of a service work order; If the target vehicle has a history of audit business, the feature data corresponding to the target vehicle is listed as target data; When comparing and analyzing the feature data to determine whether the feature data corresponds to abnormal audit data, the target data is preferentially compared and analyzed.

6. A combination tag based auditing model setup device, comprising: Comprises: At least one processor; And a memory connected in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1-5.

7. A non-transitory computer storage medium storing computer-executable instructions that, when executed, cause a computer to perform: The computer executable instructions are configured to perform the steps of the method according to any one of claims 1-5.

Images