Data processing method and device

Abstract

The embodiments of this specification provide a data processing method and device, wherein the data processing method includes: sampling indicator data of an indicator of an item to be audited in a target project according to a preset sampling interval, generating first time series data corresponding to the indicator of the item to be audited, predicting the indicator data corresponding to the indicator of the item to be audited within the target time interval based on the first time series data and project events of the target project within the target time interval, and determining the audit information corresponding to the indicator of the item to be audited within the target time interval based on the prediction result.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and more particularly to a data processing method. One or more embodiments of this specification also relate to a data processing apparatus, a computing device, and a computer-readable storage medium. Background Art

[0002] With the development of Internet technology, various services have been launched online. Although the online model is more convenient for serving users, in order to obtain a large sales market, more merchants or stores will choose to launch online services alone, or offline services alone, or both online and offline services at the same time, so as to attract more users.

[0003] However, with the increase of this phenomenon, sales scenarios have become more complicated. Some merchants or stores need to conduct compliance self-inspections when providing services to users to determine whether their business scope or business model meets the prescribed compliance conditions. With the continuous emergence of new technologies, traditional regulatory compliance methods are difficult to cope with the rapid development of various industries. At present, the compliance of projects is mainly analyzed and judged by the experience of regulatory compliance professionals. Not only is the efficiency low, but the requirements for regulatory compliance industry experience are also high. In addition, information acquisition is delayed, and the authenticity of information is difficult to verify. This has caused great obstacles to the timeliness and effectiveness of supervision. Therefore, an effective method is urgently needed to solve such problems. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a data processing method. One or more embodiments of this specification also relate to a data processing device, a computing device, and a computer-readable storage medium to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a data processing method is provided, including:

[0006] Sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed;

[0007] Predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval;

[0008] According to the prediction results, the audit information corresponding to the indicators of the items to be audited within the target time interval is determined.

[0009] Optionally, predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval includes:

[0010] The first time series data and the project events of the target project within the target time interval are input into a data prediction model, wherein the data prediction model predicts the indicator data of the indicator of the project to be reviewed within the target time interval based on the first time series data and the project events.

[0011] Optionally, the data prediction model is trained in the following manner:

[0012] Obtain historical indicator data of the indicators of the target project to be reviewed within the historical time interval;

[0013] Determine a target sampling time interval according to the indicator of the project to be reviewed, and sample the historical indicator data according to the target sampling time interval to generate second time series data corresponding to the indicator of the project to be reviewed;

[0014] Extracting target historical indicator data corresponding to the indicator of the project to be reviewed within a target historical time interval from the historical indicator data, and obtaining project events of the target project within the target historical time interval;

[0015] The second time series data and the project events are used as training samples, and the target historical indicator data are used as sample labels to train a data prediction model to obtain the data prediction model.

[0016] Optionally, the taking the second time series data and the project events as training samples, taking the target historical indicator data as sample labels, and training the data prediction model includes:

[0017] Inputting the second time series data, the project events and the target historical indicator data into a data prediction model;

[0018] Among them, the data prediction model predicts the indicator data of the project indicator to be reviewed within the target historical time interval based on the second time series data and the project event, and calculates the loss value between the predicted value and the target historical indicator data, and adjusts the model parameters of the data prediction model according to the loss value to train the data prediction model.

[0019] Optionally, the taking the second time series data and the project events as training samples, taking the target historical indicator data as sample labels, and training the data prediction model includes:

[0020] The target historical indicator data and the prediction results output by the data prediction model are used as model parameters, and a loss function is constructed based on the model parameters and the target prediction algorithm, wherein the prediction results are generated by the data prediction model predicting the indicator data of the to-be-audited project indicator within the target historical time interval according to the second time series data and the project event;

[0021] The data prediction model is iteratively trained based on the loss function until a training stop condition is reached, and the iterative training is stopped.

[0022] Optionally, constructing a loss function based on the model parameters and the target prediction algorithm includes:

[0023] The coefficient of the loss function is determined based on the number of historical indicator data included in the second time series data, and the loss function is constructed by taking the target historical indicator data and the prediction results output by the data prediction model as variables.

[0024] Optionally, sampling the indicator data of the indicator of the project to be reviewed in the target project according to a preset sampling interval to generate the first time series data corresponding to the indicator of the project to be reviewed includes:

[0025] The indicator data of the indicator of the project to be reviewed in the target project is sampled according to the target sampling time interval to generate first time series data corresponding to the indicator of the project to be reviewed.

[0026] Optionally, determining the audit information corresponding to the indicators of the items to be audited within the target time interval according to the prediction results includes:

[0027] Determine the historical audit information of the indicator of the project to be audited, and determine the indicator range corresponding to the indicator of the project to be audited in the historical audit information;

[0028] The adjustment range and adjustment direction corresponding to the indicator interval are determined according to the prediction result, and the indicator interval is adjusted based on the adjustment range and adjustment direction to generate audit information corresponding to the indicators of the items to be audited within the target time interval.

[0029] Optionally, the data processing method further includes:

[0030] Obtain the indicator value to be disclosed of the indicator of the project to be reviewed under the target project in the target time period;

[0031] Using the audit information to audit the indicator value to be disclosed, and generating a corresponding audit result;

[0032] When the audit is passed according to the audit result, the indicator value to be announced is announced.

[0033] According to a second aspect of an embodiment of this specification, there is provided a data processing device, including:

[0034] A sampling module is configured to sample the indicator data of the indicator of the project to be reviewed in the target project according to a preset sampling interval, and generate first time series data corresponding to the indicator of the project to be reviewed;

[0035] A prediction module, configured to predict the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval;

[0036] The determination module is configured to determine the audit information corresponding to the indicators of the items to be audited within the target time interval according to the prediction results.

[0037] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0038] Memory and processor;

[0039] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0040] Sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed;

[0041] Predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval;

[0042] According to the prediction results, the audit information corresponding to the indicators of the items to be audited within the target time interval is determined.

[0043] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the data processing method are implemented.

[0044] An embodiment of the present specification samples the indicator data of the project indicators to be audited in the target project according to a preset sampling interval to generate first time series data corresponding to the project indicators to be audited, predicts the indicator data corresponding to the project indicators to be audited in the target time interval based on the first time series data and the project events of the target project in the target time interval, and determines the audit information corresponding to the project indicators to be audited in the target time interval based on the prediction results.

[0045] The embodiments of this specification utilize the indicator data of the indicators of the project to be audited in the target project to predict in advance the indicator data of the project to be audited within a certain time interval in the future (target time interval), so as to determine the compliance detection rules (audit information) corresponding to the indicators of the project to be audited within the target time interval based on the prediction results, thereby facilitating the rationality of the compliance detection rules of the indicators of the project to be audited. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a processing flow chart of a data processing method provided by an embodiment of this specification;

[0047] Figure 2 is a processing flow chart of a data processing method provided by an embodiment of this specification;

[0048] Figure 3 is a schematic diagram of a data processing device provided by an embodiment of this specification;

[0049] Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0050] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0051] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0053] In this specification, a data processing method is provided. This specification also relates to a data processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0054] Figure 1 A processing flow chart of a data processing method provided according to an embodiment of the present specification is shown, including steps 102 to 106.

[0055] Step 102: sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed.

[0056] Specifically, the target project includes but is not limited to a transaction project, an information query project, an insurance project, a loan project, an investment project, a legal project, etc. The embodiments of this specification take the target project as a transaction project as an example for explanation. The specific implementation of the information query project, the insurance project, the loan project, the investment project, and the legal project is similar to the specific implementation of the transaction project. You can refer to the specific implementation of the transaction project and will not go into details here.

[0057] In addition, the indicators of the project to be reviewed, that is, the project indicators under the target project whose indicator data need to be reviewed; if the target project is a trading project, the indicators of the project to be reviewed include but are not limited to daily trading volume, monthly trading volume, annual trading volume, single transaction amount, etc.; the indicator data is the specific numerical value corresponding to the indicator of the project to be reviewed. For example, if the indicator of the project to be reviewed is daily trading volume, then its indicator data can be the sum of the trading volumes of the trading objects within one day, and the specific numerical form can be 200 or 300, etc.

[0058] In practical applications, the embodiments of this specification need to disclose the indicator data of the indicators of the projects to be reviewed in the target projects, that is, to publicize or publish them. Before disclosing the data, compliance detection needs to be performed on this part of the indicator data. Only when the detection passes, that is, it is determined that this part of the indicator data is compliant, can it be disclosed. However, the detection rules currently used for compliance detection of indicator data need to be manually configured, and then the indicator data are traversed and detected through the detection rules to determine whether there is indicator data that does not comply with the rules. Due to the limited information that can be obtained in the process of manually configuring the detection rules, the rationality of the configured detection rules needs to be improved.

[0059] Therefore, the embodiments of this specification utilize the indicator data of the indicators of the projects to be audited in the target project to predict in advance the indicator data of the indicators of the projects to be audited in a certain time period in the future, so as to generate detection rules (audit information) corresponding to the indicators of the projects to be audited in a certain time period in the future according to the prediction results, and use the detection rules as a supplement to the manually configured detection rules, thereby improving the rationality of the detection rules.

[0060] In practical applications, time series refers to a sequence formed by arranging the values ​​of a variable at different times in chronological order. Its time unit can be minutes, hours, days, weeks, months, seasons, years, etc.

[0061] Before predicting the indicator data, the indicator data of the target project's indicators for the project to be reviewed within a preset time period may be obtained first, and the aforementioned indicator data may be sampled at a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed.

[0062] Among them, the preset time period can be one month, one quarter, or one year before the current time, etc.; and the granularity of the indicator data of the indicator of the project to be reviewed within the preset time period and the preset sampling interval can be determined according to the granularity of the indicator data to be predicted. For example, if it is necessary to predict the trading volume of the transaction object on a certain day in the future, the granularity of the indicator data of the indicator of the project to be reviewed within the preset time period can be day, that is, the daily trading volume of the transaction object within one month, one quarter, or one year before the current time is obtained; then the obtained indicator data is sampled with days as the sampling interval to generate the first time series data.

[0063] If it is necessary to predict the transaction volume of the transaction object in a certain month in the future, the granularity of the indicator data of the project indicator to be reviewed within the preset time period can be monthly, that is, obtaining the monthly transaction volume of the transaction object in the months, quarters or years before the current time; then sample the obtained indicator data with months as the sampling interval to generate the first time series data.

[0064] Step 104 : predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval.

[0065] Specifically, as mentioned above, the embodiments of this specification need to utilize the indicator data of the indicators of the project to be audited in the target project to predict in advance the indicator data of the indicators of the project to be audited in a certain time interval in the future. Therefore, the target time interval represents the aforementioned certain time interval in the future, and, in actual applications, the target time interval or the certain time interval in the future can be a specific time point or a certain time period after the current time.

[0066] The project event refers to an event related to the target project within a target time interval. For example, when the target project is a transaction project, the project event may be a discount promotion or a full-discount activity.

[0067] In the case where the target project is a trading project, if there is no project event, the difference in the daily trading volume of the trading object may not be very large. In this case, the accuracy of the test result is still relatively high when the indicator data corresponding to the daily trading volume of the trading object is subjected to compliance test using artificially constructed standard test rules. However, when there is a project event within a certain time interval, the trading volume of the trading object within the time interval may increase significantly. In this case, the test result is likely to be non-compliant when the indicator data corresponding to the trading volume of the trading object within the time interval is subjected to compliance test using artificially constructed standard test rules, that is, there is a problem of inaccurate test result.

[0068] Therefore, after generating the first time series data, the embodiments of the present specification can also combine the project events of the target project within the target time interval and the first time series data to predict the indicator data corresponding to the indicators of the project to be reviewed within the target time interval, so as to adjust the artificially constructed standard detection rules according to the prediction results and generate audit information applicable to the indicators of the project to be reviewed within the target time interval.

[0069] During specific implementation, based on the first time series data and the project events of the target project within the target time interval, the indicator data corresponding to the indicator of the project to be reviewed within the target time interval is predicted. Specifically, the first time series data and the project events of the target project within the target time interval can be input into a data prediction model, wherein the data prediction model predicts the indicator data of the indicator of the project to be reviewed within the target time interval based on the first time series data and the project events.

[0070] Specifically, after generating the first time series data, the first time series data and the project events of the target project within the target time interval can be input into a data prediction model, and the data prediction model predicts the indicator data of the project indicators to be audited within the target time interval, that is, a certain time point or a certain time period after the current time, based on the first time series data and the project events, so as to adjust the artificially constructed standard detection rules according to the prediction results and generate audit information applicable to the project indicators to be audited within the target time interval.

[0071] The data prediction model is trained in the following way:

[0072] Obtain historical indicator data of the indicators of the target project to be reviewed within the historical time interval;

[0073] Determine a target sampling time interval according to the indicator of the project to be reviewed, and sample the historical indicator data according to the target sampling time interval to generate second time series data corresponding to the indicator of the project to be reviewed;

[0074] Extracting target historical indicator data corresponding to the indicator of the project to be reviewed within a target historical time interval from the historical indicator data, and obtaining project events of the target project within the target historical time interval;

[0075] The second time series data and the project events are used as training samples, and the target historical indicator data are used as sample labels to train a data prediction model to obtain the data prediction model.

[0076] Furthermore, the second time series data and the project events are used as training samples, and the target historical indicator data is used as sample labels to train the data prediction model, including:

[0077] Inputting the second time series data, the project events and the target historical indicator data into a data prediction model;

[0078] Among them, the data prediction model predicts the indicator data of the project indicator to be reviewed within the target historical time interval based on the second time series data and the project event, and calculates the loss value between the predicted value and the target historical indicator data, and adjusts the model parameters of the data prediction model according to the loss value to train the data prediction model.

[0079] Specifically, the data prediction model described in the embodiments of this specification is a time series prediction model, which can specifically use the indicator data of the historical time nodes in the time series data to predict the indicator data of the target time interval.

[0080] Therefore, when training the data prediction model, the historical indicator data of the indicators of the project to be reviewed in the target project within the historical time interval can be obtained first, and then the target sampling time interval can be determined according to the indicators of the project to be reviewed. For example, if the indicator of the project to be reviewed is the daily transaction volume, the target sampling time interval can be days, that is, it is collected once every day; if the indicator of the project to be reviewed is the monthly transaction volume, the target sampling time interval can be months, that is, it is collected once every month. After determining the target sampling time interval, the historical indicator data can be sampled according to the target sampling time interval to generate the second time series data corresponding to the indicator of the project to be reviewed.

[0081] The generation process of the second time series data is similar to the generation process of the first time series data, and will not be repeated here.

[0082] After generating the second time series data, the project events of the target project within the target historical time interval can be obtained, and the second time series data, the project events and the target historical indicator data corresponding to the project indicators to be reviewed within the target historical time interval can be input into the data prediction model to train the data prediction model.

[0083] The target historical time interval can be the time interval corresponding to the start and end time of the project event of the target project before the current time point. The target time interval can be the time interval corresponding to the start and end time of the project event of the target project after the current time point; for example, on November 11th every year, each e-commerce platform will have a product discount promotion, so November 11th 0:00 to 24:00 can be used as the target time interval of the historical year, or as the target time interval of the future year.

[0084] Since the trading volume of the transaction object, i.e. the commodity, will increase significantly on November 11 every year, in this case, in order to ensure the accuracy of the compliance test results obtained by using the compliance test rules to perform compliance testing on the indicator data corresponding to the daily trading volume on November 11, the commodity discount promotion activities on November 11 can be used as a project event, and combined with the project event and the first time series data, the indicator data of the daily trading volume on November 11 in a future year can be predicted, so as to determine the audit information based on the prediction results.

[0085] Therefore, in order to ensure that the data prediction model can predict the indicator data of the project indicators to be reviewed within the target time interval, the project event and the second time series data can be used as training samples, and the target historical indicator data corresponding to the project indicators to be reviewed within the target historical time interval can be used as labels to train the data prediction model.

[0086] In practical applications, project events and the second time series data can be used as training samples, and the target historical indicator data corresponding to the project indicator to be reviewed within the target historical time interval can be used as labels and input into a data prediction model. The data prediction model predicts the indicator data of the project indicator to be reviewed within the target historical time interval based on the second time series data and the project events, and calculates the loss value between the predicted value and the target historical indicator data. The model parameters of the data prediction model are adjusted according to the loss value to train the data prediction model, thereby ensuring the accuracy of the output results of the data prediction model obtained through training.

[0087] Alternatively, the second time series data and the project events are used as training samples, and the target historical indicator data is used as sample labels to train the data prediction model, which can also be achieved in the following manner:

[0088] The target historical indicator data and the prediction results output by the data prediction model are used as model parameters, and a loss function is constructed based on the model parameters and the target prediction algorithm, wherein the prediction results are generated by the data prediction model predicting the indicator data of the to-be-audited project indicator within the target historical time interval according to the second time series data and the project event;

[0089] The data prediction model is iteratively trained based on the loss function until a training stop condition is reached, and the iterative training is stopped.

[0090] Furthermore, a loss function is constructed according to the model parameters and the target prediction algorithm. Specifically, the coefficients of the loss function are determined based on the number of historical indicator data contained in the second time series data, and the target historical indicator data and the prediction results output by the data prediction model are used as variables to construct the loss function.

[0091] Specifically, the embodiment of this specification can construct a loss function based on an exponential smoothing prediction algorithm, and the exponential smoothing algorithm is based on α(1-α) i is the weight (0<α<1), (i=1,2,……,n) for the time series data {y1,y2……,y t}A prediction method that uses weighted average. t The weight is α, y t-1 The weight of y is α(1-α), t-2 The weight of is α(1-α) 2 , ..., and so on. The calculation formula is shown in formula (1).

[0092]

[0093] in, It indicates the forecast result of the indicator data of the project indicators expected to be audited in t+1; and They represent the exponential smoothing values ​​of the tth period and the t-1th period respectively; α is the smoothing coefficient.

[0094] The loss function constructed based on model parameters and exponential smoothing algorithm is shown in formula (2).

[0095]

[0096] Where n is the number of historical indicator data contained in the second time series data, and y t+1 Represents the real indicator data of period t+1, that is, the target historical indicator data corresponding to the indicator of the project to be reviewed within the target historical time interval. Since the target historical indicator data corresponding to the indicator of the project to be reviewed in different target historical time intervals are different, and the prediction results of the indicator data corresponding to the indicator of the project to be reviewed in different target historical time intervals are different, therefore, the embodiment of this specification can use the target historical indicator data and the prediction results output by the data prediction model as variables, and use the value after the number of historical indicator data contained in the second time series data is reduced by 1 as the coefficient of the loss function, so as to construct the loss function shown in formula (2).

[0097] In addition, the embodiments of this specification may also construct a loss function based on a moving average prediction algorithm.

[0098] After the loss function is constructed, the data prediction model to be trained can be iteratively trained based on the loss function until the training stop condition is reached, and the iterative training is stopped to generate the data prediction model.

[0099] In practical applications, after training the data prediction model, the model's output results can be used to optimize the model during the model application process. Specifically, the prediction results corresponding to the indicators of the projects to be reviewed within the target time interval output by the data prediction model can be compared with the actual indicator data corresponding to the indicators of the projects to be reviewed within the target time interval to calculate the loss value, and the data prediction model can be optimized based on the calculation results to improve the accuracy of the prediction results of the data prediction model.

[0100] In a specific implementation, the indicator data of the indicators of the project to be reviewed in the target project are sampled according to a preset sampling interval to generate the first time series data corresponding to the indicators of the project to be reviewed, including:

[0101] The indicator data of the indicator of the project to be reviewed in the target project is sampled according to the target sampling time interval to generate first time series data corresponding to the indicator of the project to be reviewed.

[0102] Specifically, during the training process of the data prediction model, the target sampling time interval is determined according to the indicators of the project to be audited, and the historical indicator data is sampled according to the target sampling time interval, so that the model is trained based on the sampling results to obtain the data prediction model. Therefore, during the application process of the data prediction model, the indicator data of the indicators of the project to be audited in the target project can still be sampled according to the target sampling time interval to generate the first time series data corresponding to the indicators of the project to be audited, so as to predict the indicator data of the project to be audited within the target time interval based on the first time series data and project events.

[0103] Sampling the indicator data of the indicators of the project to be reviewed in the target project according to the target sampling time interval to generate the first time series data, and then predicting based on the first time series data is conducive to ensuring the accuracy of the prediction result.

[0104] Step 106: Determine the audit information corresponding to the indicators of the items to be audited within the target time interval according to the prediction results.

[0105] In specific implementation, based on the prediction results, the audit information corresponding to the indicators of the items to be audited within the target time interval is determined, which can be achieved in the following ways:

[0106] Determine the historical audit information of the indicator of the project to be audited, and determine the indicator range corresponding to the indicator of the project to be audited in the historical audit information;

[0107] The adjustment range and adjustment direction corresponding to the indicator interval are determined according to the prediction result, and the indicator interval is adjusted based on the adjustment range and adjustment direction to generate audit information corresponding to the indicators of the items to be audited within the target time interval.

[0108] Specifically, the audit information includes compliance conditions of indicator data of the indicators of the project to be audited within a target time interval.

[0109] As mentioned above, the embodiment of this specification utilizes the indicator data of the indicators of the project to be audited in the target project to predict in advance the indicator data of the project to be audited in a certain time period in the future, so as to generate detection rules (audit information) corresponding to the indicators of the project to be audited in a certain time period in the future based on the prediction results, and use the detection rules as a supplement to the manually configured detection rules, thereby improving the rationality of the detection rules.

[0110] Therefore, the historical audit information can be manually configured standard detection rules, and the historical audit information also includes the compliance conditions of the indicator data of the indicators of the project to be audited within the target time interval, that is, the compliance fluctuation range of the indicator data (indicator interval); the adjustment direction of the indicator interval is to adjust the right boundary value of the indicator interval (compliance fluctuation range) upward / adjust the left boundary value of the indicator interval downward (increase the compliance fluctuation range), or adjust the right boundary value of the indicator interval downward / adjust the left boundary value of the indicator interval upward (reduce the compliance fluctuation range); and the adjustment range indicates the adjustment amplitude of the left boundary value or the right boundary value of the indicator interval.

[0111] After the data prediction model outputs the prediction results of the indicator data of the indicators of the projects to be audited within the target time interval, it can be considered that the compliance range of the indicator data of the indicators of the projects to be audited within the target time interval should be the same as or similar to the prediction results. Therefore, it can be determined based on the prediction results whether the indicator range of the indicators of the projects to be audited in the historical audit information should be increased or decreased (adjustment direction), and the adjustment range can be determined to adjust the indicator range based on the adjustment range and adjustment direction, and generate the audit information corresponding to the indicators of the projects to be audited within the target time interval.

[0112] The embodiment of this specification adjusts the manually constructed standard detection rules (historical audit information) according to the prediction results, generates audit information applicable to the indicators of the items to be audited within the target time interval, and uses this audit information as a supplement to the manually configured historical audit information, which is conducive to improving the rationality of the audit information.

[0113] Furthermore, after generating new audit information as a supplement, the audit information can be used to audit the indicator values ​​(indicator values ​​to be disclosed) of the indicators of the projects to be audited within the target time interval, which can be achieved in the following ways:

[0114] Obtain the indicator value to be disclosed of the indicator of the project to be reviewed under the target project in the target time period;

[0115] Using the audit information to audit the indicator value to be disclosed, and generating a corresponding audit result;

[0116] When the audit is passed according to the audit result, the indicator value to be announced is announced.

[0117] Specifically, the indicator values ​​to be announced are the specific values ​​or specific information of the indicators of the items to be audited that need to be announced. Before these values ​​or information are announced, they need to be audited using the audit information generated in the aforementioned manner to determine whether these values ​​or information are compliant. Moreover, if the audit is passed according to the audit results, that is, if the indicators are compliant, the indicator values ​​to be announced can be announced.

[0118] The embodiments of this specification utilize the adjusted audit information to conduct compliance self-inspection, which not only ensures the accuracy of the audit information obtained, but also ensures the credibility of the audit results, which is conducive to improving the service experience.

[0119] An embodiment of the present specification samples the indicator data of the project indicators to be audited in the target project according to a preset sampling interval to generate first time series data corresponding to the project indicators to be audited, predicts the indicator data corresponding to the project indicators to be audited in the target time interval based on the first time series data and the project events of the target project in the target time interval, and determines the audit information corresponding to the project indicators to be audited in the target time interval based on the prediction results.

[0120] The embodiments of this specification utilize the indicator data of the indicators of the project to be audited in the target project to predict in advance the indicator data of the project to be audited within a certain time interval in the future (target time interval), so as to determine the compliance detection rules (audit information) corresponding to the indicators of the project to be audited within the target time interval based on the prediction results, thereby facilitating the rationality of the compliance detection rules of the indicators of the project to be audited.

[0121] The following combination Figure 2 , taking the application of the data processing method provided in this specification in a transaction project as an example, the data processing method is further explained. Figure 2 A processing flow chart of a data processing method provided by an embodiment of the present specification is shown, and the specific steps include step 202 to step 224.

[0122] Step 202, obtaining historical indicator data of the indicators of the items to be reviewed in the transaction items within the historical time interval.

[0123] Step 204 , determining a target sampling time interval according to the indicator of the project to be reviewed, and sampling the historical indicator data according to the target sampling time interval to generate first time series data corresponding to the indicator of the project to be reviewed.

[0124] Step 206: extract the target historical indicator data corresponding to the to-be-audited project indicator within the target historical time interval from the historical indicator data, and obtain the project event of the transaction project within the target historical time interval.

[0125] Step 208, determining the coefficient of the loss function based on the number of historical indicator data included in the first time series data, and constructing the loss function by taking the target historical indicator data and the prediction result output by the data prediction model as variables.

[0126] The prediction result is generated by the data prediction model based on the first time series data and the project event, by predicting the indicator data of the to-be-audited project indicator within the target historical time interval.

[0127] Step 210: iteratively train the data prediction model based on the loss function until a training stop condition is reached, stop iterative training, and generate the data prediction model.

[0128] Step 212: sampling the indicator data of the indicator of the item to be reviewed in the transaction item according to the target sampling time interval, and generating second time series data corresponding to the indicator of the item to be reviewed.

[0129] Step 214: predict the indicator data corresponding to the indicator of the item to be reviewed within the target time interval according to the second time series data and the item events of the transaction item within the target time interval.

[0130] Step 216: input the second time series data and the project events of the transaction project within the target time interval into the data prediction model for prediction.

[0131] The data prediction model predicts the indicator data of the project indicator to be reviewed within the target time interval according to the second time series data and the project event.

[0132] Step 218: Determine the audit information corresponding to the indicators of the items to be audited within the target time interval according to the prediction results.

[0133] Step 220, obtaining the indicator value to be disclosed of the indicator of the item to be reviewed under the transaction item in the target time interval.

[0134] Step 222: Use the audit information to audit the indicator value to be disclosed and generate a corresponding audit result.

[0135] Step 224, when it is determined that the audit is passed according to the audit result, the indicator value to be announced is announced.

[0136] The embodiments of this specification utilize the indicator data of the indicators of the items to be audited in the transaction project to predict in advance the indicator data of the indicators of the items to be audited within a certain time interval in the future (target time interval), so as to determine the compliance detection rules (audit information) corresponding to the indicators of the items to be audited within the target time interval according to the prediction results, thereby facilitating the rationality of the compliance detection rules of the indicators of the items to be audited.

[0137] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 3FIG. 1 is a schematic diagram of a data processing device provided by an embodiment of the present specification. Figure 3 As shown, the device comprises:

[0138] The sampling module 302 is configured to sample the indicator data of the indicator of the project to be reviewed in the target project according to a preset sampling interval, and generate first time series data corresponding to the indicator of the project to be reviewed;

[0139] The prediction module 304 is configured to predict the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval;

[0140] The determination module 306 is configured to determine the audit information corresponding to the indicators of the items to be audited within the target time interval according to the prediction results.

[0141] Optionally, the prediction module 304 is further configured to:

[0142] The first time series data and the project events of the target project within the target time interval are input into a data prediction model, wherein the data prediction model predicts the indicator data of the indicator of the project to be reviewed within the target time interval based on the first time series data and the project events.

[0143] Optionally, the data processing device further includes:

[0144] An acquisition module is configured to acquire historical indicator data of the indicators of the project to be reviewed in the target project within a historical time interval;

[0145] A generating module is configured to determine a target sampling time interval according to the indicator of the project to be reviewed, and to sample the historical indicator data according to the target sampling time interval to generate second time series data corresponding to the indicator of the project to be reviewed;

[0146] An extraction module is configured to extract target historical indicator data corresponding to the indicator of the project to be reviewed within a target historical time interval from the historical indicator data, and obtain project events of the target project within the target historical time interval;

[0147] The training module is configured to use the second time series data and the project events as training samples and the target historical indicator data as sample labels to train the data prediction model to obtain the data prediction model.

[0148] Optionally, the training module is further configured to:

[0149] Inputting the second time series data, the project events and the target historical indicator data into a data prediction model;

[0150] Among them, the data prediction model predicts the indicator data of the project indicator to be reviewed within the target historical time interval based on the second time series data and the project event, and calculates the loss value between the predicted value and the target historical indicator data, and adjusts the model parameters of the data prediction model according to the loss value to train the data prediction model.

[0151] Optionally, the training module is further configured to:

[0152] A construction submodule is configured to use the target historical indicator data and the prediction results output by the data prediction model as model parameters, and to construct a loss function based on the model parameters and the target prediction algorithm, wherein the prediction results are generated by the data prediction model predicting the indicator data of the to-be-audited project indicator within the target historical time interval according to the second time series data and the project event;

[0153] The training submodule is configured to iteratively train the data prediction model based on the loss function until a training stop condition is reached and the iterative training is stopped.

[0154] Optionally, the construction submodule is further configured as follows:

[0155] The coefficient of the loss function is determined based on the number of historical indicator data included in the second time series data, and the loss function is constructed by taking the target historical indicator data and the prediction results output by the data prediction model as variables.

[0156] Optionally, the sampling module 302 is further configured to:

[0157] The indicator data of the indicator of the project to be reviewed in the target project is sampled according to the target sampling time interval to generate first time series data corresponding to the indicator of the project to be reviewed.

[0158] Optionally, the determining module 306 is further configured to:

[0159] Determine the historical audit information of the indicator of the project to be audited, and determine the indicator range corresponding to the indicator of the project to be audited in the historical audit information;

[0160] The adjustment range and adjustment direction corresponding to the indicator interval are determined according to the prediction result, and the indicator interval is adjusted based on the adjustment range and adjustment direction to generate audit information corresponding to the indicators of the items to be audited within the target time interval.

[0161] Optionally, the data processing device further includes a disclosure processing module configured to:

[0162] Obtain the indicator value to be disclosed of the indicator of the project to be reviewed under the target project in the target time period;

[0163] Using the audit information to audit the indicator value to be disclosed, and generating a corresponding audit result;

[0164] When the audit is passed according to the audit result, the indicator value to be announced is announced.

[0165] The above is a schematic scheme of a data processing device of this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the data processing device can be referred to the description of the technical scheme of the above data processing method.

[0166] Figure 4 The block diagram of a computing device 400 according to an embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.

[0167] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0168] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0169] Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.

[0170] The memory 410 is used to store computer executable instructions, and the processor 420 is used to execute the following computer executable instructions:

[0171] Sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed;

[0172] Predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval according to the first time series data and the project events of the target project within the target time interval;

[0173] According to the prediction results, the audit information corresponding to the indicators of the items to be audited within the target time interval is determined.

[0174] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above data processing method.

[0175] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of the data processing method when executed by a processor.

[0176] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above data processing method.

[0177] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0178] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0179] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some 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 preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0180] 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.

[0181] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, comprising: Sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed; Based on the first time series data and the project events of the target project in the target time interval, the indicator data corresponding to the indicator of the project to be reviewed in the target time interval is predicted, wherein the prediction is performed by a data prediction model, and the data prediction model is obtained by training the second time series data and the project events of the target project in the target historical time interval as training samples and the target historical indicator data as sample labels, the second time series data determines the target sampling time interval according to the indicator of the project to be reviewed, and samples the historical indicator data according to the target sampling time interval; Based on the prediction results, the audit information corresponding to the indicators of the project to be audited within the target time interval is determined, wherein the audit information corresponding to the indicators of the project to be audited within the target time interval is determined based on the prediction results, including: determining the historical audit information of the indicators of the project to be audited, and determining the indicator interval corresponding to the indicators of the project to be audited in the historical audit information; determining the adjustment range and adjustment direction corresponding to the indicator interval based on the prediction results, and adjusting the indicator interval based on the adjustment range and adjustment direction to generate the audit information corresponding to the indicators of the project to be audited within the target time interval.

2. The data processing method according to claim 1, wherein the step of predicting the indicator data corresponding to the indicator of the project to be reviewed within the target time interval based on the first time series data and the project events of the target project within the target time interval comprises: The first time series data and the project events of the target project within the target time interval are input into a data prediction model, wherein the data prediction model predicts the indicator data of the indicator of the project to be reviewed within the target time interval based on the first time series data and the project events.

3. The data processing method according to claim 2, wherein the data prediction model is trained in the following manner: Obtain historical indicator data of the indicators of the target project to be reviewed within the historical time interval; Determine a target sampling time interval according to the indicator of the project to be reviewed, and sample the historical indicator data according to the target sampling time interval to generate second time series data corresponding to the indicator of the project to be reviewed; Extracting target historical indicator data corresponding to the indicator of the project to be reviewed within a target historical time interval from the historical indicator data, and obtaining project events of the target project within the target historical time interval; The second time series data and the project events are used as training samples, and the target historical indicator data are used as sample labels to train a data prediction model to obtain the data prediction model.

4. The data processing method according to claim 3, wherein the second time series data and the project events are used as training samples, and the target historical indicator data are used as sample labels to train the data prediction model, comprising: Inputting the second time series data, the project events and the target historical indicator data into a data prediction model; Among them, the data prediction model predicts the indicator data of the project indicator to be reviewed within the target historical time interval based on the second time series data and the project event, and calculates the loss value between the predicted value and the target historical indicator data, and adjusts the model parameters of the data prediction model according to the loss value to train the data prediction model.

5. The data processing method according to claim 3, wherein the second time series data and the project events are used as training samples, and the target historical indicator data are used as sample labels to train the data prediction model, comprising: The target historical indicator data and the prediction results output by the data prediction model are used as model parameters, and a loss function is constructed based on the model parameters and the target prediction algorithm, wherein the prediction results are generated by the data prediction model predicting the indicator data of the to-be-audited project indicator within the target historical time interval according to the second time series data and the project event; The data prediction model is iteratively trained based on the loss function until a training stop condition is reached, and the iterative training is stopped.

6. The data processing method according to claim 5, wherein the loss function is constructed based on the model parameters and the target prediction algorithm, comprising: The coefficient of the loss function is determined based on the number of historical indicator data included in the second time series data, and the loss function is constructed by taking the target historical indicator data and the prediction results output by the data prediction model as variables.

7. The data processing method according to claim 1, further comprising: Obtain the indicator value to be disclosed of the indicator of the project to be reviewed under the target project in the target time period; Using the audit information to audit the indicator value to be disclosed, and generating a corresponding audit result; When the audit is passed according to the audit result, the indicator value to be announced is announced.

8. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Sampling the indicator data of the indicators of the project to be reviewed in the target project according to a preset sampling interval to generate first time series data corresponding to the indicators of the project to be reviewed; Based on the first time series data and the project events of the target project in the target time interval, the indicator data corresponding to the indicator of the project to be reviewed in the target time interval is predicted, wherein the prediction is performed by a data prediction model, and the data prediction model is obtained by training the second time series data and the project events of the target project in the target historical time interval as training samples and the target historical indicator data as sample labels, the second time series data determines the target sampling time interval according to the indicator of the project to be reviewed, and samples the historical indicator data according to the target sampling time interval; Based on the prediction results, the audit information corresponding to the indicators of the project to be audited within the target time interval is determined, wherein the audit information corresponding to the indicators of the project to be audited within the target time interval is determined based on the prediction results, including: determining the historical audit information of the indicators of the project to be audited, and determining the indicator interval corresponding to the indicators of the project to be audited in the historical audit information; determining the adjustment range and adjustment direction corresponding to the indicator interval based on the prediction results, and adjusting the indicator interval based on the adjustment range and adjustment direction to generate the audit information corresponding to the indicators of the project to be audited within the target time interval.

9. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the data processing method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The method comprises computer instructions which, when executed by a processor, implement the steps of the data processing method according to any one of claims 1 to 7.

Images