Qualitative method and device for audit problem, equipment and storage medium

Abstract

The invention discloses an auditing problem qualitative method and device, equipment and a storage medium. The method comprises the steps that an auditing problem text of an auditing unit on an auditing project is acquired; converting the audit question text into a word vector set through the target word vector model; inputting the word vector set into a target violation type prediction model to obtain a first violation type label corresponding to the audit problem text; and inputting the word vector set and the first violation type label into a target regulation prediction model, determining a first qualitative regulation label corresponding to the audit problem text through a qualitative regulation prediction task, and determining a first processing punishment regulation label corresponding to the audit problem text and the first qualitative regulation label through a processing punishment regulation prediction task. The auditing problem qualitative efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of audit data processing technology, and in particular to a qualitative method, device, equipment and storage medium for audit issues. Background Art

[0002] In the process of auditing the audited projects of the audited units, auditors need to audit the financial data, contract data, engineering data and other project data of the audited projects to discover the audit problems in the project data, and then conduct qualitative analysis of the audit problems to determine the violation types, qualitative regulations and handling and punishment regulations of the audit problems, so as to form audit opinions and audit decisions.

[0003] In the traditional qualitative method of audit problems, the audit problems are usually manually analyzed qualitatively based on the audit experience of the auditors. Since the current audit problems involve a wide range of fields, a large number of regulations and provisions, and the limited experience of auditors, it usually takes a lot of time to analyze to obtain objective and comprehensive violation types, qualitative regulations and handling and punishment regulations, resulting in low efficiency in the qualitative analysis of audit problems. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the embodiments of the present application provide a qualitative method, apparatus, device and storage medium for audit issues, which converts the audit issue text of the audited unit on the audited project into a word vector set, and inputs the word vector set into a target violation type prediction model to obtain a first violation type label, and then inputs the word vector set and the first violation type label into a target regulation prediction model to obtain a first qualitative regulation label and a first processing and punishment regulation label, thereby qualitatively analyzing the audit issue text through the pre-trained target violation type prediction model and the target regulation prediction model, thereby improving the efficiency of qualitative analysis of audit issues.

[0005] In a first aspect, an embodiment of the present application provides a qualitative method for auditing problems, including:

[0006] Acquire the audit problem text of the audited unit on the audited project; the audit problem text is a text describing the problems found in the project data of the audited project during the audit process;

[0007] The audit question text is converted into a word vector set through a target word vector model; the word vector set includes a plurality of feature word vectors;

[0008] Inputting the word vector set into the target violation type prediction model to obtain a first violation type label corresponding to the audit question text; the first violation type label is used to indicate the violation type corresponding to the audit question text;

[0009] The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task, and the first processing and penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing and penalty regulation prediction task; the qualitative regulation prediction task and the processing and penalty regulation prediction task are both subtasks of the target regulation prediction model; the first qualitative regulation label is used to indicate the qualitative regulation clause corresponding to the audit problem text, and the first processing and penalty regulation label is used to indicate the processing and penalty regulation clause corresponding to the audit problem text and the qualitative regulation clause.

[0010] In a second aspect, an embodiment of the present application provides a qualitative device for auditing problems, including:

[0011] An acquisition module is used to acquire the audit problem text of the audited unit on the audited project; the audit problem text is a text describing the problems found in the project data of the audited project during the audit process;

[0012] A processing module, used to convert the audit question text into a word vector set through a target word vector model; the word vector set includes a plurality of feature word vectors;

[0013] Inputting the word vector set into the target violation type prediction model to obtain a first violation type label corresponding to the audit question text; the first violation type label is used to indicate the violation type corresponding to the audit question text;

[0014] The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task, and the first processing and penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing and penalty regulation prediction task; the qualitative regulation prediction task and the processing and penalty regulation prediction task are both subtasks of the target regulation prediction model; the first qualitative regulation label is used to indicate the qualitative regulation clause corresponding to the audit problem text, and the first processing and penalty regulation label is used to indicate the processing and penalty regulation clause corresponding to the audit problem text and the qualitative regulation clause.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the first aspect.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program product is operable to cause a computer to execute the method described in the first aspect.

[0018] Implementing the embodiments of the present application has the following beneficial effects:

[0019] In the embodiment of the present application, firstly, the audit problem text of the audited unit on the audited project is obtained, and the audit problem text is converted into a word vector set through the target word vector model. Then, the word vector set is input into the target violation type prediction model to obtain the first violation type label corresponding to the audit problem text. Finally, the word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined by the qualitative regulation prediction task of the target regulation prediction model, and the first processing and punishment regulation label corresponding to the audit problem text and the first qualitative regulation label is determined by the processing and punishment regulation prediction task of the target regulation prediction model. Thus, through the pre-trained target violation type prediction model, the first violation type label corresponding to the audit problem text can be determined according to the word vector set corresponding to the audit problem text to determine the violation type corresponding to the audit problem text. Through the pre-trained target regulation prediction model, the first qualitative regulation label and the first processing and punishment regulation label corresponding to the audit problem text can be determined according to the word vector set and the first violation type label to determine the qualitative regulation clause and the processing and punishment regulation clause corresponding to the audit problem text. Compared with manual qualitative analysis of audit problems, the efficiency of qualitative analysis of audit problems can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A schematic diagram of an application scenario of a qualitative method for auditing problems provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of a qualitative method for auditing problems provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a target violation type prediction model provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of a target regulation prediction model provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of a qualitative device for auditing questions provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0029] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] First, see Figure 1 , Figure 1 A schematic diagram of an application scenario of a qualitative method for auditing problems provided in an embodiment of the present application. Figure 1As shown in the figure, during the process of the audited project, the audit unit needs to conduct an audit investigation on the project data of the audited project according to relevant laws and regulations to determine whether there are any audit problems in the construction process of the audited project. The audited unit can be a power grid unit. After determining the audit problems of the audited unit, the audit unit needs to characterize the audit problems and determine the violation types, qualitative laws and regulations, and handling and punishment laws and regulations corresponding to the audit problems.

[0031] The project data of the audited project of the audited unit is stored in a database, which can be multiple computers or servers for data storage, reading and writing functions, and the computer or server includes a memory, for example, the memory can be a random access memory (RAM), a read-only memory (ROM), a hard disk drive (HDD), a solid state drive (SSD), etc., which are used to store and retrieve data in a computer. The database can also store the historical audit data of the audited unit, which is not limited in this application.

[0032] Among them, the processing device of the audit unit can read the project data of the audited project from the database. The processing device can be a server with data reading and writing, high-performance computing and data caching functions, including: application server, virtual private server (Virtual Private Server, VPS), rack server, etc. The processing device can also be a processor chip of a computer, including: Central Processing Unit (CPU), Digital Signal Processing (DSP), embedded microcontroller (Micro-Controller Unit, MCU), etc., which is not limited in this application. Exemplarily, the processing device can be connected to the user interaction device to display the project data of the audited project on the user interaction device. The auditors of the audit unit can audit the project data according to the project data displayed on the user interaction device, find audit problems in the project data of the audited project, thereby determining the audit problem text corresponding to the project data of the audited project, and input the audit problem text through the user interaction device. The processing device can obtain the audit problem text of the audited unit on the audited project from the user interaction device to characterize the audit problem text.

[0033] It should be noted that in the traditional qualitative method of audit issues, the audit issues are usually manually qualitatively analyzed based on the experience of the auditors of the audit unit. When there are many audit issues, the fields involved are wide, and the number of regulations involved is large, the auditors need to spend a lot of time to conduct qualitative analysis on the audit issues in order to obtain objective and accurate qualitative results. The qualitative results include the type of violation, the qualitative regulations and the handling and punishment regulations. Therefore, the traditional qualitative method of audit issues has the problem of low qualitative efficiency. In addition, the manual qualitative analysis of audit issues is affected by the experience of the auditors, resulting in low qualitative accuracy.

[0034] To this end, in the qualitative method of audit questions provided in this application, the processing device obtains the audit question text of the audited unit on the audited project;

[0035] The processing device converts the audit question text into a word vector set through a target word vector model;

[0036] The processing device inputs the word vector set into the target violation type prediction model to obtain a first violation type label corresponding to the audit question text;

[0037] The processing device inputs the word vector set and the first violation type label into the target regulation prediction model, determines the first qualitative regulation label corresponding to the audit question text through the qualitative regulation prediction task, and determines the first processing penalty regulation label corresponding to the audit question text and the first qualitative regulation label through the processing penalty regulation prediction task.

[0038] It can be seen that, applied to the above scenario, the processing device can obtain the audit problem text of the audited unit on the audited project and convert the audit problem text into a word vector set. Then, the word vector set is input into the target violation type prediction model to obtain the first violation type label corresponding to the audit problem text. Finally, the word vector set and the first violation type label are input into the target regulation prediction model to obtain the first qualitative regulation label and the first processing and punishment regulation label corresponding to the audit problem text, so as to determine the qualitative regulation provisions and processing and punishment regulation provisions corresponding to the audit problem text. Qualitative analysis of audit issues through pre-trained target violation type prediction models and target regulation prediction models can improve the efficiency and accuracy of qualitative analysis of audit issues compared to manual qualitative analysis of audit issues.

[0039] See also Figure 2 , Figure 2 A flowchart of a qualitative method for auditing problems provided in an embodiment of the present application. The method is applied to a processing device in the above scenario, and the method includes but is not limited to the following steps:

[0040] 201: Obtain the audit question text of the audited entity on the audited project.

[0041] In an embodiment of the present application, the audited unit may be the construction unit of the audited project, and the audited projects may include: cable tunnel engineering projects, high-altitude power transmission line construction projects, power station construction projects, and the like. The audit question text is a text that describes the problems found in the project data of the audited project during the audit process. Project data may include: financial data, contract data, engineering construction data, and the like. For example, the audit question text may be "The contracts for some engineering projects of the audited unit in the audited project lack the seal of the approval unit." The format of the audit question text is a JSON format that can be input into the target word vector model.

[0042] Optionally, the processing device may directly obtain the audit question text input by the user from the user interaction device. The processing device may also determine the audit question text based on the project data of the audited project, which is not limited in this application.

[0043] 202: Convert the audit question text into a word vector set through the target word vector model.

[0044] In an embodiment of the present application, the word vector set includes multiple feature word vectors. The semantics of each feature word vector can be determined by the feature word vector value and direction corresponding to the feature word vector. The target word vector model is pre-trained from the reference word vector model.

[0045] Exemplarily, before converting the audit question text into a word vector set by using the target word vector model, the following steps may also be included:

[0046] Get the reference word vector model;

[0047] Obtain multiple sets of training data;

[0048] Preprocessing the audit question text corresponding to each set of training data in the multiple sets of training data to obtain multiple sets of target training data;

[0049] The reference word vector model is trained using multiple sets of target training data to obtain a target word vector model.

[0050] In the embodiment of the present application, each set of training data includes the audit question text corresponding to the training data and the word vector set corresponding to the audit question text. The preprocessing operation includes word segmentation operation, stop word removal operation and format conversion operation.

[0051] The reference word vector model may be a Word2vec model, which is a deep learning model for converting text into feature word vectors, and can map words in the text to a high-dimensional vector space, so that words with similar semantics are close in distance in the vector space. The Word2vec model includes a continuous bag of words model (CBOW) and a skip-gram model. CBOW can predict the current word based on the words in the context, and Skip Gram can predict the words in the context based on the current word.

[0052] Specifically, the processing device first obtains the reference word vector model, and then obtains multiple sets of training data from the database. Optionally, the processing device can also crawl multiple sets of training data from the audit qualitative retrieval system through the Fiddler tool. The audit question qualitative retrieval system is a system used to collect, process and retrieve qualitative data during the audit process. The audit question qualitative retrieval system stores a large number of audit question texts and word vector sets corresponding to the audit question texts, which can be used to train the reference word vector model.

[0053] Then, the processing device will perform a word segmentation operation on the audit question text corresponding to each set of training data in the multiple sets of training data to obtain multiple text words, and remove stop words from the multiple text words to obtain multiple content words. Finally, the multiple content words are converted into a JSON format that can be input into the reference word vector model to obtain multiple target words, thereby obtaining multiple sets of target training data. By using the multiple target words corresponding to each set of target training data in the multiple sets of target training data as the input of the reference word vector model, and using the word vector corresponding to each set of target training data as the output of the reference word vector model, the reference word vector model is trained to obtain a target word vector model. Among them, the number of iterations of model training can be preset.

[0054] Therefore, by training the reference word vector model with multiple sets of target training data after preprocessing, a target word vector model can be obtained, so as to convert the audit question text into a word vector set through the target word vector model, thereby qualitatively characterizing the audit question text through the word vector set, thereby improving the accuracy and efficiency of the qualitative characterization of audit questions.

[0055] Based on this, the processing device can obtain multiple words by performing preprocessing operations on the audit question text, and then input the multiple words into the target word vector model to obtain a word vector set.

[0056] 203: Input the word vector set into the target violation type prediction model to obtain the first violation type label corresponding to the audit question text.

[0057] In the embodiment of the present application, the first violation type label is used to indicate the violation type corresponding to the audit question text. The violation type may include: false financial data, contract violation, engineering management violation, etc.

[0058] The target violation type prediction model is a model based on the BiLSTM-TextCNN-Attention structure. Exemplarily, the target violation type prediction model includes: a bidirectional long short-term memory network (Bidirectional LongShort Term Memory, BiLSTM) model, a text convolutional neural network (Convolutional Neural Networkfor Text, TextCNN) model, an attention mechanism Attention layer and a classifier. Input the word vector set into the target violation type prediction model to obtain the first violation type label corresponding to the audit question text, which may include:

[0059] The BiLSTM model is used to extract the feature word vectors in the word vector set to obtain the global feature set.

[0060] The TextCNN model is used to extract features from the feature word vectors in the word vector set and the global feature word vectors in the global feature set to obtain a local feature set.

[0061] Determine the attention weight corresponding to each feature word vector in the global feature set and the local feature set through the Attention layer; perform weighted summation of the feature word vectors in the global feature set and the local feature set according to the attention weight corresponding to each feature word vector in the global feature set and the local feature set to obtain the target feature word vector;

[0062] The target feature word vector is classified by the classifier to obtain the first violation type label.

[0063] In the embodiment of the present application, the global feature set includes a plurality of global feature word vectors, and the local feature set includes at least one local feature word vector.

[0064] Specifically, Figure 3As shown, the processing device first extracts features from multiple feature word vectors in the word vector set through the BiLSTM model, wherein the feature extraction includes two parts, forward propagation and backward propagation, the forward propagation is processed by the forward LSTM, and the backward propagation is processed by the backward LSTM. In the forward LSTM, the features of each feature word vector are extracted from front to back according to the arrangement order of the multiple feature word vectors in the audit question text. In the backward LSTM, the features of each feature word vector are extracted from back to front according to the arrangement order of the multiple feature word vectors in the audit question text. After both the forward LSTM and the backward LSTM have extracted the features of all feature word vectors in the word vector set, the BiLSTM model can output a global feature set, which includes multiple global feature word vectors.

[0065] Then, if Figure 3 As shown, the processing device uses the TextCNN model to jointly extract features from multiple feature word vectors in the word vector set and multiple global feature word vectors in the global feature set to obtain a local feature set, which includes at least one local feature word vector. Among them, the convolution layer in the TextCNN model can extract local features by sliding the convolution kernel on multiple feature word vectors and multiple global feature word vectors, and the size of the convolution kernel can be pre-set according to needs. Then, the local features extracted by the convolution layer are downsampled through the pooling layer to reduce the dimension of the local features. Finally, the features output by the pooling layer are integrated through the fully connected layer to obtain a local feature set.

[0066] Furthermore, if Figure 3As shown, multiple global feature word vectors in the global feature set and multiple local feature sets in the local feature set can be weighted and summed through the Attention layer to obtain the target feature word vector. Specifically, the processing device determines the attention weight corresponding to each feature word vector in the global feature set and the local feature set through the Attention layer. Exemplarily, the attention weight corresponding to each feature word vector can be determined by the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm, that is, the number of occurrences of the vocabulary corresponding to each feature word vector in the global feature set and the local feature set in the audit question text is determined, and the total number of occurrences of the vocabulary corresponding to all feature word vectors in the word vector set in the audit question text is determined. Then, according to the number of occurrences corresponding to each feature word vector in the global feature set and the local feature set and the total number of occurrences of the vocabulary corresponding to all feature word vectors in the word vector set in the audit question text, the attention weight of each feature word vector in the global feature set and the local feature set is determined. Then, according to the attention weight corresponding to each feature word vector in the global feature set and the local feature set, all feature word vectors in the global feature set and the local feature set are weighted and summed to obtain the target feature word vector.

[0067] Finally, if Figure 3 As shown, the processing device can classify the target feature word vector through a classifier to obtain a first violation type label. Optionally, the classifier can be a softmax classifier, which can predict the probability that the target feature word vector is a label of different violation types.

[0068] Optionally, the target violation type prediction model can be trained by using training data crawled from the audit question qualitative retrieval system, where the training data includes a word vector set corresponding to the audit question text and a violation type label corresponding to the audit question text. The prediction performance of the target violation type prediction model can be improved through training, and a violation type label corresponding to the audit question text can be obtained.

[0069] It can be seen that after the word vector set is input into the target violation type prediction model, the feature word vectors in the word vector set can be extracted through the BiLSTM model to obtain the global feature set. Then, the feature word vectors in the word vector set and the global feature word vectors in the global feature set are extracted through the TextCNN model to obtain the local feature set. Furthermore, the weighted sum of each feature word vector in the global feature set and the local feature set is performed through the Attention layer to obtain the target feature word vector. Finally, the target feature word vector can be classified by the classifier to obtain the first violation type label. Therefore, the pre-trained target violation type prediction model can directly determine the first violation type label corresponding to the audit problem text according to the word vector set corresponding to the audit problem text, so as to obtain the violation type corresponding to the audit problem text. Compared with manual qualitative analysis of the audit problem text, the qualitative efficiency of the audit problem is improved. In addition, the accuracy of the qualitative analysis of the audit problem can be improved by training the target violation type prediction model.

[0070] 204: Input the word vector set and the first violation type label into the target regulation prediction model, determine the first qualitative regulation label corresponding to the audit problem text through the qualitative regulation prediction task, and determine the first processing penalty regulation label corresponding to the audit problem text and the first qualitative regulation label through the processing penalty regulation prediction task.

[0071] In the embodiment of the present application, both the qualitative regulation prediction task and the processing and penalty regulation prediction task are subtasks of the target regulation prediction model. The first qualitative regulation tag is used to indicate the qualitative regulation clause corresponding to the audit question text, and the first processing and penalty regulation tag is used to indicate the processing and penalty regulation clause corresponding to the audit question text and the qualitative regulation clause.

[0072] It should be noted that the target regulation prediction model is a multi-task learning model. In the embodiment of the present application, the target regulation prediction model includes two subtasks, namely, the qualitative regulation prediction task and the penalty regulation prediction task. The correlation between the two subtasks can be effectively utilized through the target regulation prediction model to improve the accuracy of the prediction of the qualitative regulation label and the penalty regulation label.

[0073] Exemplarily, inputting the word vector set and the first violation type label into the target regulation prediction model, determining the first qualitative regulation label corresponding to the audit question text through the qualitative regulation prediction task, and determining the first processing penalty regulation label corresponding to the audit question text and the first qualitative regulation label through the processing penalty regulation prediction task may include:

[0074] According to the first violation type label, feature extraction is performed on multiple feature word vectors in the word vector set to obtain multiple common feature word vectors;

[0075] Extract features from multiple feature word vectors through the qualitative law prediction task to obtain multiple first sub-feature word vectors corresponding to the qualitative law prediction task; use the multiple common feature word vectors and the multiple first sub-feature word vectors as task feature word vectors corresponding to the qualitative law prediction task to obtain multiple first task feature word vectors;

[0076] Determine the semantic distance between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of first semantic distances;

[0077] Determining a first qualitative regulatory label from a plurality of preset qualitative regulatory labels according to a plurality of first semantic distances;

[0078] By processing the penalty regulations prediction task, feature extraction is performed on multiple feature word vectors to obtain multiple second sub-feature word vectors corresponding to the penalty regulations prediction task;

[0079] Determine a third sub-feature word vector corresponding to the first qualitative regulatory label;

[0080] The plurality of common feature word vectors, the third sub-feature word vectors and the plurality of second sub-feature word vectors are used together as task feature word vectors corresponding to the penalty regulations prediction task to obtain a plurality of second task feature word vectors;

[0081] Determine the semantic distance between the plurality of second task feature word vectors and the feature word vector set of each preset processing penalty regulation label in the plurality of preset processing penalty regulation labels to obtain a plurality of second semantic distances;

[0082] According to the plurality of second semantic distances, a first processing penalty regulation label is determined from a plurality of preset processing penalty regulation labels.

[0083] In the embodiments of the present application, Figure 4 As shown, the target regulation prediction model may include: a sharing layer, a qualitative regulation prediction task hidden layer, and a processing penalty regulation prediction task hidden layer.

[0084] Specifically, Figure 4 As shown, the processing device inputs multiple feature word vectors in the word vector set and the first violation type label into the shared layer of the target regulation prediction model. The shared layer can obtain the target feature word vector according to the first violation type label. Then, feature extraction is performed on the target feature word vector and the multiple feature word vectors to extract common features from the target feature word vector and the multiple feature word vectors to obtain multiple common feature word vectors. Optionally, the shared layer may include a convolutional neural network (CNN) for performing feature extraction on the target feature word vector and the multiple feature word vectors.

[0085] After extracting multiple common feature word vectors, the multiple common feature word vectors are input into the hidden layer of the qualitative regulations prediction task and the hidden layer of the processing and punishment regulations prediction task. Among them, the hidden layer of the qualitative regulations prediction task and the hidden layer of the processing and punishment regulations prediction task also input the word vector set corresponding to the audit question text. Specifically, firstly, the multiple feature word vectors are feature extracted through the hidden layer of the qualitative regulations prediction task to obtain multiple first sub-feature word vectors corresponding to the qualitative regulations prediction task. It can be understood that the number of layers and the hidden layer function of the qualitative regulations prediction task hidden layer can be pre-set according to the actual test results, so that the qualitative regulations prediction task hidden layer can extract multiple first sub-feature word vectors corresponding to the qualitative regulations prediction task. Then, the multiple common feature word vectors and the multiple first sub-feature word vectors are used together as the task feature word vectors corresponding to the qualitative regulations prediction task to obtain multiple first task feature word vectors.

[0086] Furthermore, the processing device determines the semantic distance between the first task feature word vectors and the feature word vector set of each of the plurality of preset qualitative regulatory labels through the qualitative regulatory prediction task hidden layer, and obtains a plurality of first semantic distances. The plurality of preset qualitative regulatory labels are the qualitative regulatory labels corresponding to all qualitative regulatory provisions in the audit question qualitative retrieval system.

[0087] Exemplarily, determining the semantic distances between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain the plurality of first semantic distances may include:

[0088] Determine the intersection of the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of feature word vector intersections;

[0089] Determine the intersection of the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of feature word vector unions;

[0090] Determine multiple similarity coefficients according to the intersection of multiple feature word vectors and the union of multiple feature word vectors;

[0091] A plurality of first semantic distances are determined according to the plurality of similarity coefficients.

[0092] In an embodiment of the present application, the first semantic distance is used to represent the semantic relevance between the semantics corresponding to multiple first task feature word vectors and the preset regulatory label corresponding to the first semantic distance. The closer the first semantic distance is, the closer the semantics corresponding to multiple first task feature word vectors are to the preset regulatory label corresponding to the first semantic distance.

[0093] Specifically, the processing device first determines the intersection of multiple first task feature word vectors and the feature word vector set of each preset qualitative regulatory label in multiple preset qualitative regulatory labels, and obtains multiple feature word vector intersections. Determine the number of feature word vectors in each feature word vector intersection in the multiple feature word vector intersections, and obtain multiple first quantities. Then, determine the union of multiple first task feature word vectors and the feature word vector set of each preset qualitative regulatory label in multiple preset qualitative regulatory labels, and obtain multiple feature word vector unions. Determine the number of feature word vectors in each feature word vector union in the multiple feature word vector unions, and obtain multiple second quantities.

[0094] Further, the processing device uses the ratio of the multiple first quantities to the multiple second quantities as a similarity coefficient to obtain multiple similarity coefficients, and the multiple preset qualitative regulatory labels correspond to the multiple similarity coefficients one by one. Optionally, the similarity coefficient can be a Jaccard coefficient. The value range of the similarity coefficient is [0, 1]. When the similarity coefficient is 1, it means that the multiple first task feature word vectors completely overlap with the feature word vector set of the preset qualitative regulatory label corresponding to the similarity coefficient. When the similarity coefficient is 0, it means that the multiple first task feature word vectors have no intersection with the feature word vector set of the preset qualitative regulatory label corresponding to the similarity coefficient. Finally, based on the multiple similarity coefficients, multiple first semantic distances can be determined, wherein the first semantic distance is equal to (1-similarity coefficient). The value range of the first semantic distance is [0, 1]. When the first semantic distance is 0, it means that the semantics corresponding to the multiple first task feature word vectors are consistent with the semantics of the preset qualitative regulatory label corresponding to the similarity coefficient. When the first semantic distance is 1, it means that the semantics corresponding to the multiple first task feature word vectors are completely different from the semantics of the preset qualitative regulatory label corresponding to the similarity coefficient. The closer the first semantic distance is, the closer the semantics corresponding to the multiple first task feature word vectors are to the semantics of the preset regulatory label corresponding to the first semantic distance.

[0095] Thus, by determining the intersection of multiple first task feature word vectors and the feature word vector set of each preset qualitative regulatory label in multiple preset qualitative regulatory labels, multiple feature word vector intersections are obtained. Then, the union of multiple first task feature word vectors and the feature word vector set of each preset qualitative regulatory label in multiple preset qualitative regulatory labels is determined to obtain multiple feature word vector unions. Furthermore, based on the multiple feature word vector intersections and the multiple feature word vector unions, multiple similarity coefficients can be determined. Finally, based on the multiple similarity coefficients, multiple first semantic distances can be determined, thereby determining the correlation between the semantics corresponding to the multiple first task feature word vectors and the semantics of each preset qualitative regulatory label, thereby improving the accuracy of qualitative regulatory label prediction.

[0096] Furthermore, the processing device may use the preset regulatory label with the shortest first semantic distance among the plurality of preset regulatory labels as the first qualitative regulatory label. Figure 4 As shown, the first qualitative regulation label can also be used as the input of the hidden layer of the processing and punishment regulation prediction task. The processing and punishment regulation prediction task hidden layer will extract features from multiple feature word vectors in the word vector set to obtain multiple second sub-feature word vectors corresponding to the processing and punishment regulation prediction task. It can be understood that the number of layers and hidden layer functions of the processing and punishment regulation prediction task hidden layer can be pre-set according to actual test results so that the processing and punishment regulation prediction task hidden layer can extract multiple second sub-feature word vectors corresponding to the processing and punishment regulation prediction task.

[0097] Furthermore, the processing device extracts features of the first qualitative regulation label by processing the hidden layer of the penalty regulation prediction task to obtain a third sub-feature word vector corresponding to the first qualitative regulation label. Then, the plurality of common feature word vectors, the third sub-feature word vectors and the plurality of second sub-feature word vectors are used together as the task feature word vector corresponding to the penalty regulation prediction task to obtain a plurality of second task feature word vectors.

[0098] Next, determine the semantic distance between the multiple second task feature word vectors and the feature word vector set of each preset processing and punishment regulation label in the multiple preset processing and punishment regulation labels to obtain multiple second semantic distances. The second semantic distance is used to represent the semantic relevance between the semantics corresponding to the multiple second task feature word vectors and the preset processing and punishment regulation label corresponding to the second semantic distance. The closer the second semantic distance, the closer the semantics corresponding to the multiple second task feature word vectors are to the semantics of the preset processing and punishment regulation label corresponding to the second semantic distance. Among them, the method for determining the semantic distance between the multiple second task feature word vectors and the feature word vector set of each preset processing and punishment regulation label in the multiple preset processing and punishment regulation labels is similar to the method for determining the semantic distance between the multiple first task feature word vectors and the feature word vector set of each preset processing and punishment regulation label in the above-mentioned embodiment, and will not be repeated here.

[0099] Finally, the processing device will take the preset processing penalty regulation label with the shortest second semantic distance among multiple preset processing penalty regulation labels as the first processing penalty regulation label, and thereby determine the processing penalty regulation article corresponding to the audit question text based on the first processing penalty regulation label.

[0100] It can be seen that according to the first violation type label, the feature word vectors in the word vector set can be feature extracted to obtain multiple common feature word vectors. Then, by performing feature extraction on multiple feature word vectors through the qualitative regulation prediction task, multiple first sub-feature word vectors corresponding to the qualitative regulation prediction task can be obtained, so as to obtain multiple first task feature word vectors corresponding to the qualitative regulation prediction task based on multiple common feature word vectors and multiple first sub-feature word vectors. By determining the semantic distance between multiple first task feature word vectors and the feature word vector set of each preset qualitative regulation label in multiple preset qualitative regulation labels, the first qualitative regulation label can be determined from multiple preset qualitative regulation labels, thereby obtaining the qualitative regulatory provisions corresponding to the audit problem text, thereby improving the efficiency and accuracy of the qualitative characterization of audit problems. Furthermore, by performing feature extraction on multiple feature word vectors through the processing and punishment regulations prediction task, multiple second sub-feature word vectors corresponding to the processing and punishment regulations prediction task are obtained, and the third sub-feature word vector corresponding to the first qualitative regulation label is determined, and multiple common feature word vectors, the third sub-feature word vectors and multiple second sub-feature word vectors are used together as the task feature word vector corresponding to the processing and punishment regulations prediction task, so that the processing and punishment regulations prediction task can more accurately predict the processing and punishment regulations label. By determining the semantic distance between the multiple second task feature word vectors and the feature word vector set of each preset processing and punishment regulations label in the multiple preset processing and punishment regulations labels, the first processing and punishment regulations label can be determined from the multiple preset processing and punishment regulations labels, thereby obtaining the processing and punishment regulations clause corresponding to the audit problem text, which improves the efficiency and accuracy of the qualitative characterization of the audit problem.

[0101] In an optional embodiment, the method may further include:

[0102] Obtain target project data corresponding to the audit question text from the project data;

[0103] Obtain the qualitative regulatory provisions corresponding to the first qualitative regulatory label, and obtain a verification relationship table based on the qualitative regulatory provisions;

[0104] According to the verification relationship table, the target project data is verified to obtain the verification results;

[0105] When the verification result is a verification match, the processing and punishment regulation article corresponding to the first processing and punishment regulation article tag is obtained; and multiple punishment levels are determined according to the processing and punishment regulation article;

[0106] According to the target project data, a penalty level is selected from multiple penalty levels as the target penalty level;

[0107] Determine the handling and punishment decision for the audited unit based on the target penalty level.

[0108] Among them, the verification relationship table is used to represent the mapping relationship between the project data corresponding to the qualitative regulatory provisions, and the verification relationship table can be pre-set according to the content of the qualitative regulatory provisions. The verification result includes a verification match or a verification mismatch. It can be understood that after determining the first qualitative regulatory label and the first processing and penalty regulatory label corresponding to the audit question text, the processing device will verify the first qualitative regulatory label and the first processing and penalty regulatory label to make the qualitative characterization of the audit question more accurate.

[0109] Specifically, the processing device will obtain the target project data corresponding to the audit question text from the project data of the audited project. For example, when the audit question text is "the audited project was not completed according to the contract period", the processing device will obtain the contract period and the actual completion period from the project data, and use the contract period and the actual completion period as the target project data. Then, the qualitative regulatory provisions corresponding to the first qualitative regulatory label are obtained, and the verification relationship table is obtained according to the qualitative regulatory provisions. For example, when the qualitative regulatory provisions mention the delay of the construction period, the verification relationship table is the contract period and the theoretical completion period range. At this time, the processing device shall verify the target project data according to the verification relationship table to obtain the verification result. For example, the contract period matching the audited project is found in the verification relationship table, and the theoretical completion period range of the contract period is determined. If the actual completion period of the audited project is within the theoretical completion period range, it means that the construction period is not delayed, and the verification result is verification mismatch. If the actual completion period of the audited project is outside the theoretical completion period, it means that the construction period is delayed, and the verification result is a verification match.

[0110] When the verification result is a verification match, it means that the first qualitative regulatory tag matches the audit question text. At this time, the processing device obtains the processing penalty regulatory article corresponding to the first processing penalty regulatory tag. According to the processing penalty regulatory article, multiple penalty levels are determined. For example, the processing penalty regulatory article indicates that the amount range of the fine x1-x2 for the audited unit is indicated. The processing device can divide multiple penalty levels according to the amount range, and each penalty level corresponds to a specific amount in x1-x2.

[0111] Then, according to the target project data, a penalty level is selected from multiple penalty levels as the target penalty level. For example, when the construction period is delayed by 1-10 days, the first penalty level among multiple penalty levels is used as the target penalty level, and when the construction period is delayed by 11-30 days, the second penalty level among multiple penalty levels is used as the target penalty level. In this way, the target penalty level for the audited unit can be determined, and then the handling and penalty decision for the audited unit can be determined according to the target penalty level.

[0112] It can be seen that by obtaining the target project data corresponding to the audit question text, the qualitative regulatory provisions corresponding to the first qualitative regulatory label are obtained, and the verification relationship table is obtained according to the qualitative regulatory provisions. Then, the target project data is verified through the verification relationship table to obtain the verification result, so as to verify the first qualitative regulatory label and improve the accuracy of the qualitative characterization of the audit question. When the verification result is a verification match, the processing and punishment regulatory provisions corresponding to the first processing and punishment regulatory label are obtained, and multiple penalty levels are determined according to the processing and punishment regulatory provisions. Furthermore, according to the target project data, a penalty level is selected from multiple penalty levels as the target penalty level, and the processing and punishment decision for the audited unit is determined according to the target penalty level, thereby improving the accuracy of the qualitative characterization of the audit problem.

[0113] In an optional embodiment, the method may further include:

[0114] When the verification result is a verification mismatch, determine the preset relationship corresponding to the audit question text;

[0115] If the target project data satisfies the preset relationship, the target audit question text is determined according to the target project data, and the target audit question text is used as the audit question text to obtain the second violation type label, the second qualitative regulation label, and the second processing and punishment regulation label; according to the second processing and punishment regulation label, the processing and punishment decision for the audited unit is determined;

[0116] If the target project data does not meet the preset relationship, the audit question text is input into the document material library to obtain the target violation type, target qualitative regulations and target handling and penalty regulations;

[0117] If the first violation type label and the label corresponding to the target violation type are inconsistent, determining a model adjustment parameter according to the first violation type label and the label corresponding to the target violation type; adjusting the parameters of the target violation type prediction model according to the model adjustment parameter to obtain an adjusted target violation type prediction model;

[0118] Input the word vector set into the adjusted target violation type prediction model to obtain the third violation type label;

[0119] Input the word vector set and the third violation type label into the target regulation prediction model to obtain the third qualitative regulation label and the third processing penalty regulation label;

[0120] When the third processing and penalty regulation label is consistent with the label corresponding to the target processing and penalty regulation article, the processing and penalty decision on the audited unit is determined based on the third processing and penalty regulation label.

[0121] The document material library is used to retrieve the violation types, qualitative regulatory provisions and handling and punishment regulatory provisions corresponding to the audit question text. Optionally, the document material library can be the audit question qualitative retrieval system in the above embodiment.

[0122] It is understandable that when the verification result is a verification mismatch, it means that the audit question text does not match the first qualitative regulatory label. At this time, one possibility is that the audit question text is incorrect, and another possibility is that the first violation type label predicted by the target violation type prediction model is inaccurate. Therefore, the processing device will determine the preset relationship corresponding to the audit question text. For example, when the audit question text is "the project expenditure and the declared expenditure of the final account report of the audited project do not match", the preset relationship is the mapping relationship between the project expenditure and the declared expenditure of the final account report.

[0123] If the target project data satisfies the preset relationship, it indicates that the audit question text is incorrect. The processing device can determine the target audit question text according to the target project data, use the target audit question text as the audit question text, and execute the method described in any of the above embodiments to obtain the second violation type label, the second qualitative regulation label, and the second processing and punishment regulation label. Then, the processing and punishment regulation article corresponding to the second processing and punishment regulation label is determined, and the processing and punishment decision on the audited unit is determined according to the processing and punishment regulation article corresponding to the second processing and punishment regulation label.

[0124] If the target project data does not meet the preset relationship, it means that the model prediction may have errors. The processing device will input the audit question text into the document material library to retrieve the target violation type, target qualitative regulatory provisions and target processing and penalty regulatory provisions corresponding to the audit question text in the document material library.

[0125] If the first violation type label and the label corresponding to the target violation type are inconsistent, it means that the first violation type label predicted by the target violation type prediction model is wrong, and the processing device will determine the model loss of the target violation type prediction model based on the first violation type label and the label corresponding to the target violation type. For example, the model loss can be a mean square error. According to the model loss of the target violation type prediction model, the model adjustment parameters of the target violation type prediction model can be determined. Among them, the mapping relationship between the model loss and the model adjustment parameter can be pre-set according to the actual test results. According to the model adjustment parameters of the target violation type prediction model, the parameters of the target violation type prediction model are adjusted to obtain the adjusted target violation type prediction model. Then, the word vector set is input into the adjusted target violation type prediction model to obtain a third violation type label, wherein the third violation type label is consistent with the target violation type label, and the word vector set and the third violation type label are input into the target regulation prediction model to obtain a third qualitative regulation label and a third processing and penalty regulation label.

[0126] When the third processing and penalty regulation label is consistent with the label corresponding to the target processing and penalty regulation article, the processing and penalty regulation article corresponding to the third processing and penalty regulation label is determined, and the processing and penalty decision on the audited unit is determined based on the processing and penalty regulation article corresponding to the third processing and penalty regulation label.

[0127] When the third handling and penalty regulation label is inconsistent with the label corresponding to the target handling and penalty regulation article, the first loss of the target regulation prediction model is determined based on the third handling and penalty regulation label and the target penalty regulation label, and the second loss of the target regulation prediction model is determined based on the third qualitative regulation label and the target qualitative regulation label, and the sum of the first loss and the second loss is taken as the total loss of the target regulation prediction model. The model parameters of the target regulation prediction model are adjusted according to the total loss of the target regulation prediction model until the qualitative regulation label predicted by the target regulation prediction model is consistent with the target qualitative regulation label, and the handling and penalty regulation label predicted by the target regulation prediction model is consistent with the target handling and penalty regulation label. The handling and penalty decision on the audited unit is determined based on the target handling and penalty regulation label.

[0128] Therefore, when the audit question text is incorrect, the audit question text can be adjusted; when the predicted results of the target violation type prediction model or the target regulation prediction model are incorrect, the model parameters of the target violation type prediction model or the target regulation prediction model can be adjusted to improve the accuracy of the qualitative characterization of the audit question.

[0129] In summary, in the embodiment of the present application, firstly, the audit problem text of the audited unit on the audited project is obtained, and the audit problem text is converted into a word vector set through the target word vector model. Then, the word vector set is input into the target violation type prediction model to obtain the first violation type label corresponding to the audit problem text. Finally, the word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined by the qualitative regulation prediction task of the target regulation prediction model, and the first processing and punishment regulation label corresponding to the audit problem text and the first qualitative regulation label is determined by the processing and punishment regulation prediction task of the target regulation prediction model. Thus, through the pre-trained target violation type prediction model, the first violation type label corresponding to the audit problem text can be determined according to the word vector set corresponding to the audit problem text to determine the violation type corresponding to the audit problem text. Through the pre-trained target regulation prediction model, the first qualitative regulation label and the first processing and punishment regulation label corresponding to the audit problem text can be determined according to the word vector set and the first violation type label to determine the qualitative regulation clause and the processing and punishment regulation clause corresponding to the audit problem text. Compared with manual qualitative analysis of audit issues, it can improve the efficiency of qualitative analysis of audit issues.

[0130] See also Figure 5 , Figure 5 The schematic diagram of a device for qualitative analysis of audit questions provided in an embodiment of the present application is shown in FIG. The device for qualitative analysis of audit questions 500 may be a processing device of any of the above embodiments. The device for qualitative analysis of audit questions 500 includes an acquisition module 501 and a processing module 502 .

[0131] The acquisition module 501 is used to acquire the audit problem text of the audited unit on the audited project; the audit problem text is a text describing the problems found in the project data of the audited project during the audit process;

[0132] Processing module 502, used to convert the audit question text into a word vector set through a target word vector model; the word vector set includes multiple feature word vectors;

[0133] Input the word vector set into the target violation type prediction model to obtain the first violation type label corresponding to the audit question text; the first violation type label is used to indicate the violation type corresponding to the audit question text;

[0134] The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task, and the first processing and penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing and penalty regulation prediction task; the qualitative regulation prediction task and the processing and penalty regulation prediction task are both subtasks of the target regulation prediction model; the first qualitative regulation label is used to indicate the qualitative regulation clause corresponding to the audit problem text, and the first processing and penalty regulation label is used to indicate the processing and penalty regulation clause corresponding to the audit problem text and the qualitative regulation clause.

[0135] In a possible embodiment, the target violation type prediction model includes: a BiLSTM model, a TextCNN model, an Attention layer, and a classifier; in inputting the word vector set into the target violation type prediction model to obtain a first violation type label corresponding to the audit question text, the processing module 502 is specifically used to:

[0136] The feature word vectors in the word vector set are extracted through the BiLSTM model to obtain a global feature set; the global feature set includes multiple global feature word vectors;

[0137] The feature word vectors in the word vector set and the global feature word vectors in the global feature set are extracted through the TextCNN model to obtain a local feature set; the local feature set includes at least one local feature word vector;

[0138] Determine the attention weight corresponding to each feature word vector in the global feature set and the local feature set through the Attention layer; perform weighted summation of the feature word vectors in the global feature set and the local feature set according to the attention weight corresponding to each feature word vector in the global feature set and the local feature set to obtain the target feature word vector;

[0139] The target feature word vector is classified by the classifier to obtain the first violation type label.

[0140] In a possible embodiment, in inputting the word vector set and the first violation type label into the target regulation prediction model, determining the first qualitative regulation label corresponding to the audit question text through the qualitative regulation prediction task, and determining the first processing penalty regulation label corresponding to the audit question text and the first qualitative regulation label through the processing penalty regulation prediction task, the processing module 502 is specifically used to:

[0141] According to the first violation type label, feature extraction is performed on multiple feature word vectors in the word vector set to obtain multiple common feature word vectors;

[0142] Extract features from multiple feature word vectors through the qualitative law prediction task to obtain multiple first sub-feature word vectors corresponding to the qualitative law prediction task; use the multiple common feature word vectors and the multiple first sub-feature word vectors as task feature word vectors corresponding to the qualitative law prediction task to obtain multiple first task feature word vectors;

[0143] Determine the semantic distance between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of first semantic distances;

[0144] Determining a first qualitative regulatory label from a plurality of preset qualitative regulatory labels according to a plurality of first semantic distances;

[0145] By processing the penalty regulations prediction task, feature extraction is performed on multiple feature word vectors to obtain multiple second sub-feature word vectors corresponding to the penalty regulations prediction task;

[0146] Determine a third sub-feature word vector corresponding to the first qualitative regulatory label;

[0147] The plurality of common feature word vectors, the third sub-feature word vectors and the plurality of second sub-feature word vectors are used together as task feature word vectors corresponding to the penalty regulations prediction task to obtain a plurality of second task feature word vectors;

[0148] Determine the semantic distance between the plurality of second task feature word vectors and the feature word vector set of each preset processing penalty regulation label in the plurality of preset processing penalty regulation labels to obtain a plurality of second semantic distances;

[0149] According to the plurality of second semantic distances, a first processing penalty regulation label is determined from a plurality of preset processing penalty regulation labels.

[0150] In a possible embodiment, in determining the semantic distance between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain the plurality of first semantic distances, the processing module 502 is specifically configured to:

[0151] Determine the intersection of the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of feature word vector intersections;

[0152] Determine a union of a plurality of first task feature word vectors and a feature word vector set of each of a plurality of preset regulatory labels to obtain a plurality of feature word vector unions;

[0153] Determine multiple similarity coefficients according to the intersection of multiple feature word vectors and the union of multiple feature word vectors;

[0154] A plurality of first semantic distances are determined according to the plurality of similarity coefficients.

[0155] In a possible embodiment, before converting the audit question text into a word vector set by using the target word vector model, the processing module 502 is further used to:

[0156] Get the reference word vector model;

[0157] Acquire multiple sets of training data, each set of training data includes an audit question text corresponding to the training data and a word vector set corresponding to the audit question text;

[0158] Performing preprocessing operations on the audit question texts corresponding to each set of training data in the multiple sets of training data to obtain multiple sets of target training data; the preprocessing operations include word segmentation operations, stop word removal operations, and format conversion operations;

[0159] The reference word vector model is trained using multiple sets of target training data to obtain a target word vector model.

[0160] In a possible embodiment, the processing module 502 is further configured to:

[0161] Obtain target project data corresponding to the audit question text from the project data;

[0162] Obtaining the qualitative regulatory article corresponding to the first qualitative regulatory tag, and obtaining a verification relationship table according to the qualitative regulatory article; the verification relationship table is used to represent the mapping relationship between the project data corresponding to the qualitative regulatory article;

[0163] According to the verification relationship table, the target project data is verified to obtain the verification result; the verification result includes verification match or verification mismatch;

[0164] When the verification result is a verification match, the processing and punishment regulation article corresponding to the first processing and punishment regulation article tag is obtained; and multiple punishment levels are determined according to the processing and punishment regulation article;

[0165] According to the target project data, a penalty level is selected from multiple penalty levels as the target penalty level;

[0166] Determine the handling and punishment decision for the audited unit based on the target penalty level.

[0167] In a possible embodiment, the processing module 502 is further configured to:

[0168] When the verification result is a verification mismatch, determine the preset relationship corresponding to the audit question text;

[0169] If the target project data satisfies the preset relationship, the target audit question text is determined according to the target project data, and the target audit question text is used as the audit question text to obtain the second violation type label, the second qualitative regulation label, and the second processing and punishment regulation label; according to the second processing and punishment regulation label, the processing and punishment decision for the audited unit is determined;

[0170] If the target project data does not satisfy the preset relationship, the audit question text is input into the document material library to obtain the target violation type, target qualitative regulatory provisions and target handling and punishment regulatory provisions; the document material library is used to retrieve the violation type, qualitative regulatory provisions and handling and punishment regulatory provisions corresponding to the audit question text;

[0171] If the first violation type label and the label corresponding to the target violation type are inconsistent, determining a model adjustment parameter according to the first violation type label and the label corresponding to the target violation type; adjusting the parameters of the target violation type prediction model according to the model adjustment parameter to obtain an adjusted target violation type prediction model;

[0172] Input the word vector set into the adjusted target violation type prediction model to obtain the third violation type label;

[0173] Input the word vector set and the third violation type label into the target regulation prediction model to obtain the third qualitative regulation label and the third processing penalty regulation label;

[0174] When the third processing and penalty regulation label is consistent with the label corresponding to the target processing and penalty regulation article, the processing and penalty decision on the audited unit is determined based on the third processing and penalty regulation label.

[0175] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes a transceiver 601, a processor 602 and a memory 603. They are connected via a bus 604. The memory 603 is used to store computer programs and data, and can transmit the data stored in the memory 603 to the processor 602. The electronic device 600 can be the qualitative device 500 of the audit question. The electronic device 600 can also be a processing device of any of the above embodiments.

[0176] The processor 602 is used to read the computer program in the memory 603 and perform the following operations:

[0177] Obtain the audit question text of the audited unit on the audited project;

[0178] The audit question text is converted into a word vector set through the target word vector model; the word vector set includes multiple feature word vectors;

[0179] Input the word vector set into the target violation type prediction model to obtain the first violation type label corresponding to the audit question text;

[0180] The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task. The first processing penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing penalty regulation prediction task.

[0181] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0182] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0183] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods recorded in the above method embodiments.

[0184] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0185] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0186] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0187] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0188] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0189] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0190] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0191] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A qualitative approach to audit questions, characterized in that include: Obtain the audit question text of the audited unit on the audited project; The audit question text is a text describing the problems found in the project data of the audited project during the audit process; The audit question text is converted into a word vector set through a target word vector model; the word vector set includes a plurality of feature word vectors; Inputting the word vector set into a target violation type prediction model to obtain a first violation type label corresponding to the audit question text; The first violation type label is used to indicate the violation type corresponding to the audit question text; The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task, and the first processing and penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing and penalty regulation prediction task; the qualitative regulation prediction task and the processing and penalty regulation prediction task are both subtasks of the target regulation prediction model; the first qualitative regulation label is used to indicate the qualitative regulation clause corresponding to the audit problem text, and the first processing and penalty regulation label is used to indicate the processing and penalty regulation clause corresponding to the audit problem text and the qualitative regulation clause.

2. The method according to claim 1, characterized in that The target violation type prediction model includes: a BiLSTM model, a TextCNN model, an Attention layer and a classifier; the word vector set is input into the target violation type prediction model to obtain a first violation type label corresponding to the audit question text, including: Extracting features from the feature word vectors in the word vector set by the BiLSTM model to obtain a global feature set; the global feature set includes multiple global feature word vectors; Performing feature extraction on the feature word vectors in the word vector set and the global feature word vectors in the global feature set through the TextCNN model to obtain a local feature set; the local feature set includes at least one local feature word vector; Determine the attention weight corresponding to each feature word vector in the global feature set and the local feature set through the Attention layer; perform weighted summation of the feature word vectors in the global feature set and the local feature set according to the attention weight corresponding to each feature word vector in the global feature set and the local feature set to obtain a target feature word vector; The target feature word vector is classified by the classifier to obtain the first violation type label.

3. The method according to claim 1, characterized in that The step of inputting the word vector set and the first violation type label into a target regulation prediction model, determining a first qualitative regulation label corresponding to the audit question text through a qualitative regulation prediction task, and determining a first processing penalty regulation label corresponding to the audit question text and the first qualitative regulation label through a processing penalty regulation prediction task includes: According to the first violation type label, feature extraction is performed on multiple feature word vectors in the word vector set to obtain multiple common feature word vectors; Extracting features from the multiple feature word vectors through the qualitative law prediction task to obtain multiple first sub-feature word vectors corresponding to the qualitative law prediction task; using the multiple common feature word vectors and the multiple first sub-feature word vectors together as task feature word vectors corresponding to the qualitative law prediction task to obtain multiple first task feature word vectors; Determine the semantic distance between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of first semantic distances; determining the first qualitative regulatory label from the plurality of preset qualitative regulatory labels according to the plurality of first semantic distances; Performing feature extraction on the plurality of feature word vectors through the processing penalty law prediction task to obtain a plurality of second sub-feature word vectors corresponding to the processing penalty law prediction task; Determine a third sub-feature word vector corresponding to the first qualitative regulatory label; The plurality of common feature word vectors, the third sub-feature word vectors and the plurality of second sub-feature word vectors are used together as task feature word vectors corresponding to the processing penalty regulations prediction task to obtain a plurality of second task feature word vectors; Determine the semantic distance between the plurality of second task feature word vectors and the feature word vector set of each preset processing penalty regulation label in the plurality of preset processing penalty regulation labels to obtain a plurality of second semantic distances; The first processing penalty regulation label is determined from the plurality of preset processing penalty regulation labels according to the plurality of second semantic distances.

4. The method according to claim 3, characterized in that: The determining of the semantic distances between the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of first semantic distances includes: Determine the intersection of the plurality of first task feature word vectors and the feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of feature word vector intersections; Determine a union of the plurality of first task feature word vectors and a feature word vector set of each of the plurality of preset regulatory labels to obtain a plurality of feature word vector unions; Determining a plurality of similarity coefficients according to the intersection of the plurality of feature word vectors and the union of the plurality of feature word vectors; The plurality of first semantic distances are determined according to the plurality of similarity coefficients.

5. The method according to any one of claims 1 to 4, characterized in that: Before converting the audit question text into a word vector set through a target word vector model, the method further includes: Get the reference word vector model; Acquire multiple sets of training data, each set of training data includes an audit question text corresponding to the training data and a word vector set corresponding to the audit question text; Performing a preprocessing operation on the audit question text corresponding to each set of training data in the plurality of sets of training data to obtain a plurality of sets of target training data; the preprocessing operation includes a word segmentation operation, a stop word removal operation, and a format conversion operation; The reference word vector model is trained using the multiple sets of target training data to obtain the target word vector model.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire target project data corresponding to the audit question text from the project data; Acquire the qualitative regulatory article corresponding to the first qualitative regulatory tag, and acquire a verification relationship table according to the qualitative regulatory article; the verification relationship table is used to represent the mapping relationship between the project data corresponding to the qualitative regulatory article; According to the verification relationship table, the target project data is verified to obtain a verification result; the verification result includes a verification match or a verification mismatch; When the verification result is the verification match, obtaining the processing and punishment regulation article corresponding to the first processing and punishment regulation article tag; and determining multiple punishment levels according to the processing and punishment regulation article; According to the target item data, selecting a penalty level from the multiple penalty levels as a target penalty level; Based on the target penalty level, determine the handling and penalty decision for the audited unit.

7. The method according to claim 6, characterized in that The method further comprises: When the verification result is the verification mismatch, determining a preset relationship corresponding to the audit question text; If the target project data satisfies the preset relationship, a target audit question text is determined according to the target project data, and the target audit question text is used as the audit question text to obtain a second violation type label, a second qualitative regulation label, and a second processing and punishment regulation label; and a processing and punishment decision on the audited unit is determined according to the second processing and punishment regulation label; If the target project data does not satisfy the preset relationship, the audit question text is input into the document material library to obtain the target violation type, target qualitative regulatory provisions and target handling and punishment regulatory provisions; the document material library is used to retrieve the violation type, qualitative regulatory provisions and handling and punishment regulatory provisions corresponding to the audit question text; If the first violation type label and the label corresponding to the target violation type are inconsistent, determining a model adjustment parameter according to the first violation type label and the label corresponding to the target violation type; adjusting the parameters of the target violation type prediction model according to the model adjustment parameter to obtain an adjusted target violation type prediction model; Inputting the word vector set into the adjusted target violation type prediction model to obtain a third violation type label; Inputting the word vector set and the third violation type label into the target regulation prediction model to obtain a third qualitative regulation label and a third processing penalty regulation label; When the third processing and penalty regulation label is consistent with the label corresponding to the target processing and penalty regulation article, the processing and penalty decision on the audited unit is determined according to the third processing and penalty regulation label.

8. A qualitative device for audit questions, characterized in that include: The acquisition module is used to obtain the audit question text of the audited unit on the audited project; The audit question text is a text describing the problems found in the project data of the audited project during the audit process; A processing module, used to convert the audit question text into a word vector set through a target word vector model; the word vector set includes a plurality of feature word vectors; Inputting the word vector set into a target violation type prediction model to obtain a first violation type label corresponding to the audit question text; The first violation type label is used to indicate the violation type corresponding to the audit question text; The word vector set and the first violation type label are input into the target regulation prediction model, and the first qualitative regulation label corresponding to the audit problem text is determined through the qualitative regulation prediction task, and the first processing and penalty regulation label corresponding to the audit problem text and the first qualitative regulation label is determined through the processing and penalty regulation prediction task; the qualitative regulation prediction task and the processing and penalty regulation prediction task are both subtasks of the target regulation prediction model; the first qualitative regulation label is used to indicate the qualitative regulation clause corresponding to the audit problem text, and the first processing and penalty regulation label is used to indicate the processing and penalty regulation clause corresponding to the audit problem text and the qualitative regulation clause.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images