A channel data inspection and auditing method and system

Abstract

The present invention provides a channel data inspection and audit method and system, wherein the method includes: obtaining channel data to be inspected and audited; parsing the channel data, determining multiple key indicators and constructing a key indicator set corresponding to the channel data; inspecting the key indicator set based on a preset inspection indicator set; obtaining the inspection rules corresponding to each key indicator; and inspecting the key indicators based on the inspection rules. The channel data inspection and audit method and system of the present invention realize the inspection and audit of channel data, ensure the accuracy and quality of channel data, and further ensure the accuracy of channel analysis results.

Description

Technical Field

[0001] The present invention relates to the technical field of data auditing, and in particular to a channel data auditing method and system. Background Art

[0002] At present, channels are the loops and channels that link products and users. They present products or services to potential customers and collect their money. Channels are sales channels, that is, the channels through which goods reach consumers. Channel data refers to various types of data generated during the channel management process, such as the purchase, sales and inventory data of distributors. Channel analysis technology is one of the important applications of big data technology. In order to ensure the accuracy of channel analysis results, the accuracy and quality of channel data are particularly important. Therefore, the inspection and audit of channel data is a technical problem that needs to be solved urgently. Summary of the invention

[0003] One of the purposes of the present invention is to provide a channel data inspection and auditing method and system to realize the inspection and auditing of channel data, ensure the accuracy and quality of channel data, and further ensure the accuracy of channel analysis results.

[0004] An embodiment of the present invention provides a channel data inspection and auditing method, comprising:

[0005] Obtain channel data to be audited;

[0006] Analyze channel data, identify multiple key indicators and build a key indicator set corresponding to the channel data;

[0007] Audit the key indicator set based on the preset audit indicator set;

[0008] Obtain the audit rules corresponding to each key indicator;

[0009] Audit key indicators based on audit rules.

[0010] Preferably, auditing the key indicator set based on the preset audit indicator set includes:

[0011] Associate each key indicator in the audit indicator set with each key in the key indicator set one by one;

[0012] When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit passes, otherwise it fails;

[0013] Among them, each key indicator in the audit indicator set is associated with each key in the key indicator set one by one; including:

[0014] Quantify each key indicator in the audit indicator set based on a preset quantification template, and determine a first parameter value corresponding to each key indicator in the audit indicator set;

[0015] Quantify each key indicator in the key indicator set based on the quantification template, and determine a second parameter value corresponding to each key indicator in the key indicator set;

[0016] Extract key indicators in the key indicator set in sequence, and calculate the difference between the first parameter value corresponding to the key indicator in the extracted key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set;

[0017] When the difference is less than or equal to the preset association threshold and the minimum value among the calculated differences is obtained, the key indicators in the corresponding key indicator set are associated with the key indicators in the corresponding audit indicator set.

[0018] Preferably, key indicators are audited based on audit rules, including:

[0019] Analyze audit rules and determine the permissible range of values ​​corresponding to key indicators;

[0020] When the value corresponding to the key indicator is within the allowable range, the audit is passed; otherwise, it fails;

[0021] and / or,

[0022] Get the last uploaded channel data of the object corresponding to the channel data to be audited;

[0023] Determine the numerical difference between the key indicator in the last uploaded channel data and the corresponding key indicator in the channel data uploaded this time;

[0024] When the numerical difference is within the preset difference range, the audit is passed; otherwise, it fails;

[0025] The allowable range of the value corresponding to the key indicator is determined by the following steps:

[0026] Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited;

[0027] Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator;

[0028] Perform outlier elimination processing on the data in the data set to obtain the processed data set;

[0029] Determine the maximum and minimum values ​​of the processed data set;

[0030] Based on the maximum and minimum values, the permissible range is determined.

[0031] Preferably, the channel data inspection and audit method further includes:

[0032] Obtain the verification data associated with the channel data to be audited;

[0033] Verify the verification data; if the verification is successful, the audit is passed; otherwise, it fails;

[0034] The verification data includes one or more combinations of the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, and the identity information of the uploading person when uploading.

[0035] Preferably, the channel data inspection and audit method further includes:

[0036] Parse the channel data to be audited and determine multiple third parties that interact with the objects corresponding to the channel data to be audited;

[0037] Obtain channel data uploaded by third parties;

[0038] Audit channel data to be audited based on channel data uploaded by third parties;

[0039] When using channel data uploaded by a third party to audit channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows:

[0040] Obtain historical audit results records from third parties;

[0041] Inputting historical audit result records into a preset neural network model to determine a first credit value;

[0042] Get the third party liability values ​​of other preset number of third parties on the platform;

[0043] Get the effectiveness coefficients of other third parties on the platform;

[0044] Determining a second credit value of the third party based on the effectiveness coefficient and the commitment value;

[0045] Determining the credibility of the third party based on the first credibility value and the second credibility value;

[0046] When the credibility is greater than the preset credibility threshold, the channel data uploaded by the third party is used to audit the channel data to be audited;

[0047] When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table;

[0048] When channel data uploaded by a third party is used to audit channel data, and the audit result is abnormal, but the channel data to be audited is subsequently manually determined to be normal, the effectiveness coefficients of all other third parties on the platform are adjusted downward based on the preset effectiveness coefficient step adjustment table.

[0049] The present invention also provides a channel data inspection and auditing system, comprising:

[0050] The first acquisition module is used to obtain channel data to be audited;

[0051] A first parsing module, used to parse the channel data, determine multiple key indicators and construct a key indicator set corresponding to the channel data;

[0052] A first audit module, used to audit the key indicator set based on a preset audit indicator set;

[0053] The second acquisition module is used to obtain the audit rules corresponding to each key indicator;

[0054] The second audit module is used to audit key indicators based on audit rules.

[0055] Preferably, the first audit module performs the following operations:

[0056] Associate each key indicator in the audit indicator set with each key in the key indicator set one by one;

[0057] When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit passes, otherwise it fails;

[0058] Among them, each key indicator in the audit indicator set is associated with each key in the key indicator set one by one; including:

[0059] Quantify each key indicator in the audit indicator set based on a preset quantification template, and determine a first parameter value corresponding to each key indicator in the audit indicator set;

[0060] Quantify each key indicator in the key indicator set based on the quantification template, and determine a second parameter value corresponding to each key indicator in the key indicator set;

[0061] Extract key indicators in the key indicator set in sequence, and calculate the difference between the first parameter value corresponding to the key indicator in the extracted key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set;

[0062] When the difference is less than or equal to the preset association threshold and the minimum value among the calculated differences is obtained, the key indicators in the corresponding key indicator set are associated with the key indicators in the corresponding audit indicator set.

[0063] Preferably, the second audit module performs the following operations:

[0064] Analyze audit rules and determine the permissible range of values ​​corresponding to key indicators;

[0065] When the value corresponding to the key indicator is within the allowable range, the audit is passed; otherwise, it fails;

[0066] and / or,

[0067] Get the last uploaded channel data of the object corresponding to the channel data to be audited;

[0068] Determine the numerical difference between the key indicator in the last uploaded channel data and the corresponding key indicator in the channel data uploaded this time;

[0069] When the numerical difference is within the preset difference range, the audit is passed; otherwise, it fails;

[0070] The allowable range of the value corresponding to the key indicator is determined by the following steps:

[0071] Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited;

[0072] Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator;

[0073] Perform outlier elimination processing on the data in the data set to obtain the processed data set;

[0074] Determine the maximum and minimum values ​​of the processed data set;

[0075] Based on the maximum and minimum values, the permissible range is determined.

[0076] Preferably, the channel data inspection and audit system further includes:

[0077] The third audit module is used to obtain the verification data associated with the channel data to be audited;

[0078] And verify the verification data; if the verification passes, the audit is passed; otherwise, it fails;

[0079] The verification data includes one or more combinations of the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, and the identity information of the uploading person when uploading.

[0080] Preferably, the channel data inspection and audit system further includes:

[0081] The fourth audit module is used to analyze the channel data to be audited, determine multiple third parties that interact with the object corresponding to the channel data to be audited; obtain the channel data uploaded by the third party; and audit the channel data to be audited based on the channel data uploaded by the third party;

[0082] When using channel data uploaded by a third party to audit channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows:

[0083] Obtain historical audit results records from third parties;

[0084] Inputting historical audit result records into a preset neural network model to determine a first credit value;

[0085] Get the third party liability values ​​of other preset number of third parties on the platform;

[0086] Get the effectiveness coefficients of other third parties on the platform;

[0087] Determining a second credit value of the third party based on the effectiveness coefficient and the commitment value;

[0088] Determining the credibility of the third party based on the first credibility value and the second credibility value;

[0089] When the credibility is greater than the preset credibility threshold, the channel data uploaded by the third party is used to audit the channel data to be audited;

[0090] When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table;

[0091] When channel data uploaded by a third party is used to audit channel data, and the audit result is abnormal, but the channel data to be audited is subsequently manually determined to be normal, the effectiveness coefficients of all other third parties on the platform are adjusted downward based on the preset effectiveness coefficient step adjustment table.

[0092] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0093] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0095] Figure 1 It is a schematic diagram of a channel data inspection and auditing method in an embodiment of the present invention. DETAILED DESCRIPTION

[0096] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0097] The present invention provides a method for checking and auditing channel data. Figure 1 As shown, including:

[0098] Step S1: Obtain channel data to be audited;

[0099] Step S2: parsing the channel data, determining multiple key indicators and constructing a key indicator set corresponding to the channel data;

[0100] Step S3: Auditing the key indicator set based on the preset audit indicator set;

[0101] Step S4: Obtain the audit rules corresponding to each key indicator;

[0102] Step S5: Audit key indicators based on audit rules.

[0103] The working principle and beneficial effects of the above technical solution are:

[0104] Before processing the channel data, it is necessary to conduct an audit on the channel data to find out whether the channel data is abnormal. If it is abnormal, it should be eliminated or manually confirmed to ensure the accuracy of subsequent channel data processing and analysis. The audit of channel data mainly includes the audit of the composition of channel data and the accuracy of each component. The preset audit indicator set is used to audit the key indicator set representing the composition of channel data. The audit indicator set is constructed based on the upload of the channel data uploader, for example: the distributor's purchase, sales and inventory data, mainly includes the key indicators of the purchase quantity, sales quantity and inventory data of each commodity; corresponding The preset audit indicator set of the distributor includes: the number of purchases of commodity A, the number of sales of commodity A, the inventory of commodity A, the number of purchases of commodity B, the number of sales of commodity B, the inventory of commodity B...; by auditing the key indicator set constructed by the channel data through the preset audit indicator set, the integrity of the channel data can be confirmed; the refined audit of each key indicator is achieved through the audit rules corresponding to each key indicator; for example, the preset maximum inventory value of commodity A is 1000, when the inventory of commodity A in the channel data is 1100, the data is determined to be abnormal and the data is transferred to subsequent manual confirmation; after confirmation, the channel data can enter the data analysis stage.

[0105] The channel data inspection and auditing method of the present invention realizes the inspection and auditing of channel data, ensures the accuracy and quality of channel data, and further ensures the accuracy of channel analysis results.

[0106] In one embodiment, auditing the key indicator set based on the preset audit indicator set includes:

[0107] Associate each key indicator in the audit indicator set with each key in the key indicator set one by one;

[0108] When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit passes, otherwise it fails;

[0109] Among them, each key indicator in the audit indicator set is associated with each key in the key indicator set one by one; including:

[0110] Quantify each key indicator in the audit indicator set based on a preset quantification template, and determine a first parameter value corresponding to each key indicator in the audit indicator set;

[0111] Quantify each key indicator in the key indicator set based on the quantification template, and determine a second parameter value corresponding to each key indicator in the key indicator set;

[0112] Extract key indicators in the key indicator set in sequence, and calculate the difference between the first parameter value corresponding to the key indicator in the extracted key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set;

[0113] When the difference is less than or equal to the preset association threshold and the minimum value among the calculated differences is obtained, the key indicators in the corresponding key indicator set are associated with the key indicators in the corresponding audit indicator set.

[0114] The working principle and beneficial effects of the above technical solution are:

[0115] The key indicator set is audited based on the preset audit indicator set, mainly to determine whether each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set; when associating, a quantitative template is used to achieve quantification to facilitate the association of key indicators; the quantitative template is a tree template; for example: the dealer's purchase, sales and inventory data, the corresponding quantitative template is a two-level tree template, the first level is the purchase number, sales number, and inventory; the second level corresponds to each commodity, commodity A, commodity B; in this way, the corresponding purchase number of the quantitative template is quantified as 100; the corresponding sales number is quantified as 200, and the corresponding inventory is quantified as 300; the corresponding quantification of commodity A is 0001; the corresponding quantification of commodity B is 0002; the key indicator: the inventory of commodity A is quantified as 0001300.

[0116] In one embodiment, auditing key indicators based on audit rules includes:

[0117] Analyze audit rules and determine the permissible range of values ​​corresponding to key indicators;

[0118] When the value corresponding to the key indicator is within the allowable range, the audit is passed; otherwise, it fails;

[0119] and / or,

[0120] Get the last uploaded channel data of the object corresponding to the channel data to be audited;

[0121] Determine the numerical difference between the key indicator in the last uploaded channel data and the corresponding key indicator in the channel data uploaded this time;

[0122] When the numerical difference is within the preset difference range, the audit is passed; otherwise, it fails;

[0123] The allowable range of the value corresponding to the key indicator is determined by the following steps:

[0124] Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited;

[0125] Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator;

[0126] Perform outlier elimination processing on the data in the data set to obtain the processed data set;

[0127] Determine the maximum and minimum values ​​of the processed data set;

[0128] Based on the maximum and minimum values, the permissible range is determined.

[0129] The working principle and beneficial effects of the above technical solution are:

[0130] The audit rules mainly include: auditing based on the allowable range of key indicators, and data beyond the allowable range is abnormal; the allowable range can be obtained by analyzing historical channel data, that is, a distributor's purchase data for commodity A has always been between 100 and 200. When the purchase data of commodity A in this channel data is 210, it can be determined to be abnormal and needs to be verified. It can also be determined by the change amount, that is, the last purchase volume was 150, and the current purchase volume was 230. The preset difference threshold is 30, so the channel data this time is abnormal and needs to be verified. The difference threshold can be pre-set, or it can be input into the preset analysis model for analysis based on the specific situation of the object corresponding to the channel data to be audited.

[0131] In one embodiment, the channel data audit method further includes:

[0132] Obtain the verification data associated with the channel data to be audited;

[0133] Verify the verification data; if the verification is successful, the audit is passed; otherwise, it fails;

[0134] The verification data includes one or more combinations of the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, and the identity information of the uploading person when uploading.

[0135] The working principle and beneficial effects of the above technical solution are:

[0136] When uploading channel data, the associated verification data is uploaded synchronously to verify the validity of the uploading method; mainly starting from the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, the identity information of the uploading personnel when uploading, etc.; among which, the environmental parameter data of the area where the terminal device is located when uploading, for example, can be the weather conditions, sunny, cloudy, etc.; thereby ensuring the accuracy of channel data acquisition and preventing the occurrence of human fabrication.

[0137] In one embodiment, the channel data audit method further includes:

[0138] Parse the channel data to be audited and determine multiple third parties that interact with the objects corresponding to the channel data to be audited;

[0139] Obtain channel data uploaded by third parties;

[0140] Audit channel data to be audited based on channel data uploaded by third parties;

[0141] When using channel data uploaded by a third party to audit channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows:

[0142] Obtain historical audit results records from third parties;

[0143] Inputting historical audit result records into a preset neural network model to determine a first credit value;

[0144] Get the third party liability values ​​of other preset number of third parties on the platform;

[0145] Get the effectiveness coefficients of other third parties on the platform;

[0146] Determining a second credit value of the third party based on the effectiveness coefficient and the commitment value;

[0147] Determining the credibility of the third party based on the first credibility value and the second credibility value;

[0148] When the credibility is greater than the preset credibility threshold, the channel data uploaded by the third party is used to audit the channel data to be audited;

[0149] When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table;

[0150] When channel data uploaded by a third party is used to audit channel data, and the audit result is abnormal, but the channel data to be audited is subsequently manually determined to be normal, the effectiveness coefficients of all other third parties on the platform are adjusted downward based on the preset effectiveness coefficient step adjustment table.

[0151] The working principle and beneficial effects of the above technical solution are:

[0152] The audit of channel data for inspection and audit can also be conducted based on channel data uploaded by a third party, that is, the purchase data of distributor A corresponds to the shipment data of factory B; when using third-party data for inspection, it is necessary to determine the credibility of the third party to ensure the credibility of the third-party data; the credibility is mainly determined by the first credit value reflecting the third party itself and the second credit value reflecting the trust of other third parties in the third party; based on the first credit value and the second credit value, the credibility of the third party can be determined by weighted sum calculation, that is, the first credit value and the second credit value are multiplied by the corresponding preset coefficients and then summed. Among them, the first credit value uses the neural network model method to analyze the historical inspection results of the channel data uploaded by the third party; when there is no abnormality in the historical inspection results, the first credit value is the full value, preset to 100; when the number of abnormalities in the historical inspection results increases, it gradually decreases. The second credit value is calculated based on the effective coefficient and the bearing value, and the calculation formula is as follows: Among them, X2 is the second credit value, A i is the commitment value of the i-th other third party; α i is the effective coefficient of the ith other third party; the commitment value is allocated according to the audit results of the third party, for example, 20 is allocated for an audit without abnormality, and 30 is deducted for an audit with abnormality; the effective coefficient is the initial value allocated by the system to the third party; the final value is adjusted based on the commitment result; in addition, the effective coefficient is reversely adjusted according to the manual review results of the audit results to ensure the accuracy of the subsequent third-party credibility confirmation. When adjusting, it is adjusted based on the effective coefficient ladder adjustment table, which is mainly determined based on the historical adjustment records of the third party. For example, the last time was a downward adjustment, and this time was an upward adjustment, and at this time it corresponds to an adjustment coefficient, which is a 1st upward adjustment coefficient; the last time was an upward adjustment, and this time was an upward adjustment, and at this time it corresponds to an adjustment coefficient, which is a 2nd upward adjustment coefficient; the first upward adjustment coefficient is less than the second upward adjustment coefficient; the first upward adjustment coefficient is less than the first downward adjustment coefficient; the same downward adjustment coefficient is greater than the same upward adjustment coefficient; the higher upward adjustment coefficient is greater than the lower upward adjustment coefficient; the higher downward adjustment coefficient is greater than the lower downward adjustment coefficient.

[0153] The present invention also provides a channel data inspection and auditing system, comprising:

[0154] The first acquisition module is used to obtain channel data to be audited;

[0155] A first parsing module, used to parse the channel data, determine multiple key indicators and construct a key indicator set corresponding to the channel data;

[0156] A first audit module, used to audit the key indicator set based on a preset audit indicator set;

[0157] The second acquisition module is used to obtain the audit rules corresponding to each key indicator;

[0158] The second audit module is used to audit key indicators based on audit rules.

[0159] The working principle and beneficial effects of the above technical solution are:

[0160] Before processing the channel data, it is necessary to conduct an audit on the channel data to find out whether the channel data is abnormal. If it is abnormal, it should be eliminated or manually confirmed to ensure the accuracy of subsequent channel data processing and analysis. The audit of channel data mainly includes the audit of the composition of channel data and the accuracy of each component. The preset audit indicator set is used to audit the key indicator set representing the composition of channel data. The audit indicator set is constructed based on the upload of the channel data uploader, for example: the distributor's purchase, sales and inventory data, mainly includes the key indicators of the purchase quantity, sales quantity and inventory data of each commodity; corresponding The preset audit indicator set of the distributor includes: the number of purchases of commodity A, the number of sales of commodity A, the inventory of commodity A, the number of purchases of commodity B, the number of sales of commodity B, the inventory of commodity B...; by auditing the key indicator set constructed by the channel data through the preset audit indicator set, the integrity of the channel data can be confirmed; the refined audit of each key indicator is achieved through the audit rules corresponding to each key indicator; for example, the preset maximum inventory value of commodity A is 1000, when the inventory of commodity A in the channel data is 1100, the data is determined to be abnormal and the data is transferred to subsequent manual confirmation; after confirmation, the channel data can enter the data analysis stage.

[0161] The channel data inspection and auditing system of the present invention realizes the inspection and auditing of channel data, ensures the accuracy and quality of channel data, and further ensures the accuracy of channel analysis results.

[0162] In one embodiment, the first audit module performs the following operations:

[0163] Associate each key indicator in the audit indicator set with each key in the key indicator set one by one;

[0164] When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit passes, otherwise it fails;

[0165] Among them, each key indicator in the audit indicator set is associated with each key in the key indicator set one by one; including:

[0166] Quantify each key indicator in the audit indicator set based on a preset quantification template, and determine a first parameter value corresponding to each key indicator in the audit indicator set;

[0167] Quantify each key indicator in the key indicator set based on the quantification template, and determine a second parameter value corresponding to each key indicator in the key indicator set;

[0168] Extract key indicators in the key indicator set in sequence, and calculate the difference between the first parameter value corresponding to the key indicator in the extracted key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set;

[0169] When the difference is less than or equal to the preset association threshold and the minimum value among the calculated differences is obtained, the key indicators in the corresponding key indicator set are associated with the key indicators in the corresponding audit indicator set.

[0170] The working principle and beneficial effects of the above technical solution are:

[0171] The key indicator set is audited based on the preset audit indicator set, mainly to determine whether each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set; when associating, a quantitative template is used to achieve quantification to facilitate the association of key indicators; the quantitative template is a tree template; for example: the dealer's purchase, sales and inventory data, the corresponding quantitative template is a two-level tree template, the first level is the purchase number, sales number, and inventory; the second level corresponds to each commodity, commodity A, commodity B; in this way, the corresponding purchase number of the quantitative template is quantified as 100; the corresponding sales number is quantified as 200, and the corresponding inventory is quantified as 300; the corresponding quantification of commodity A is 0001; the corresponding quantification of commodity B is 0002; the key indicator: the inventory of commodity A is quantified as 0001300.

[0172] In one embodiment, the second audit module performs the following operations:

[0173] Analyze audit rules and determine the permissible range of values ​​corresponding to key indicators;

[0174] When the value corresponding to the key indicator is within the allowable range, the audit is passed; otherwise, it fails;

[0175] and / or,

[0176] Get the last uploaded channel data of the object corresponding to the channel data to be audited;

[0177] Determine the numerical difference between the key indicator in the last uploaded channel data and the corresponding key indicator in the channel data uploaded this time;

[0178] When the numerical difference is within the preset difference range, the audit is passed; otherwise, it fails;

[0179] The allowable range of the value corresponding to the key indicator is determined by the following steps:

[0180] Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited;

[0181] Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator;

[0182] Perform outlier elimination processing on the data in the data set to obtain the processed data set;

[0183] Determine the maximum and minimum values ​​of the processed data set;

[0184] Based on the maximum and minimum values, the permissible range is determined.

[0185] The working principle and beneficial effects of the above technical solution are:

[0186] The audit rules mainly include: auditing based on the allowable range of key indicators, and data beyond the allowable range is abnormal; the allowable range can be obtained by analyzing historical channel data, that is, a distributor's purchase data for commodity A has always been between 100 and 200. When the purchase data of commodity A in this channel data is 210, it can be determined to be abnormal and needs to be verified. It can also be determined by the change amount, that is, the last purchase volume was 150, and the current purchase volume was 230. The preset difference threshold is 30, so the channel data this time is abnormal and needs to be verified. The difference threshold can be pre-set, or it can be input into the preset analysis model for analysis based on the specific situation of the object corresponding to the channel data to be audited.

[0187] In one embodiment, the channel data inspection and auditing system further includes:

[0188] The third audit module is used to obtain the verification data associated with the channel data to be audited;

[0189] And verify the verification data; if the verification passes, the audit is passed; otherwise, it fails;

[0190] The verification data includes one or more combinations of the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, and the identity information of the uploading person when uploading.

[0191] The working principle and beneficial effects of the above technical solution are:

[0192] When uploading channel data, the associated verification data is uploaded synchronously to verify the validity of the uploading method; mainly starting from the ID of the uploading terminal device, the environmental parameter data of the area where the terminal device is located when uploading, the positioning data of the uploading device when uploading, the identity information of the uploading personnel when uploading, etc.; among which, the environmental parameter data of the area where the terminal device is located when uploading, for example, can be the weather conditions, sunny, cloudy, etc.; thereby ensuring the accuracy of channel data acquisition and preventing the occurrence of human fabrication.

[0193] In one embodiment, the channel data inspection and auditing system further includes:

[0194] The fourth audit module is used to analyze the channel data to be audited, determine multiple third parties that interact with the object corresponding to the channel data to be audited; obtain the channel data uploaded by the third party; and audit the channel data to be audited based on the channel data uploaded by the third party;

[0195] When using channel data uploaded by a third party to audit channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows:

[0196] Obtain historical audit results records from third parties;

[0197] Inputting historical audit result records into a preset neural network model to determine a first credit value;

[0198] Get the third party liability values ​​of other preset number of third parties on the platform;

[0199] Get the effectiveness coefficients of other third parties on the platform;

[0200] Determining a second credit value of the third party based on the effectiveness coefficient and the commitment value;

[0201] Determining the credibility of the third party based on the first credibility value and the second credibility value;

[0202] When the credibility is greater than the preset credibility threshold, the channel data uploaded by the third party is used to audit the channel data to be audited;

[0203] When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table;

[0204] When channel data uploaded by a third party is used to audit channel data, and the audit result is abnormal, but the channel data to be audited is subsequently manually determined to be normal, the effectiveness coefficients of all other third parties on the platform are adjusted downward based on the preset effectiveness coefficient step adjustment table.

[0205] The working principle and beneficial effects of the above technical solution are:

[0206] The audit of channel data for inspection and audit can also be conducted based on channel data uploaded by a third party, that is, the purchase data of distributor A corresponds to the shipment data of factory B; when using third-party data for inspection, it is necessary to determine the credibility of the third party to ensure the credibility of the third-party data; the credibility is mainly determined by the first credit value reflecting the third party itself and the second credit value reflecting the trust of other third parties in the third party; based on the first credit value and the second credit value, the credibility of the third party can be determined by weighted sum calculation, that is, the first credit value and the second credit value are multiplied by the corresponding preset coefficients and then summed. Among them, the first credit value uses the neural network model method to analyze the historical inspection results of the channel data uploaded by the third party; when there is no abnormality in the historical inspection results, the first credit value is the full value, preset to 100; when the number of abnormalities in the historical inspection results increases, it gradually decreases. The second credit value is calculated based on the effective coefficient and the bearing value, and the calculation formula is as follows: Among them, X2 is the second credit value, A i is the commitment value of the i-th other third party; α i is the effective coefficient of the ith other third party; the commitment value is allocated according to the audit results of the third party, for example, 20 is allocated for an audit without abnormality, and 30 is deducted for an audit with abnormality; the effective coefficient is the initial value allocated by the system to the third party; the final value is adjusted based on the commitment result; in addition, the effective coefficient is reversely adjusted according to the manual review results of the audit results to ensure the accuracy of the subsequent third-party credibility confirmation. When adjusting, it is adjusted based on the effective coefficient ladder adjustment table, which is mainly determined based on the historical adjustment records of the third party. For example, the last time was a downward adjustment, and this time was an upward adjustment, and at this time it corresponds to an adjustment coefficient, which is a 1st upward adjustment coefficient; the last time was an upward adjustment, and this time was an upward adjustment, and at this time it corresponds to an adjustment coefficient, which is a 2nd upward adjustment coefficient; the first upward adjustment coefficient is less than the second upward adjustment coefficient; the first upward adjustment coefficient is less than the first downward adjustment coefficient; the same downward adjustment coefficient is greater than the same upward adjustment coefficient; the higher upward adjustment coefficient is greater than the lower upward adjustment coefficient; the higher downward adjustment coefficient is greater than the lower downward adjustment coefficient.

[0207] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A channel data inspection and audit method, characterized in that: include: Obtain channel data to be audited; parsing the channel data, determining a plurality of key indicators and constructing a key indicator set corresponding to the channel data; Auditing the key indicator set based on a preset audit indicator set; Obtain the audit rules corresponding to each key indicator; Auditing the key indicators based on the audit rules; Parsing the channel data to be audited, and determining a plurality of third parties that interact with the object corresponding to the channel data to be audited; Obtaining channel data uploaded by the third party; Auditing the channel data to be audited based on the channel data uploaded by the third party; When the channel data uploaded by a third party is used to audit the channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows: Obtain historical audit results records of the third party; Inputting the historical audit result records into a preset neural network model to determine a first credit value; Obtaining the commitment values ​​of a preset number of other third parties on the platform for the third party; Get the effectiveness coefficients of other third parties on the platform; determining a second credit value of the third party based on the validity coefficient and the commitment value; determining the credibility of the third party based on the first credit value and the second credit value; When the credibility is greater than a preset credibility threshold, the channel data to be audited is audited using the channel data uploaded by a third party; When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table; When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is normal, the effective coefficients of all other third parties on the platform are adjusted downward based on the preset effective coefficient ladder adjustment table; The second credit value is calculated based on the effective coefficient and the commitment value, and the calculation formula is: ;in, is the second credit value, For the other third party's commitment value; For the The effective coefficient of other third parties; the assumed value is the value assigned according to the audit results of the third party; the effective coefficient is the initial value assigned by the system to the third party.

2. The channel data inspection and auditing method according to claim 1, characterized in that: The auditing of the key indicator set based on the preset audit indicator set includes: Associating each key indicator in the audit indicator set with each key indicator in the key indicator set one by one; When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit is passed, otherwise it is not passed; The step of associating each key indicator in the audit indicator set with each key indicator in the key indicator set one by one includes: Quantifying each key indicator in the audit indicator set based on a preset quantification template to determine a first parameter value corresponding to each key indicator in the audit indicator set; quantifying each key indicator in the key indicator set based on the quantification template, and determining a second parameter value corresponding to each key indicator in the key indicator set; Extracting key indicators in the key indicator set in sequence, and calculating the difference between the first parameter value corresponding to the extracted key indicator in the key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set; When the difference is less than or equal to a preset association threshold and the minimum value among the calculated differences is found, the key indicator in the corresponding key indicator set is associated with the key indicator in the corresponding audit indicator set.

3. The channel data inspection and auditing method according to claim 1, characterized in that: Auditing the key indicators based on the audit rules includes: Analyze the audit rules to determine the allowable range of the values ​​corresponding to the key indicators; When the value corresponding to the key indicator is within the allowable range, the audit is passed; otherwise, it fails; and / or, Obtain the last uploaded channel data of the object corresponding to the channel data to be audited; Determine the difference between the key indicator in the channel data uploaded last time and the key indicator corresponding to the channel data uploaded this time; When the numerical difference is within the preset difference range, the audit is passed; otherwise, it is not passed; The allowable range of the value corresponding to the key indicator is determined by the following steps: Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited; Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator; Performing outlier elimination processing on the data in the data set to obtain a processed data set; Determine the maximum and minimum values ​​of the processed data set; Based on the maximum value and the minimum value, the allowable range is determined.

4. The channel data inspection and auditing method according to claim 1, characterized in that: Also includes: Obtaining verification data associated with the channel data to be audited; Verifying the verification data; When the verification is passed, the audit is passed; Otherwise, fail; The verification data includes one or more combinations of the ID of the uploading terminal device, environmental parameter data of the area where the terminal device is located when uploading, positioning data of the uploading device when uploading, and identity information of the uploading person when uploading.

5. A channel data inspection and audit system, characterized in that: include: The first acquisition module is used to obtain channel data to be audited; A first parsing module, used to parse the channel data, determine a plurality of key indicators and construct a key indicator set corresponding to the channel data; A first audit module, used for auditing the key indicator set based on a preset audit indicator set; The second acquisition module is used to obtain the audit rules corresponding to each key indicator; A second audit module, used to audit the key indicators based on the audit rules; A fourth audit module, used for parsing the channel data to be audited, and determining a plurality of third parties interacting with the object corresponding to the channel data to be audited; Obtaining channel data uploaded by the third party; Auditing the channel data to be audited based on the channel data uploaded by the third party; When the channel data uploaded by a third party is used to audit the channel data to be audited, the credibility of the third party is confirmed. The credibility determination steps are as follows: Obtain historical audit results records of the third party; Inputting the historical audit result records into a preset neural network model to determine a first credit value; Obtaining the commitment values ​​of a preset number of other third parties on the platform for the third party; Get the effectiveness coefficients of other third parties on the platform; determining a second credit value of the third party based on the validity coefficient and the commitment value; determining the credibility of the third party based on the first credit value and the second credit value; When the credibility is greater than a preset credibility threshold, the channel data to be audited is audited using the channel data uploaded by a third party; When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is abnormal, the effective coefficients of all other third parties on the platform are adjusted upward based on the preset effective coefficient ladder adjustment table; When the channel data uploaded by a third party is used to audit the channel data to be audited, and the audit result is abnormal, and it is subsequently manually determined that the channel data to be audited is normal, the effective coefficients of all other third parties on the platform are adjusted downward based on the preset effective coefficient ladder adjustment table; The second credit value is calculated based on the effective coefficient and the commitment value, and the calculation formula is: ;in, is the second credit value, For the other third party's commitment value; For the The effective coefficient of other third parties; the assumed value is the value assigned according to the audit results of the third party; the effective coefficient is the initial value assigned by the system to the third party.

6. The channel data inspection and auditing system according to claim 5, characterized in that: The first audit module performs the following operations: Associating each key indicator in the audit indicator set with each key indicator in the key indicator set one by one; When each key indicator in the key indicator set has a unique associated key indicator in the audit indicator set and each key indicator in the audit indicator set has a unique associated key indicator in the key indicator set, the audit is passed, otherwise it is not passed; The step of associating each key indicator in the audit indicator set with each key indicator in the key indicator set one by one includes: Quantifying each key indicator in the audit indicator set based on a preset quantification template to determine a first parameter value corresponding to each key indicator in the audit indicator set; quantifying each key indicator in the key indicator set based on the quantification template, and determining a second parameter value corresponding to each key indicator in the key indicator set; Extracting key indicators in the key indicator set in sequence, and calculating the difference between the first parameter value corresponding to the extracted key indicator in the key indicator set and each second parameter value corresponding to each key indicator in the audit indicator set; When the difference is less than or equal to a preset association threshold and the minimum value among the calculated differences is found, the key indicator in the corresponding key indicator set is associated with the key indicator in the corresponding audit indicator set.

7. The channel data inspection and auditing system according to claim 5, characterized in that: The second audit module performs the following operations: Analyze the audit rules to determine the allowable range of the values ​​corresponding to the key indicators; When the value corresponding to the key indicator is within the allowable range, the audit is passed; Otherwise, fail; and / or, Obtain the last uploaded channel data of the object corresponding to the channel data to be audited; Determine the difference between the key indicator in the channel data uploaded last time and the key indicator corresponding to the channel data uploaded this time; When the numerical difference is within the preset difference range, the audit is passed; otherwise, it is not passed; The allowable range of the value corresponding to the key indicator is determined by the following steps: Obtain the historically uploaded channel data of the object corresponding to the channel data to be audited; Parse the channel data uploaded historically and determine the data set of the values ​​corresponding to each key indicator; Performing outlier elimination processing on the data in the data set to obtain a processed data set; Determine the maximum and minimum values ​​of the processed data set; Based on the maximum value and the minimum value, the allowable range is determined.

8. The channel data inspection and auditing system according to claim 5, characterized in that: Also includes: The third audit module is used to obtain the verification data corresponding to the channel data to be audited; and verifying the verification data; When the verification is passed, the audit is passed; Otherwise, fail; The verification data includes one or more combinations of the ID of the uploading terminal device, environmental parameter data of the area where the terminal device is located when uploading, positioning data of the uploading device when uploading, and identity information of the uploading person when uploading.

Images