Data auditing method and device, electronic equipment and storage medium

By integrating the allocation model and historical audit results within the property area, the system intelligently determines the target audit roles, solving the problem of unreasonable audit roles caused by traditional manual allocation and improving the efficiency and accuracy of the audit process.

CN118917610APending Publication Date: 2024-11-08CHINA CONSTRUCTION BANK +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411022306.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional methods of assigning roles in property area reviews rely on human experience, leading to unreasonable role allocation and consequently, stagnation and inefficiency in the review process.

Method used

By acquiring the business area information and pending review information corresponding to the review task, the review probability is calculated using an allocation model, and the target review role is intelligently determined by combining historical review results and role levels.

Benefits of technology

This improved the accuracy and efficiency of the assignment of review roles, ensuring that review tasks are reasonably assigned to the most suitable review roles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917610A_ABST
    Figure CN118917610A_ABST
Patent Text Reader

Abstract

The invention discloses a data auditing method and device, electronic equipment and a storage medium, and relates to the technical field of big data. A specific embodiment of the method comprises the steps of obtaining a business area corresponding to an auditing task in response to the auditing task of to-be-processed data, querying a current state and an area type of the business area, and determining a corresponding auditing role set; obtaining to-be-audited information corresponding to the auditing task and basic information of the business area, extracting auditing elements from the to-be-audited information, and calculating an auditing probability of each auditing role corresponding to the auditing task based on the auditing elements and the basic information; obtaining a historical auditing result corresponding to each auditing role, fusing the historical auditing result with the auditing probability, and determining a target auditing role corresponding to the auditing task based on a fusion result; and sending the auditing task to the target auditing role. According to the embodiment, the problems that the auditing process is stagnated and the auditing efficiency is reduced due to the fact that auditing role distribution is unreasonable sometimes in a traditional auditing role distribution method can be solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method, device, electronic device and storage medium for data auditing. Background Art

[0002] In the context of urbanization, the property management industry has risen rapidly, and the management and auditing of property areas have become increasingly critical. As a core link in property management, the accuracy and efficiency of audit role allocation in property areas play a decisive role in the normal operation and service quality of the entire property area. In related technologies, traditional audit role allocation methods mainly rely on the experience and rules of offline staff, which sometimes makes audit role allocation unreasonable, leading to stagnation of the audit process and reduced audit efficiency. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method, device, electronic device and storage medium for data auditing, which can solve the problem that the traditional audit role allocation method sometimes makes the audit role allocation unreasonable, causing the audit process to stagnate and reduce the audit efficiency.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for data auditing is provided.

[0005] A data audit method according to an embodiment of the present invention includes: in response to an audit task of data to be processed, obtaining a business area corresponding to the audit task, querying a current state and area type of the business area, and determining a corresponding audit role set;

[0006] Acquire the to-be-audited information corresponding to the audit task and the basic information of the business area, extract the audit elements from the to-be-audited information, call a preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information;

[0007] Obtaining historical audit results corresponding to each of the audit roles, fusing the historical audit results with the audit probability, and determining a target audit role corresponding to the audit task based on the fusion result;

[0008] The audit task is sent to the target audit role.

[0009] In one embodiment, the historical audit results include a historical audit success rate;

[0010] Obtaining the historical audit results corresponding to each of the audit roles, and fusing the historical audit results with the audit probability, including:

[0011] Obtaining the role level corresponding to each of the audit roles, determining each set of pending audit roles through a clustering model, and filtering the target set based on the audit probability;

[0012] The historical audit success rate of each audit role in the target set is obtained, and the historical audit success rate and the audit probability are fused to obtain a fusion result corresponding to the target set.

[0013] In yet another embodiment, obtaining the historical audit results corresponding to each of the audit roles and fusing the historical audit results with the audit probability includes:

[0014] Based on the audit probability, a target set is screened from the audit roles, and time information of historical audit tasks corresponding to each audit role in the target set is obtained;

[0015] The application time corresponding to the audit task is obtained, and the application time is matched with the time information to determine the fusion result corresponding to the target set based on the matching result.

[0016] In yet another embodiment, determining a target audit role corresponding to the audit task based on the fusion result includes:

[0017] The fusion result of each audit role in each of the target sets is obtained, and a preset conversion model is called to convert the fusion result into a code in a preset format to determine the target audit role through the code.

[0018] In yet another embodiment, after sending the audit task to the target audit role, the method further includes:

[0019] Monitoring the audit status of the audit tasks;

[0020] In response to the audit status being updated to an abnormal state, the audit data of the audit task is acquired to identify abnormal information, and the abnormal information is updated to a verification set.

[0021] In yet another embodiment, calling a preset allocation model to calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information includes:

[0022] The audit elements and the basic information are input into the input layer of the allocation model, and the data features of the audit elements and the basic information are extracted in turn through each hidden layer in the allocation model, so as to calculate the audit probability of the audit elements corresponding to each audit role through the output layer in the allocation model.

[0023] To achieve the above objective, according to another aspect of an embodiment of the present invention, a data auditing device is provided.

[0024] A data audit device according to an embodiment of the present invention includes: a determination unit, configured to respond to an audit task of data to be processed, obtain a business area corresponding to the audit task, query a current state and area type of the business area, and determine a corresponding audit role set;

[0025] A calculation unit, used to obtain the to-be-audited information corresponding to the audit task and the basic information of the business area, extract the audit elements from the to-be-audited information, call a preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information;

[0026] The determination unit is further configured to obtain historical audit results corresponding to each of the audit roles, fuse the historical audit results with the audit probability, and determine the target audit role corresponding to the audit task based on the fusion result;

[0027] A sending unit is used to send the audit task to the target audit role.

[0028] In one embodiment, the historical audit results include a historical audit success rate;

[0029] The determining unit is specifically configured to:

[0030] Obtaining the role level corresponding to each of the audit roles, determining each set of pending audit roles through a clustering model, and filtering the target set based on the audit probability;

[0031] The historical audit success rate of each pending audit role in the target set is obtained, and the historical audit success rate and the audit probability are fused to obtain a fusion result corresponding to the target set.

[0032] In yet another embodiment, the determining unit is specifically configured to:

[0033] Based on the audit probability, a target set is screened from the audit roles, and time information of historical audit tasks corresponding to each audit role in the target set is obtained;

[0034] The application time corresponding to the audit task is obtained, and the application time is matched with the time information to determine the fusion result corresponding to the target set based on the matching result.

[0035] In yet another embodiment, the determining unit is specifically configured to:

[0036] The fusion result of each audit role in each of the target sets is obtained, and a preset conversion model is called to convert the fusion result into a code in a preset format to determine the target audit role through the code.

[0037] In yet another embodiment, the apparatus further comprises:

[0038] A monitoring unit, used to monitor the audit status of the audit task;

[0039] An updating unit is used for acquiring the audit data of the audit task in response to the audit status being updated to an abnormal state, so as to identify abnormal information, and to update the abnormal information to a verification set.

[0040] In yet another embodiment, the computing unit is specifically configured to:

[0041] The audit elements and the basic information are input into the input layer of the allocation model, and the data features of the audit elements and the basic information are extracted in turn through each hidden layer in the allocation model, so as to calculate the audit probability of the audit elements corresponding to each audit role through the output layer in the allocation model.

[0042] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device is provided.

[0043] An electronic device according to an embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the data audit method provided by the embodiment of the present invention.

[0044] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer readable medium is provided.

[0045] A computer-readable medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements the data audit method provided by the embodiment of the present invention.

[0046] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer program product is provided.

[0047] A computer program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the data audit method provided by the embodiment of the present invention is implemented.

[0048] One embodiment of the above invention has the following advantages or beneficial effects: In the embodiment of the present invention, for an audit task, the current status and area type of the corresponding business area can be obtained first to query the audit role set, that is, to determine the range of audit roles to which the audit task can be assigned; then, the audit probability of each audit role corresponding to the audit task can be calculated using the allocation model through the audit task's pending information and the basic information of the business area; then, the target audit role corresponding to the audit task can be determined in combination with the audit probability and the historical audit results corresponding to each audit role, and the audit task can be sent to the target audit role. In the embodiment of the present invention, for a task that needs to be audited, the set of audit roles that can be assigned can be determined first, and then the audit probability that can be assigned to each audit role that can be assigned can be calculated through the audit task's pending information and the basic information of the corresponding business area, so that the audit role can be determined more reasonably and intelligently, and the target audit role can be determined by the fusion of the audit probability and the historical audit results, thereby improving the accuracy of the audit task allocation.

[0049] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0051] Figure 1 is a schematic diagram of a main process of a method for data auditing according to an embodiment of the present invention;

[0052] Figure 2 is a schematic diagram of another main process of the data audit method according to an embodiment of the present invention;

[0053] Figure 3 is a schematic diagram of another main process of the data audit method according to an embodiment of the present invention;

[0054] Figure 4 is a schematic diagram of main units of a data auditing apparatus according to an embodiment of the present invention;

[0055] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0056] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0058] It should be pointed out that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict. The acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0059] The embodiment of the present invention provides a data audit system, which can be used to assign audit roles to audit tasks, so that the audit roles can audit the audit tasks, and specifically can be used to assign audit tasks in the property field. In the embodiment of the present invention, the digital housing field included in the property field is used as an example for explanation. The digital housing field can include but is not limited to residential areas, commercial buildings, industrial parks and other property areas. In these areas, there will be different audit tasks that need to audit property data in different states, and the corresponding audit roles are also different.

[0060] The embodiment of the present invention provides a method for data auditing, which can be executed by a data auditing system, such as Figure 1 As shown, the method includes:

[0061] S101: In response to an audit task of data to be processed, obtain a business area corresponding to the audit task, query the current state and area type of the business area, and determine a corresponding audit role set.

[0062] Among them, the audit task of the data to be processed can be sent to the data audit system by the party who needs to conduct data audit, and the audit task can carry the information to be audited in the form of description text, etc. The business area can represent the area of ​​business processing, such as the area of ​​property business processing, and the data to be processed can be specifically property data, so the business area can be specifically the property area. Taking the data to be processed as property data as an example, the audit task can include auditing the property area information belonging to it, such as the address information or identification of the property area, etc., to determine the property area corresponding to this audit task. The current state of the property area can represent the construction state of the building in the property area, such as before construction, under construction and completed construction. The area type of the property area can represent the type of building, such as residential areas, commercial buildings, industrial parks and other property areas. The audit role represents the role that audits the audit task. Since there are differences in the property data required to be audited in different states and area types, the corresponding audit roles are not exactly the same. In the embodiment of the present invention, the audit roles corresponding to the current state and area type of each property area can be pre-established, and then the audit role set corresponding to the audit task can be determined in this step.

[0063] S102: Obtain the information to be audited and the basic information of the business area corresponding to the audit task, extract the audit elements from the information to be audited, call the preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information.

[0064] Among them, the information to be reviewed corresponding to the audit task may include specific audit data that needs to be reviewed, such as the delivery review of equipment belonging to a residential community, and the information to be reviewed may include the equipment name, installation location, ownership, type, activation time, equipment status, etc. These information usually need to be used or confirmed in the task review. The basic information of the business area can be diverse, such as basic information such as the size, type, and administrative area of ​​the property area. This information is usually used to determine the corresponding audit role for the audit task. The extraction method in this step is not limited, and the specific audit requirements to be extracted can be extracted by text recognition. In an embodiment of the present invention, the allocation model is pre-configured, and the audit elements and basic information are input into the allocation model to calculate the audit probability of each audit role corresponding to the audit task. The audit probability of an audit role represents the probability of assigning the audit task to the audit role.

[0065] Specifically, in an embodiment of the present invention, the allocation model may include an input layer, a hidden layer, and an input layer, so in this step, the audit elements and basic information may be input into the input layer of the allocation model, and the data features of the audit elements and basic information may be extracted in turn through each hidden layer in the allocation model, so as to calculate the audit probability of each audit role corresponding to the audit elements through the output layer in the allocation model.

[0066] For example, the allocation model can be specifically a deep neural network model. A multi-layer deep neural network structure is adopted, including an input layer, multiple hidden layers and an output layer. The activation function of the allocation model can be selected as ReLU to promote the learning of nonlinear relationships. Among them, the input layer is used to receive input data; multiple hidden layers can perform feature extraction through each hidden layer, such as the first hidden layer can use the fully connected layer for feature extraction, and each neuron in the hidden layer can be responsible for capturing key features in different data. The intermediate hidden layer (abstract representation layer) can extract higher-level abstract features step by step, such as complex audit role distribution relationships; the output layer can be used to calculate and output the probability distribution of the audit role, such as using a softmax activation function to output the corresponding probability distribution for each possible audit role.

[0067] S103: Obtain the historical audit results corresponding to each audit role, fuse the historical audit results with the audit probability, and determine the target audit role corresponding to the audit task based on the fusion results.

[0068] Among them, after the audit probability of each audit role is obtained, the historical audit results corresponding to each audit role can be obtained, so as to integrate the historical audit results and the audit probability to determine the target audit role corresponding to the audit task.

[0069] Specifically, on the one hand, the historical audit results include the historical audit success rate, which indicates the success probability of the audit task being sent to the audit role, and illustrates the accuracy of the audit task allocation. The fusion process in this step can be performed as follows: obtaining the role level corresponding to each audit role, determining each pending audit role set through a clustering model, and filtering the target set based on the audit probability; obtaining the historical audit success rate of each audit role in the target set, and fusing the historical audit success rate and the audit probability to obtain the fusion result corresponding to the target set.

[0070] The role level corresponding to the audit role can be pre-set, and the audit roles of the same role level can be clustered through clustering calculation to obtain the pending audit role sets, and then the sum of the audit probabilities of the audit roles included in the pending audit role set can be determined as the target set. After determining the target set, the historical audit success rate of each audit role and the corresponding historical audit success rate can be fused, such as weighted summation, to obtain the fusion result.

[0071] On the other hand, the fusion process in this step can also be performed as follows: based on the audit probability, the target set is screened from the audit roles, and the time information of the historical audit tasks corresponding to each pending audit role in the target set is obtained; the application time corresponding to the audit task is obtained, and the application time is matched with the time information to determine the fusion result corresponding to the target set based on the matching result. In this step, the audit roles with lower audit probability can be first proposed, that is, the target set is screened from the audit roles based on the audit probability. The target set can represent the audit roles with an audit probability greater than a preset threshold, and then the time information of the historical audit tasks corresponding to each pending audit role in the target set can be obtained. The time information can be specifically a time distribution trend. Since the submission of audit tasks usually has time characteristics, such as external planned audit tasks are usually sent at the initial stage of work every day, and then they will be assigned to different audit roles, and some audit tasks that need to be assigned to other audit roles by one audit role are usually at the later stage of work every day. Therefore, in the embodiment of the present invention, after determining the time information of the historical audit tasks corresponding to each audit role, it can be matched with the application time corresponding to the audit task to determine whether the application time matches the time information. Specifically, in this step, the time interval of the historical audit task allocation corresponding to the audit role can be determined based on the time information, and then it can be judged whether the application time belongs to the time interval. If so, the matching result is determined to be a successful match; if not, the matching result is determined to be a failed match, so that the audit roles that failed to match in the target set can be eliminated to obtain the fusion result.

[0072] In an embodiment of the present invention, after obtaining the fusion result, the target audit role corresponding to the audit task can be determined based on the fusion result. Specifically, it can be performed as follows: obtain the fusion result of each audit role in each target set, call a preset conversion model, convert the fusion result into a code in a preset format, and determine the target audit role through the code.

[0073] After the fusion results of each audit role in the target set, the results can be converted into a code in a preset format to facilitate the determination of the target audit role. The conversion model is pre-configured, the specific method may not be limited, and the preset format may be set based on demand.

[0074] It should be noted that in an embodiment of the present invention, a pre-trained fusion model can also be established to input the historical audit results and audit probabilities corresponding to each audit role into the fusion model, so as to obtain the target audit role corresponding to the audit task. The construction method of the fusion model can be the same as the allocation model.

[0075] S104: Send the audit task to the target audit role.

[0076] Among them, after the target audit role is determined, that is, the object of auditing the audit task is determined, the audit task can be sent to the target audit role so that the target audit role can audit the audit task.

[0077] It should be noted that, in the embodiment of the present invention, the subsequent audit status of the audit task can also be monitored, that is, the audit status of the audit task can be monitored; if the status of the audit task is abnormal, that is, the audit task is in an abnormal state, the audit data of the audit task can be obtained first to identify the abnormal information, and the abnormal information is updated to the verification set. The verification set can include the abnormal information of each audit task, which is used to perform verification on the audit task before this step, so as to avoid abnormalities as much as possible.

[0078] In an embodiment of the present invention, for tasks that need to be audited, a set of audit roles that can be assigned can be determined first, and then the audit probability that can be assigned to each audit role can be calculated through the audited information of the audit task and the basic information of the corresponding property area. This allows the audit role to be determined more reasonably and intelligently, and the target audit role is determined through the fusion of the audit probability and historical audit results, thereby improving the accuracy of audit task allocation.

[0079] It should be noted that in the embodiments of the present invention, the allocation model is usually pre-trained, and the training can adopt supervised learning, so the loss function can select the cross entropy loss function, which is used to measure the difference between the predicted probability distribution in the model training procedure and the actual audit role allocation. The cross entropy loss function is widely used in classification tasks, and its mathematical form is shown in Formula 1.

[0080] H(y,p)=-∑iyilog(pi) (1)

[0081] Where y represents the actual audit role allocation result, p is the audit probability distribution of the audit role predicted by the model, and i represents the i-th audit role.

[0082] During the model training process, the optimization algorithm can be selected from the optimization algorithm such as gradient descent, which calculates the gradient of the loss function with respect to the distribution model parameters and iteratively adjusts the parameters to minimize the loss. The update rule of gradient descent can be shown in Formula 2.

[0083]

[0084] Among them, θ represents the model parameters of the allocation model, and η represents the learning rate.

[0085] At the same time, regularization techniques can also be introduced during the training process, such as L2 regularization, which adds regularization terms to the loss function to reduce the complexity of the distribution model and avoid overfitting. L2 regularization adds the square sum of parameter weights to the loss function and adjusts the degree of fit of the model, as shown in Formula 3. Where λ represents the regularization coefficient.

[0086] H′(y,p)=H(y,p)+λ∑iθi^2 (3)

[0087] Batch normalization can also be applied during training to accelerate the convergence process and improve the stability of the model. Standardizing the input within each training mini-batch helps alleviate the gradient vanishing problem and improve the stability of the gradient flow. The standardized input introduces additional expressive power to the network through learnable scaling and translation parameters.

[0088] For the allocation model, the network depth is adjusted in the embodiment of the present invention. The allocation model can use a depth of 3 layers to ensure that the model has sufficient flexibility to capture the basic pattern of the property area audit task, and then through experiments and cross-validation, the network depth is dynamically adjusted according to the complexity of the specific property area audit task. For the number of input layer nodes: 10 nodes can be selected for the multi-dimensional features of the historical data used for model training in the property area, such as area, approval type, approval status, etc. to ensure that the data features are fully expressed. For the number of hidden layer nodes: for the first hidden layer, each neuron should focus on capturing key features in different historical data, such as the impact of development and construction unit satisfaction on the audit role; the neurons in the middle hidden layer can be increased step by step to extract higher-level abstract features.

[0089] Monitoring of overfitting and underfitting: Monitoring performance: During the training process, the performance of the model on the validation set can also be closely monitored, with special attention paid to the accuracy and generalization ability of the model. If overfitting is found, the number of layers can be reduced or regularization techniques can be added, such as introducing a Dropout layer, to reduce the complexity of the model. If underfitting exists, the number of layers or nodes can be increased to increase the complexity of the model to ensure a better fit to the data. The embodiments of the present invention combine the complexity of the data and the generalization ability of the model, which helps to improve the performance and adaptability of the audit role allocation model.

[0090] During model training, the prediction results also need to be verified. The trained allocation model receives data from process modeling and predicts the audit role of each process node. These prediction results are compared with the actual audit results to verify the accuracy and effectiveness of the model. By monitoring the performance of the allocation model in the business scenario, it can be confirmed whether the allocation model has successfully learned the patterns and rules in the process. Through the above steps, the data from process modeling plays a role in verification and confirmation in model training. Process modeling provides real business data, and the prediction results of the model prove to a certain extent whether the model can understand and apply the patterns in these data. The mutual verification process further enhances the credibility and adaptability of the model by ensuring that the training data of the model is consistent with the actual business scenario.

[0091] Combine the following Figure 1 The embodiment shown in the figure specifically describes the method for data auditing in the embodiment of the present invention. Figure 2 As shown, the method includes:

[0092] S201: In response to an audit task of property data, obtain the property area corresponding to the audit task, query the current status and area type of the property area, and determine the corresponding audit role set.

[0093] S202: Obtain the information to be reviewed and the basic information of the property area corresponding to the review task, and extract the review elements from the information to be reviewed.

[0094] S203: Calling a preset allocation model, and calculating the audit probability of each audit role corresponding to the audit task based on the audit elements and basic information.

[0095] S204: Obtain the role level corresponding to each audit role, determine each pending audit role set through a clustering model, and filter the target set based on the audit probability.

[0096] S205: Obtain the historical audit results corresponding to each audit role, fuse the historical audit results with the audit probability, and determine the target audit role corresponding to the audit task based on the fusion results.

[0097] S206: Send the audit task to the target audit role.

[0098] S207: Monitor the audit status of the audit task; in response to the audit status being updated to an abnormal state, obtain the audit data of the audit task to identify abnormal information, and update the abnormal information to the verification set.

[0099] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The corresponding data processing principles in the illustrated embodiments are the same and will not be described in detail here.

[0100] Combine the following Figure 1 The embodiment shown in the figure specifically describes the method for data auditing in the embodiment of the present invention. Figure 3 As shown, the method includes:

[0101] S301: In response to an audit task of property data, obtain the property area corresponding to the audit task, query the current status and area type of the property area, and determine the corresponding audit role set.

[0102] S302: Obtain the information to be reviewed and the basic information of the property area corresponding to the review task, and extract the review elements from the information to be reviewed.

[0103] S303: Calling a preset allocation model, and calculating the audit probability of each audit role corresponding to the audit task based on the audit elements and basic information.

[0104] S304: Obtain the role level corresponding to each audit role, determine each pending audit role set through a clustering model, and filter the target set based on the audit probability.

[0105] S305: Obtain the historical audit success rate of each audit role in the target set, and fuse the historical audit success rate and the audit probability to obtain a fusion result corresponding to the target set.

[0106] S306: Determine the target audit role corresponding to the audit task based on the fusion result.

[0107] S307: Send the audit task to the target audit role.

[0108] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The corresponding data processing principles in the illustrated embodiments are the same and will not be described in detail here.

[0109] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a data auditing device 400, such as Figure 4 As shown, the device 400 includes:

[0110] A determination unit 401 is used to respond to the audit task of the data to be processed, obtain the business area corresponding to the audit task, query the current state and area type of the business area, and determine the corresponding audit role set;

[0111] A calculation unit 402 is used to obtain the to-be-audited information corresponding to the audit task and the basic information of the business area, extract the audit elements from the to-be-audited information, call a preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information;

[0112] The determination unit 401 is further configured to obtain historical audit results corresponding to each audit role, fuse the historical audit results with the audit probability, and determine the target audit role corresponding to the audit task based on the fusion result;

[0113] The sending unit 403 is used to send the audit task to the target audit role.

[0114] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 The method of the illustrated embodiment is the same and will not be repeated here.

[0115] In one embodiment, the historical audit results include a historical audit success rate;

[0116] The determining unit is specifically configured to:

[0117] Obtaining the role level corresponding to each of the audit roles, determining each set of pending audit roles through a clustering model, and filtering the target set based on the audit probability;

[0118] The historical audit success rate of each pending audit role in the target set is obtained, and the historical audit success rate and the audit probability are fused to obtain a fusion result corresponding to the target set.

[0119] In yet another embodiment, the determining unit is specifically configured to:

[0120] Based on the audit probability, a target set is screened from the audit roles, and time information of historical audit tasks corresponding to each audit role in the target set is obtained;

[0121] The application time corresponding to the audit task is obtained, and the application time is matched with the time information to determine the fusion result corresponding to the target set based on the matching result.

[0122] In yet another embodiment, the determining unit is specifically configured to:

[0123] The fusion result of each audit role in each of the target sets is obtained, and a preset conversion model is called to convert the fusion result into a code in a preset format to determine the target audit role through the code.

[0124] In yet another embodiment, the apparatus further comprises:

[0125] A monitoring unit, used to monitor the audit status of the audit task;

[0126] An updating unit is used for acquiring the audit data of the audit task in response to the audit status being updated to an abnormal state, so as to identify abnormal information, and to update the abnormal information to a verification set.

[0127] In yet another embodiment, the computing unit is specifically configured to:

[0128] The audit elements and the basic information are input into the input layer of the allocation model, and the data features of the audit elements and the basic information are extracted in turn through each hidden layer in the allocation model, so as to calculate the audit probability of the audit elements corresponding to each audit role through the output layer in the allocation model.

[0129] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 , 2 , and 3 are the same as the embodiments shown in FIG. 3 and will not be described again here.

[0130] In an embodiment of the present invention, for tasks that need to be audited, a set of audit roles that can be assigned can be determined first, and then the audit probability that can be assigned to each audit role can be calculated through the audited information of the audit task and the basic information of the corresponding property area. This allows the audit role to be determined more reasonably and intelligently, and the target audit role is determined through the fusion of the audit probability and historical audit results, thereby improving the accuracy of audit task allocation.

[0131] According to an embodiment of the present invention, the embodiment of the present invention further provides an electronic device and a readable storage medium.

[0132] The electronic device of an embodiment of the present invention comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the data audit method provided by the embodiment of the present invention.

[0133] Figure 5 An exemplary system architecture 500 is shown to which the method for data auditing or the apparatus for data auditing according to the embodiment of the present invention can be applied.

[0134] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0135] The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various client applications can be installed on the terminal devices 501, 502, 503.

[0136] The terminal devices 501 , 502 , and 503 may be, but are not limited to, smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0137] The server 505 may be a server that provides various services. The server may analyze and process the received data such as the product information query request, and feed back the processing result (such as product information - just an example) to the terminal device.

[0138] It should be noted that the data audit method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the data audit device is generally set in the server 505 .

[0139] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0140] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an embodiment of the present invention. Figure 6 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0141] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0142] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0143] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0144] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0145] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a unit, a program segment, or a part of a code, and the above-mentioned unit, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0146] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a determination unit, a calculation unit, and a sending unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the determination unit may also be described as a "unit for determining a function".

[0147] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device executes the data audit method provided by the present invention.

[0148] As another aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the data audit method provided by an embodiment of the present invention.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for data auditing, characterized in that: include: In response to the audit task of the data to be processed, obtaining the business area corresponding to the audit task, querying the current state and area type of the business area, and determining the corresponding audit role set; Acquire the to-be-audited information corresponding to the audit task and the basic information of the business area, extract the audit elements from the to-be-audited information, call a preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information; Obtaining historical audit results corresponding to each of the audit roles, fusing the historical audit results with the audit probability, and determining a target audit role corresponding to the audit task based on the fusion result; The audit task is sent to the target audit role.

2. The method according to claim 1, characterized in that: The historical audit results include historical audit success rate; Obtaining the historical audit results corresponding to each of the audit roles, and fusing the historical audit results with the audit probability, including: Obtaining the role level corresponding to each of the audit roles, determining each set of pending audit roles through a clustering model, and filtering the target set based on the audit probability; The historical audit success rate of each audit role in the target set is obtained, and the historical audit success rate and the audit probability are fused to obtain a fusion result corresponding to the target set.

3. The method according to claim 1, characterized in that Obtaining the historical audit results corresponding to each of the audit roles, and fusing the historical audit results with the audit probability, including: Based on the audit probability, a target set is selected from the audit roles, and time information of historical audit tasks corresponding to each audit role in the target set is obtained; The application time corresponding to the audit task is obtained, and the application time is matched with the time information to determine the fusion result corresponding to the target set based on the matching result.

4. The method according to claim 2 or 3, characterized in that: The target audit role corresponding to the audit task is determined based on the fusion result, including: The fusion result of each audit role in each of the target sets is obtained, and a preset conversion model is called to convert the fusion result into a code in a preset format to determine the target audit role through the code.

5. The method according to claim 1, characterized in that After sending the audit task to the target audit role, the method further includes: Monitoring the audit status of the audit tasks; In response to the audit status being updated to an abnormal state, the audit data of the audit task is acquired to identify abnormal information, and the abnormal information is updated to a verification set.

6. The method according to claim 1, characterized in that Calling a preset allocation model to calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information, including: The audit elements and the basic information are input into the input layer of the allocation model, and the data features of the audit elements and the basic information are extracted in turn through each hidden layer in the allocation model, so as to calculate the audit probability of the audit elements corresponding to each audit role through the output layer in the allocation model.

7. A data audit device, characterized in that: include: A determination unit, configured to respond to an audit task of the data to be processed, obtain a business area corresponding to the audit task, query a current state and area type of the business area, and determine a corresponding audit role set; A calculation unit, used to obtain the to-be-audited information corresponding to the audit task and the basic information of the business area, extract the audit elements from the to-be-audited information, call a preset allocation model, and calculate the audit probability of each audit role corresponding to the audit task based on the audit elements and the basic information; The determination unit is further configured to obtain historical audit results corresponding to each of the audit roles, fuse the historical audit results with the audit probability, and determine the target audit role corresponding to the audit task based on the fusion result; A sending unit is used to send the audit task to the target audit role.

8. The device according to claim 7, characterized in that The historical audit results include historical audit success rate; The determining unit is specifically configured to: Obtaining the role level corresponding to each of the audit roles, determining each set of pending audit roles through a clustering model, and filtering the target set based on the audit probability; The historical audit success rate of each pending audit role in the target set is obtained, and the historical audit success rate and the audit probability are fused to obtain a fusion result corresponding to the target set.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.