Intelligent wage audit method, device and electronic equipment for engineering projects

Abstract

The present invention relates to the field of wage audit, and discloses a method, device and electronic device for intelligent wage audit applied to engineering projects, wherein the method comprises: performing real-name authentication on personnel data, obtaining real-name authentication data, collecting attendance information, and calculating a payroll to be issued; performing a three-party wage audit on the payroll to be issued, obtaining a three-party audited wage, analyzing the virtual wage of the party to be paid, and calculating the wage similarity between the three-party audited wage and the virtual wage; constructing a payment evidence stream, storing the payment evidence stream in a blockchain, and obtaining a storage evidence stream; performing wage clearing on the party to be paid, obtaining cleared wages, and performing a final wage audit on the cleared wages, and obtaining a final audited wage; storing the real-name authentication data, attendance information and the final audited wage in a blockchain, constructing a visual multi-dimensional report, and auditing abnormal fund conditions to obtain abnormal audit results; and obtaining a wage audit result. The present invention can reduce loopholes in wage audits for engineering projects.

Description

Technical Field

[0001] The present invention relates to the field of wage auditing, and in particular to an intelligent wage auditing method, device and electronic equipment applied to engineering projects. Background Art

[0002] The risk of wage arrears for employees has not been completely eradicated in the existing technology, and it is urgent to break through. The risk points are mainly concentrated in: First, the monthly full payment system for employees' wages is not implemented in place; second, there is basically no arrears problem for employees who directly sign labor contracts with enterprises and their subsidiaries, but the phenomenon of irregular employment and failure to pay employees' wages on time and in full also occurs occasionally; third, some construction units have difficulties in financing, lack of funds, untimely settlement, slow return of deposits, etc., which leads to some companies paying funds in advance in order not to default on funds for small and medium-sized enterprises and employee wages, and the financial pressure has doubled. Therefore, there are many loopholes in the wage review under engineering projects. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a method, device and electronic equipment for intelligent salary auditing applied to engineering projects, which can reduce salary auditing loopholes in engineering projects.

[0004] In a first aspect, the present invention provides a method for intelligent salary auditing applied to engineering projects, comprising:

[0005] Obtaining personnel information of the party to be paid wages under the project, performing real-name authentication on the personnel information to obtain real-name authentication information, collecting attendance information of the real-name authentication information, and using the attendance information to calculate the payroll to be paid of the party to be paid wages;

[0006] Conducting a three-party review of the payroll to be issued to obtain a three-party reviewed salary, analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculating the salary similarity between the three-party reviewed salary and the virtual salary;

[0007] When the salary similarity is less than the preset similarity, return to the above step of obtaining the personnel information of the party to be paid salary under the engineering project;

[0008] When the salary similarity is not less than a preset similarity, a three-party review of the salary to be issued is performed on the salary slip to obtain the three-party reviewed salary, a payment evidence flow of the three-party reviewed salary is constructed, and the payment evidence flow is stored in the blockchain to obtain a storage evidence flow;

[0009] Based on the stored evidence flow, clearing the wages of the party to be paid to obtain cleared wages, and conducting a final review of the cleared wages to obtain final reviewed wages;

[0010] The real-name authentication information, the attendance information and the final audited salary are stored in a preset blockchain, a visual multi-dimensional report of the final audited salary is constructed in the preset blockchain, and the abnormal funds of the final audited salary are audited by combining the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormal audit result;

[0011] The final audited salary and the abnormal audit result are combined to obtain the salary audit result under the engineering project.

[0012] In a possible implementation of the first aspect, performing real-name authentication on the personnel information to obtain real-name authentication information includes:

[0013] Searching for ID card information in the personnel data, and extracting the ID card photo from the ID card information;

[0014] Collect on-site photos of the party to be paid wages corresponding to the personnel information;

[0015] Extracting features from the ID card photo and the on-site photo respectively to obtain ID card features and on-site photo features;

[0016] The feature similarity between the ID card feature and the on-site shooting feature is calculated using the following formula:

[0017]

[0018] Where S represents the feature similarity between the ID card feature and the on-site shooting feature, x i Represents the identity card characteristics, y i represents the on-site shooting feature, i represents the sequence number of the feature, and k represents the total number of features;

[0019] When the feature similarity is greater than a preset similarity, a real-name authentication success mark of the personnel information corresponding to the feature similarity is constructed, and the real-name authentication success mark is combined with the personnel information to obtain the real-name authentication information.

[0020] In a possible implementation of the first aspect, the step of calculating the payroll of the party to be paid wages by using the attendance information includes:

[0021] Submitting a salary payment application to the general contractor of the party to be paid wages based on the attendance information;

[0022] In the general contractor, according to the wage payment application, the labor wages of the party to be paid are calculated using the following formula:

[0023]

[0024] Wherein, m represents the labor wage, q represents the workload of the attendance information, p represents the unit price per unit workload, m1 represents the wage calculated according to the q*p method, u represents the daily wage, v represents the number of working days, m2 represents the wage calculated according to the u*v method, w represents the monthly fixed wage, m3 represents the wage calculated according to the w method, a represents the basic wage, b represents the performance, and m4 represents the wage calculated according to the a*b method;

[0025] On the basis of the labor wages, query the increase or decrease of the wages of the party to be paid;

[0026] The labor wages and the increased and decreased wages are combined to determine the payroll to be issued.

[0027] In a possible implementation of the first aspect, performing a three-party review of the payroll to be issued to obtain the three-party reviewed wages includes:

[0028] Obtaining the payroll party, subcontractor and general contractor of the payroll to be issued, and sending the payroll to be issued to the payroll party, the subcontractor and the general contractor respectively;

[0029] The wage slip to be paid is signed and confirmed by the party to be paid, the subcontractor and the general contractor respectively, and the wage signature confirmation result is used as the three-party audited wage.

[0030] In a possible implementation of the first aspect, analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information includes:

[0031] Extracting a salary influencing factor from the real-name authentication information and the attendance information, and dividing the salary influencing factor into a parent factor and a child factor;

[0032] The absolute value difference between the parent factor and the child factor is calculated using the following formula:

[0033] L=|ms|

[0034] Wherein, L represents the absolute value difference, m represents the parent factor after initialization and averaging, and s represents the child factor after initialization and averaging;

[0035] Selecting a minimum value and a maximum value from the absolute value differences;

[0036] According to the minimum value and the maximum value, the correlation coefficient of the wage influencing factor is calculated using the following formula:

[0037]

[0038] Wherein, ξ represents the correlation coefficient, x represents the salary influencing factor, a represents the minimum value, b represents the maximum value, and ρ represents the resolution coefficient, which is 0.5;

[0039] According to the correlation coefficient, selecting a target influencing factor from the wage influencing factors;

[0040] Based on the target impact factor, the mapping degree of the virtual salary is calculated using the following formula:

[0041]

[0042] Among them, β j represents the mapping degree, α h Represents the hidden layer data of the BP neural network, x i represents the value of the target impact factor, θ h represents the bias from the input layer to the hidden layer, v ih represents the weight from the input layer to the hidden layer, w hj represents the weight from the hidden layer to the output layer, θ j represents the bias from the hidden layer to the output layer, i represents the serial number of the target influencing factor, d represents the number of the target influencing factor, h represents the serial number of the hidden layer data, and q represents the number of the hidden layer data;

[0043] According to the mapping degree, the virtual salary is calculated using the following formula:

[0044] I=β j *F

[0045] Among them, I represents the virtual salary, β j represents the mapping degree, and F represents the mapping function from the mapping degree to the virtual salary.

[0046] In a possible implementation manner of the first aspect, storing the payment evidence flow on a blockchain to obtain the stored evidence flow includes:

[0047] Determining a timestamp of the payment evidence stream, and determining a blockchain node component of the payment evidence stream based on the timestamp;

[0048] Encrypting the blockchain node component to obtain an encrypted node component;

[0049] Performing vector encoding on the encrypted node component to obtain an encoded node component;

[0050] The blockchain node number of the encoding node component is calculated using the following formula:

[0051] H(k0=n*(f*k%1)

[0052] Wherein, H(k) represents the blockchain serial number of the encoding node component, n represents the total number of nodes in the blockchain, f represents a randomly selected number, 0≤f<1, and k represents the encoding node component;

[0053] The encoded node component is stored in the blockchain corresponding to the blockchain node serial number.

[0054] In a possible implementation of the first aspect, clearing wages for the party to be paid wages based on the stored evidence flow to obtain cleared wages includes:

[0055] Constructing the wage payment requirements of the storage evidence flow at the general contractor of the party to be paid wages;

[0056] Based on the salary payment requirements, the constructed salary payment instruction is transmitted to the bank unit of the general contractor, and a special salary payment account for the party to be paid is established;

[0057] Based on the salary pending payment instruction and the special account for salary payment, the salary is paid to the party to be paid at the bank unit to obtain the cleared salary.

[0058] In a possible implementation of the first aspect, performing a final review on the cleared wages to obtain a final reviewed wage includes:

[0059] Issue a wage receipt for the cleared wages, and transmit the wage receipt to the general contractor corresponding to the cleared wages;

[0060] The wage receipt is signed and confirmed at the general contractor to obtain a signed and confirmed receipt, and a wage voucher and a bank payment journal for the signed and confirmed receipt are constructed;

[0061] The wage payment voucher is signed and confirmed at the subcontractor corresponding to the general contractor to obtain a first confirmation result;

[0062] Sign and confirm the bank payment log at the party to be paid wages corresponding to the general contractor to obtain a second confirmation result;

[0063] The signed confirmation receipt, the first confirmation result and the second confirmation result are used as the final audited salary.

[0064] In a possible implementation of the first aspect, constructing a visualized multi-dimensional report of the final audited salary in the preset blockchain includes:

[0065] In the preset blockchain, extract the report base point and report structure of the final audited salary;

[0066] Based on the report base point and the report structure, construct a multi-dimensional report of the final audited salary;

[0067] The multi-dimensional report is visualized to obtain the visualized multi-dimensional report.

[0068] In a possible implementation of the first aspect, combining the visualized multi-dimensional report, the real-name authentication information, and the attendance information to review the abnormal situation of the funds of the final audited salary to obtain an abnormal audit result includes:

[0069] Combining the visualized multi-dimensional report, the real-name authentication information and the attendance information, the expected value of the final audited salary is calculated using the following formula:

[0070] P(Y)=p

[0071]

[0072] Wherein, E represents the expected value of the fund audit, w represents the length of a sampling time period for data sampling when detecting fund anomalies in the visualized multi-dimensional report, the real-name authentication information and the attendance information, T represents the total sampling time period, k represents the total number of time intervals that exceed the upper limit of fund transactions in a short period of time from i0 to i0+w-1, i0 represents the first time period of sampling, i represents the time period sequence number, and p represents Y j =1, Y represents the number of time intervals exceeding the upper limit of capital transactions in the short term, b k Represents the binomial probability formula where the time period contains multiple time intervals.

[0073] When the expected value of the fund audit is less than the preset expected value, a first abnormal audit result is obtained;

[0074] When the expected value of the fund review is not less than the preset expected value, querying the overlapping data of the final reviewed salary in the visualized multi-dimensional report, the real-name authentication information and the attendance information;

[0075] Based on the overlapping data, a second abnormal audit result of the final audited salary is identified.

[0076] In a second aspect, the present invention provides a smart salary audit device for use in engineering projects, the device comprising:

[0077] The salary calculation module is used to obtain the personnel information of the party to be paid wages under the engineering project, perform real-name authentication on the personnel information to obtain the real-name authentication information, collect the attendance information of the real-name authentication information, and use the attendance information to calculate the payroll to be paid of the party to be paid wages;

[0078] A similarity calculation module is used to perform a three-party review of the salary to be issued to obtain a three-party reviewed salary, perform a three-party review of the salary to be issued to obtain a three-party reviewed salary, analyze the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculate the salary similarity between the three-party reviewed salary and the virtual salary;

[0079] A step return module, used for returning to the step of obtaining the personnel information of the party to be paid wages under the engineering project when the salary similarity is less than a preset similarity;

[0080] A blockchain storage module, used for constructing a payment evidence flow of the three-party review of the salary when the salary similarity is not less than a preset similarity, storing the payment evidence flow in blockchain, and obtaining a storage evidence flow;

[0081] A salary review module, configured to perform salary clearing for the party to be paid based on the stored evidence flow to obtain cleared salary, and perform final salary review on the cleared salary to obtain final reviewed salary;

[0082] An abnormality audit module is used to store the real-name authentication information, the attendance information and the final audited salary in a preset blockchain, construct a visual multi-dimensional report of the final audited salary in the preset blockchain, and audit the abnormal funds of the final audited salary in combination with the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormality audit result;

[0083] The result determination module is used to combine the final audited salary with the abnormal audit result to obtain the salary audit result under the engineering project.

[0084] In a third aspect, the present invention provides an electronic device, comprising:

[0085] at least one processor; and a memory communicatively coupled to the at least one processor;

[0086] Wherein, the memory stores a computer program executable by the at least one processor, so that the at least one processor can execute the intelligent wage audit method applied to engineering projects as described in any one of the first aspects above.

[0087] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent wage audit method applied to an engineering project as described in any one of the first aspects above.

[0088] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0089] The embodiment of the present invention first performs real-name authentication on the personnel information to ensure that the electronic information of the party to be paid is consistent with the actual facial information, thereby realizing the unified management of the electronic information of the party to be paid. Furthermore, the embodiment of the present invention collects the attendance information of the real-name authentication information to count the wages of the party to be paid based on the daily attendance punch-in data of the party to be paid. Furthermore, the embodiment of the present invention calculates the payroll of the party to be paid by using the attendance information, so as to send the counted wage data to all parties of the project for review. The salary slip is subject to a three-party review of the salary, so that all parties involved in the salary payment process can review and confirm the salary results to ensure the openness of salary payment. Furthermore, the embodiment of the present invention analyzes the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, so as to predict the employee salary using a machine learning model, which is convenient for comparison with the actual calculated salary. Furthermore, the embodiment of the present invention constructs a payment evidence flow for the three-party review of the salary to record the entire salary payment process information, associates the project progress, employee attendance and employee salary calculation, and avoids false reporting of project progress and funds. The problems of misappropriation and so on make the accumulated employee salary data clear and understandable, which greatly avoids the false reporting of project progress. Furthermore, the embodiment of the present invention stores the payment evidence flow on blockchain, so as to add blockchain as the underlying technology to the process of project engineering salary payment, and serve the employee group. It can effectively solve many drawbacks of the traditional model in the past, such as information asymmetry between subjects, uncertainty of capital flow, imperfect management mechanism, etc., support online labor contract signing, ensure data security, non-tamperability and traceability, realize the on-chain storage of various engineering-related information such as projects, subjects and contracts, associate contract information with capital payment, and form The complete payment evidence chain, the fund payment record information at each layer is clear and traceable, effectively reducing the risk of misappropriation of key funds and forming substantial fund supervision. The embodiment of the present invention clears the wages of the party to be paid based on the stored evidence flow, so as to pay the wages to the employee's salary card, paving the way for the subsequent review of the salary payment process. The embodiment of the present invention stores the real-name authentication information, the attendance information and the final audited wages in the preset blockchain, so as to add the blockchain as the underlying technology to the process of infrastructure project wage payment, serve the employee group, and effectively solve many drawbacks of the traditional model in the past. Therefore, the intelligent wage audit method, device and electronic equipment applied to engineering projects proposed in the embodiment of the present invention can reduce the wage audit loopholes in engineering projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0091] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0092] Figure 1 A flowchart of an intelligent wage audit method for an engineering project provided by an embodiment of the present invention;

[0093] Figure 2 In one embodiment of the present invention Figure 1 A flowchart of one of the steps of a wage intelligent audit method applied to engineering projects is provided;

[0094] Figure 3 In one embodiment of the present invention Figure 1 A flowchart of another step of a wage intelligent audit method applied to engineering projects is provided;

[0095] Figure 4 A schematic diagram of a module of an intelligent salary audit device applied to an engineering project provided by an embodiment of the present invention;

[0096] Figure 5 A schematic diagram of the internal structure of an electronic device for implementing an intelligent wage audit method applied to an engineering project provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0097] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0098] The embodiment of the present invention provides a method for intelligent wage auditing applied to engineering projects, and the execution subject of the method for intelligent wage auditing applied to engineering projects includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the method for intelligent wage auditing applied to engineering projects can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0099] See also Figure 1 FIG. 1 is a flow chart of an intelligent wage audit method for an engineering project provided by an embodiment of the present invention. Figure 1 The intelligent wage audit methods described in the application to engineering projects include:

[0100] S1. Obtain personnel information of the party to be paid wages under the engineering project, perform real-name authentication on the personnel information to obtain real-name authentication information, collect attendance information of the real-name authentication information, and use the attendance information to calculate the payroll to be paid of the party to be paid wages.

[0101] The engineering project described in the embodiment of the present invention refers to project engineering in various industries, such as infrastructure projects; the party to be paid refers to the person waiting to be paid; the personnel information refers to the personal identity information of the party to be paid, including employee name, photo, ID number, unit, performance record, job classification, project contract and other information.

[0102] Furthermore, the embodiment of the present invention performs real-name authentication on the personnel information to ensure that the electronic information of the party to be paid is consistent with the actual facial information, thereby achieving unified management of the electronic information of the party to be paid with both person and ID.

[0103] In one embodiment of the present invention, the real-name authentication of the personnel information to obtain the real-name authentication information includes: searching the personnel information for ID card information and extracting the ID card photo from the ID card information; collecting the on-site photo of the party to be paid corresponding to the personnel information; performing feature extraction on the ID card photo and the on-site photo respectively to obtain ID card features and on-site shooting features; and calculating the feature similarity between the ID card features and the on-site shooting features using the following formula:

[0104]

[0105] Where S represents the feature similarity between the ID card feature and the on-site shooting feature, x i Represents the identity card characteristics, y i represents the on-site shooting feature, i represents the sequence number of the feature, and k represents the total number of features;

[0106] When the feature similarity is greater than a preset similarity, a real-name authentication success mark of the personnel information corresponding to the feature similarity is constructed, and the real-name authentication success mark is combined with the personnel information to obtain the real-name authentication information.

[0107] The preset similarity can be set to 0.8, or can be set according to the actual scenario. For example, the information of on-site construction workers is collected and verified online in a "person-document integration" manner, basic management of on-site construction workers' information is implemented through real-name authentication, and attendance information is entered and supervised with the help of technologies such as face recognition and real-time positioning.

[0108] Furthermore, the embodiment of the present invention collects the attendance information of the real-name authentication data to calculate the salary of the party to be paid based on the daily attendance punch-in data of the party to be paid.

[0109] In one embodiment of the present invention, referring to Figure 2 As shown, the attendance information collected from the real-name authentication data includes:

[0110] S201, identifying the job category corresponding to the real-name authentication information;

[0111] S202, extracting the daily clock-in data of the real-name authentication information from the job category;

[0112] S203: Normalize the daily clock-in data to obtain the attendance information.

[0113] Optionally, the process of normalizing the daily clock-in data to obtain the attendance information refers to the situation where some staff members are not late for the day but forget to clock in. At this time, the staff members report to their superiors to make up for the clock-in. In this process, the clock-in data will consist of system clock-ins and staff clock-ins. Therefore, it needs to be standardized and unified into the system's clock-in method. For example, on Wednesday: clock in once in the morning and once in the evening.

[0114] Furthermore, the embodiment of the present invention calculates the payroll of the party to be paid by using the attendance information, so as to send the statistical salary data to various parties involved in the project for review.

[0115] In one embodiment of the present invention, the method of calculating the payroll of the party to be paid by using the attendance information includes: submitting a salary payment application to the general contractor of the party to be paid according to the attendance information; and calculating the labor wages of the party to be paid according to the salary payment application in the general contractor using the following formula:

[0116]

[0117] Wherein, m represents the labor wage, q represents the workload of the attendance information, p represents the unit price per unit workload, m1 represents the wage calculated according to the q*p method, u represents the daily wage, v represents the number of working days, m2 represents the wage calculated according to the u*v method, w represents the monthly fixed wage, m3 represents the wage calculated according to the w method, a represents the basic wage, b represents the performance, and m4 represents the wage calculated according to the a*b method;

[0118] On the basis of the labor wages, the wage increase or decrease of the party to be paid is queried; and the wage slip to be paid is determined by combining the labor wages with the wage increase or decrease.

[0119] Among them, the superior unit refers to the superior who is responsible for managing the attendance information of the party to be paid wages. For example, if the party to be paid wages is a migrant worker, the subcontracting unit is responsible for managing the attendance information of the party to be paid wages. The subcontracting unit sends the attendance information to the general contractor as a wage payment application; the increase or decrease in wages refers to the wages increased or decreased on the basis of the labor wages, such as deductions for lateness, bonuses, taxes, etc.

[0120] S2. Conduct a three-party review of the salary to be paid to obtain the three-party reviewed salary, analyze the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculate the salary similarity between the three-party reviewed salary and the virtual salary.

[0121] The embodiment of the present invention conducts a three-party review of the payroll to be issued, so that all parties involved in the payroll process can review and confirm the payroll results, thereby ensuring the openness of payroll issuance.

[0122] In one embodiment of the present invention, referring to Figure 3 As shown, the three-party review of the salary to be issued to obtain the three-party reviewed salary includes:

[0123] S301, obtaining the party to be paid wages, the subcontractor and the general contractor of the payroll to be issued, and sending the payroll to be issued to the party to be paid wages, the subcontractor and the general contractor respectively;

[0124] S302, respectively, signing and confirming the wage slip at the party to be paid, the subcontractor and the general contractor, and using the wage signature confirmation result as the three-party audited wage.

[0125] Furthermore, the embodiment of the present invention analyzes the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, so as to use a machine learning model to predict the employee's salary, which is convenient for comparison with the actual calculated salary.

[0126] In one embodiment of the present invention, the analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information includes: extracting the salary influencing factor from the real-name authentication information and the attendance information, and dividing the parent factor and the child factor in the salary influencing factor; and calculating the absolute value difference between the parent factor and the child factor using the following formula:

[0127] L=|ms|

[0128] Wherein, L represents the absolute value difference, m represents the parent factor after initialization and averaging, and s represents the child factor after initialization and averaging;

[0129] Select a minimum value and a maximum value from the absolute value difference; and calculate the correlation coefficient of the wage influencing factor according to the minimum value and the maximum value using the following formula:

[0130]

[0131] Wherein, ξ represents the correlation coefficient, x represents the salary influencing factor, a represents the minimum value, b represents the maximum value, and ρ represents the resolution coefficient, which is 0.5;

[0132] According to the correlation coefficient, a target influencing factor is selected from the salary influencing factors; based on the target influencing factor, the mapping degree of the virtual salary is calculated using the following formula:

[0133]

[0134] Among them, β j represents the mapping degree, α h Represents the hidden layer data of the BP neural network, x i represents the value of the target impact factor, θ h represents the bias from the input layer to the hidden layer, v ih represents the weight from the input layer to the hidden layer, w hj represents the weight from the hidden layer to the output layer, θ jrepresents the bias from the hidden layer to the output layer, i represents the serial number of the target influencing factor, d represents the number of the target influencing factor, h represents the serial number of the hidden layer data, and q represents the number of the hidden layer data;

[0135] According to the mapping degree, the virtual salary is calculated using the following formula:

[0136] I=β j *F

[0137] Among them, I represents the virtual salary, β j represents the mapping degree, and F represents the mapping function from the mapping degree to the virtual salary.

[0138] Among them, the initialization refers to dividing the data of each factor indicator by the initial value. The initial value can be determined by pre-setting or by collecting historical data of the factor indicator; the averaging is obtained by first calculating the average value of the parent factor and each child factor, and then dividing the data of each factor by the average value of the corresponding factor.

[0139] S3. When the salary similarity is less than a preset similarity, return to the above step of obtaining the personnel information of the party to be paid salary under the engineering project.

[0140] S4. When the salary similarity is not less than a preset similarity, a payment evidence flow of the three-party salary review is constructed, and the payment evidence flow is stored in the blockchain to obtain a storage evidence flow.

[0141] The embodiment of the present invention constructs the payment evidence flow of the three-party review of wages to record the entire wage payment process information, associates the project progress, employee attendance and employee wage calculation, avoids problems such as false reporting of project progress and misappropriation of funds, makes the accumulated employee wage data clear, and greatly avoids false reporting of project progress.

[0142] In one embodiment of the present invention, the construction of the payment evidence flow for the three-party salary review includes: collecting data flow information corresponding to the three-party salary review; dividing the business data flow, capital data flow and payment instruction flow in the data flow information; and using the business data flow, the capital data flow and the payment instruction flow as the payment evidence flow.

[0143] Furthermore, the embodiments of the present invention store the payment evidence stream on blockchain to add blockchain as the underlying technology to the process of project engineering wage payment to serve the employee group, and can effectively solve many drawbacks of the traditional model in the past, such as information asymmetry between entities, uncertain capital flow, imperfect management mechanism, etc. It supports online labor contract signing, ensures the security, non-tamperability and traceability of data, realizes the on-chain storage of information related to various projects, such as projects, entities, contracts, etc., associates contract information with capital payment, forms a complete payment evidence chain, and makes the capital payment record information at each layer clear and traceable, effectively reduces the risk of misappropriation of key funds, and forms substantial capital supervision.

[0144] In one embodiment of the present invention, the blockchain storage of the payment evidence stream to obtain the stored evidence stream includes: determining the timestamp of the payment evidence stream, and determining the blockchain node component of the payment evidence stream based on the timestamp; encrypting the blockchain node component to obtain an encrypted node component; vector encoding the encrypted node component to obtain an encoded node component; and calculating the blockchain node sequence number of the encoded node component using the following formula:

[0145] H(k)=n*(f*k%1)

[0146] Wherein, H(k) represents the blockchain serial number of the encoding node component, n represents the total number of nodes in the blockchain, f represents a randomly selected number, 0≤f<1, and k represents the encoding node component;

[0147] The encoded node component is stored in the blockchain corresponding to the blockchain node serial number.

[0148] Among them, the blockchain node component refers to dividing the payment evidence flow into multiple blocks, each block contains multiple evidence flow data. For example, in an infrastructure project, the blockchain node component may include data from blocks such as the enterprise storage block, the worker wage supervision end, the general contractor end, and the subcontractor end. Multiple blockchain node components are interconnected to achieve a closed process loop. The on-chain evidence storage technology realizes the on-chain storage of information related to various projects, such as projects, entities, and contracts. The contract information is associated with the payment of funds to form a complete payment evidence chain. The payment record information at each layer is clear and traceable, effectively reducing the risk of misappropriation of key funds and forming substantive funds supervision. Optionally, the node component encryption of the blockchain node component to obtain the encrypted node component can be achieved through the SHA-512 encryption algorithm, the PBFT consensus algorithm, and the like.

[0149] In another embodiment of the present invention, the node component of the blockchain is encrypted to obtain the encrypted node component, including: constructing a padding bit of the blockchain node component, and increasing the message length after the padding bit to obtain a growth node component; and calculating the number of blocks of the growth node component using the following formula:

[0150]

[0151] Wherein, e represents the number of blocks, G represents the total length of the growth node component, and 512 represents the length of each block when the growth node component is divided into e blocks;

[0152] The growth node component is processed by block processing using the block number to obtain block node components; and information encoding is performed on the block node components to obtain the encrypted node components.

[0153] Optionally, the process of encoding the information of the block node component to obtain the encrypted node component refers to the process of inputting the block node component and the initialized link variable into a register, and using the register to call the value in the initialized link variable to modify the data of the block node component.

[0154] S5. Based on the stored evidence flow, the wages to be paid are cleared to obtain cleared wages, and a final wage audit is performed on the cleared wages to obtain final audited wages.

[0155] The embodiment of the present invention performs salary clearing for the party to be paid based on the stored evidence flow, so as to pay the salary to the employee's salary card, thereby paving the way for the subsequent review of the salary payment process.

[0156] In one embodiment of the present invention, based on the stored evidence flow, wages are cleared for the party to be paid to obtain cleared wages, including: constructing wage payment requirements of the stored evidence flow at the general contractor of the party to be paid; based on the wage payment requirements, transmitting the constructed wage payment instructions to the bank unit of the general contractor, and constructing a special account for wage payment of the party to be paid; based on the wage payment instructions and the special account for wage payment, paying the wages to the party to be paid at the bank unit to obtain the cleared wages.

[0157] Among them, the special account for wage payment refers to an account established by the project engineering unit for employees to store the pending wages of all employees; optionally, the general contractor issues payment requirements, and based on the payment requirements, the system sends a wage payment instruction to the bank. At the same time, the construction unit pays the labor costs and pays them to the bank's special account for migrant workers' wages. According to the system sending the wage payment instruction and the payment to the special account for employees' wages, the bank clears the funds and clears them into the employees' wage cards.

[0158] In one embodiment of the present invention, the final review of the cleared wages to obtain the final reviewed wages includes: issuing a wage receipt for the cleared wages, and transmitting the wage receipt to the general contractor corresponding to the cleared wages; signing and confirming the wage receipt at the general contractor to obtain a signed and confirmed receipt, and constructing a wage payment voucher and a bank payment journal for the signed and confirmed receipt; signing and confirming the wage payment voucher at the subcontractor corresponding to the general contractor to obtain a first confirmation result; signing and confirming the bank payment journal at the wage-to-be-paid party corresponding to the general contractor to obtain a second confirmation result; and using the signed and confirmed receipt, the first confirmation result, and the second confirmation result as the final reviewed wages.

[0159] S6. The real-name authentication information, the attendance information and the final audited salary are stored in a preset blockchain. In the preset blockchain, a visualized multi-dimensional report of the final audited salary is constructed. In combination with the visualized multi-dimensional report, the real-name authentication information and the attendance information, the abnormal funds of the final audited salary are audited to obtain an abnormal audit result.

[0160] The embodiment of the present invention stores the real-name authentication information, the attendance information and the final audited salary in a preset blockchain, so as to add blockchain as the underlying technology to the process of wage payment for infrastructure projects, serve the employee group, and effectively solve many drawbacks of the traditional model in the past.

[0161] In one embodiment of the present invention, the principle of storing the real-name authentication information, the attendance information and the final audited salary in a preset blockchain is similar to the principle of storing the payment evidence stream in a blockchain to obtain a stored evidence stream, and will not be further elaborated here.

[0162] In one embodiment of the present invention, constructing a visualized multi-dimensional report of the final audited salary in the preset blockchain includes: extracting the report base point and report structure of the final audited salary in the preset blockchain; constructing a multi-dimensional report of the final audited salary based on the report base point and the report structure; and visualizing the multi-dimensional report to obtain the visualized multi-dimensional report.

[0163] Among them, the report base point refers to the point referenced when constructing the report for the final audited salary. Under different report structures, the reference points are different. For example, under the tree structure report structure, the reference points are the root node and parent node of each tree; under the chain structure report structure, the reference point is the predecessor node. Exemplarily, based on the on-chain evidence storage technology, around the infrastructure project salary management platform and the infrastructure project salary supervision platform, an infrastructure project salary management system with unified capital flow and information flow, traceable application and payment process, and transparent salary approval and payment standards is built. This can solve the problems that have long plagued the infrastructure project salary supervision, such as the long chain of post-supervision penetration, the difficulty in ensuring the quality of supervision information, and the uneconomical supervision cost-benefit, avoid the occurrence of problems such as false reporting of unpaid wages and labor disputes, and protect the legitimate interests of both parties to the employment.

[0164] In one embodiment of the present invention, the combination of the visualized multi-dimensional report, the real-name authentication information and the attendance information to review the abnormal situation of the funds of the final audited salary and obtain the abnormal audit result includes: combining the visualized multi-dimensional report, the real-name authentication information and the attendance information, and using the following formula to calculate the expected value of the funds audit of the final audited salary:

[0165] P(Y)=p

[0166]

[0167] Wherein, E represents the expected value of the fund audit, w represents the length of a sampling time period for data sampling when detecting fund anomalies in the visualized multi-dimensional report, the real-name authentication information and the attendance information, T represents the total sampling time period, k represents the total number of time intervals that exceed the upper limit of fund transactions in a short period of time from i0 to i0+w-1, i0 represents the first time period of sampling, i represents the time period sequence number, and p represents Y j =1, Y represents the number of time intervals exceeding the upper limit of capital transactions in the short term, b k represents the binomial probability formula, where the time period contains multiple time intervals;

[0168] When the expected value of the fund audit is less than the preset expected value, a first abnormal audit result is obtained; when the expected value of the fund audit is not less than the preset expected value, overlapping data of the final audited salary is queried in the visualized multi-dimensional report, the real-name authentication information and the attendance information; based on the overlapping data, a second abnormal audit result of the final audited salary is identified.

[0169] S7. Combining the final audited salary with the abnormal audit result, the salary audit result under the engineering project is obtained.

[0170] It can be seen that the embodiment of the present invention first performs real-name authentication on the personnel information to ensure that the electronic information of the party to be paid is consistent with the actual facial information, thereby realizing the unified management of the electronic information of the party to be paid with the identity card. Furthermore, the embodiment of the present invention collects the attendance information of the real-name authentication information to count the wages of the party to be paid based on the daily attendance punch-in data of the party to be paid. Furthermore, the embodiment of the present invention calculates the payroll of the party to be paid by using the attendance information, so as to send the counted wage data to all parties of the project for review. The wage slip to be issued is subject to a three-party review, so that all parties involved in the wage payment process can review and confirm the wage results, thereby ensuring the openness of wage payment. Furthermore, the embodiment of the present invention analyzes the virtual wages of the party to be paid based on the real-name authentication information and the attendance information, so as to predict the employee wages using a machine learning model, thereby facilitating comparison with the actual calculated wages. Furthermore, the embodiment of the present invention constructs a payment evidence flow for the three-party review of wages, so as to record the entire wage payment process information, associate the project progress, employee attendance and employee wage calculation, and avoid false reporting of project progress. and misappropriation of funds, making the accumulated employee salary data clear and understandable, greatly avoiding false reporting of project progress. Furthermore, the embodiments of the present invention store the payment evidence flow on blockchain to use blockchain as the underlying technology in the process of project engineering salary payment to serve the employee group, which can effectively solve many drawbacks of the traditional model in the past, such as information asymmetry between entities, uncertainty of capital flow, imperfect management mechanism, etc., support online labor contract signing, ensure data security, non-tamperability and traceability, realize the on-chain storage of various engineering-related information such as projects, entities and contracts, and associate contract information with capital payment. A complete payment evidence chain is formed, and the payment record information of each layer is clear and traceable, which effectively reduces the risk of misappropriation of key funds and forms substantial fund supervision. The embodiment of the present invention clears the wages of the party to be paid based on the stored evidence flow, so as to pay the wages to the employee's salary card, paving the way for the subsequent review of the link of paying wages. The embodiment of the present invention stores the real-name authentication information, the attendance information and the final audited wages in the preset blockchain, so as to add the blockchain as the underlying technology to the process of wage payment of infrastructure projects, serve the employee group, and effectively solve many drawbacks of the traditional model in the past. Therefore, the intelligent wage audit method applied to engineering projects proposed in the embodiment of the present invention can reduce the wage audit loopholes under engineering projects.

[0171] like Figure 4 As shown, it is a functional module diagram of the intelligent wage auditing device of the present invention applied to engineering projects.

[0172] The intelligent wage audit device 400 applied to engineering projects of the present invention can be installed in an electronic device. According to the functions implemented, the intelligent wage audit device applied to engineering projects can include a wage calculation module 401, a blockchain storage module 402, a wage audit module 403, an abnormal audit module 404 and a result determination module 405. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0173] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0174] The salary calculation module 401 is used to obtain the personnel information of the party to be paid wages under the engineering project, perform real-name authentication on the personnel information to obtain real-name authentication information, collect attendance information of the real-name authentication information, and use the attendance information to calculate the payroll of the party to be paid wages;

[0175] The similarity calculation module 402 is used to perform a three-party review of the salary to be issued to obtain the three-party reviewed salary, perform a three-party review of the salary to be issued to obtain the three-party reviewed salary, analyze the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculate the salary similarity between the three-party reviewed salary and the virtual salary;

[0176] The step returns to module 403, which is used to return to the step of obtaining the personnel information of the party to be paid wages under the engineering project when the salary similarity is less than the preset similarity;

[0177] The blockchain storage module 404 is used to construct the payment evidence flow of the three-party review of the salary when the salary similarity is not less than the preset similarity, and store the payment evidence flow in the blockchain to obtain the storage evidence flow;

[0178] The salary review module 405 is used to clear the salary of the party to be paid based on the stored evidence flow to obtain cleared salary, and to conduct final salary review on the cleared salary to obtain final reviewed salary;

[0179] The abnormal audit module 406 is used to store the real-name authentication information, the attendance information and the final audited salary in a preset blockchain, and to construct a visual multi-dimensional report of the final audited salary in the preset blockchain, and to review the abnormal situation of the funds of the final audited salary in combination with the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormal audit result;

[0180] The result determination module 407 is used to combine the final audited salary with the abnormal audit result to obtain the salary audit result under the engineering project.

[0181] In detail, the modules in the intelligent wage audit device 400 for engineering projects in the embodiment of the present invention are used in the same manner as described above. Figures 1 to 3 The same technical means as described in the intelligent wage audit method applied to engineering projects can produce the same technical effects, so I will not go into details here.

[0182] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device for realizing the intelligent wage audit method applied to engineering projects according to the present invention.

[0183] The electronic device may include a processor 50, a memory 51, a communication bus 52 and a communication interface 53, and may also include a computer program stored in the memory 51 and executable on the processor 50, such as an intelligent salary audit program applied to engineering projects.

[0184] In some embodiments, the processor 50 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 50 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 51 (for example, executing a smart salary audit program for an engineering project, etc.), and calls data stored in the memory 51 to execute various functions of the electronic device and process data.

[0185] The memory 51 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 51 may be an internal storage unit of an electronic device in some embodiments, such as a mobile hard disk of the electronic device. The memory 51 may also be an external storage device of an electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 51 may also include both an internal storage unit of the electronic device and an external storage device. The memory 51 may not only be used to store application software and various types of data installed in the electronic device, such as the code of the database configuration connection program, but also be used to temporarily store data that has been output or is to be output.

[0186] The communication bus 52 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 51 and at least one processor 50, etc.

[0187] The communication interface 53 is used for communication between the above-mentioned electronic device 5 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0188] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0189] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 50 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0190] It should be understood that the embodiment is for illustrative purposes only and the scope of the patent invention is not limited to this structure.

[0191] The database configuration connection program stored in the memory 51 in the electronic device is a combination of multiple computer programs. When running in the processor 50, it can achieve:

[0192] Obtaining personnel information of the party to be paid wages under the project, performing real-name authentication on the personnel information to obtain real-name authentication information, collecting attendance information of the real-name authentication information, and using the attendance information to calculate the payroll to be paid of the party to be paid wages;

[0193] Conducting a three-party review of the payroll to be issued to obtain a three-party reviewed salary, analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculating the salary similarity between the three-party reviewed salary and the virtual salary;

[0194] When the salary similarity is less than the preset similarity, return to the above step of obtaining the personnel information of the party to be paid salary under the engineering project;

[0195] When the salary similarity is not less than a preset similarity, constructing a payment evidence flow for the three-party review of the salary, and performing blockchain storage on the payment evidence flow to obtain a storage evidence flow;

[0196] Based on the stored evidence flow, clearing the wages of the party to be paid to obtain cleared wages, and conducting a final review of the cleared wages to obtain final reviewed wages;

[0197] The real-name authentication information, the attendance information and the final audited salary are stored in a preset blockchain, a visual multi-dimensional report of the final audited salary is constructed in the preset blockchain, and the abnormal funds of the final audited salary are audited by combining the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormal audit result;

[0198] The final audited salary and the abnormal audit result are combined to obtain the salary audit result under the engineering project.

[0199] Specifically, the specific implementation method of the processor 50 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0200] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0201] The present invention further provides a storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0202] Obtaining personnel information of the party to be paid wages under the project, performing real-name authentication on the personnel information to obtain real-name authentication information, collecting attendance information of the real-name authentication information, and using the attendance information to calculate the payroll to be paid of the party to be paid wages;

[0203] Conducting a three-party review of the payroll to be issued to obtain a three-party reviewed salary, analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculating the salary similarity between the three-party reviewed salary and the virtual salary;

[0204] When the salary similarity is less than the preset similarity, return to the above step of obtaining the personnel information of the party to be paid salary under the engineering project;

[0205] When the salary similarity is not less than a preset similarity, constructing a payment evidence flow for the three-party review of the salary, and storing the payment evidence flow in blockchain to obtain a storage evidence flow;

[0206] Based on the stored evidence flow, clearing the wages of the party to be paid to obtain cleared wages, and conducting a final review of the cleared wages to obtain final reviewed wages;

[0207] The real-name authentication information, the attendance information and the final audited salary are stored in a preset blockchain, a visual multi-dimensional report of the final audited salary is constructed in the preset blockchain, and the abnormal funds of the final audited salary are audited by combining the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormal audit result;

[0208] The final audited salary and the abnormal audit result are combined to obtain the salary audit result under the engineering project.

[0209] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0210] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0212] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0213] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0214] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0215] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A smart salary audit method for engineering projects, characterized in that: The method comprises: Obtaining personnel information of the party to be paid wages under the project, performing real-name authentication on the personnel information to obtain real-name authentication information, collecting attendance information of the real-name authentication information, and using the attendance information to calculate the payroll to be paid of the party to be paid wages; Conducting a three-party review of the payroll to be issued to obtain a three-party reviewed salary, analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculating the salary similarity between the three-party reviewed salary and the virtual salary; When the salary similarity is less than the preset similarity, return to the above step of obtaining the personnel information of the party to be paid salary under the engineering project; When the salary similarity is not less than a preset similarity, constructing a payment evidence flow for the three-party review of the salary, and storing the payment evidence flow in blockchain to obtain a storage evidence flow; Based on the stored evidence flow, clearing the wages of the party to be paid to obtain cleared wages, and conducting a final review of the cleared wages to obtain final reviewed wages; The real-name authentication information, the attendance information and the final audited salary are stored in a preset blockchain, a visual multi-dimensional report of the final audited salary is constructed in the preset blockchain, and the abnormal funds of the final audited salary are audited by combining the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormal audit result; The final audited salary and the abnormal audit result are combined to obtain the salary audit result under the engineering project; The method of calculating the payroll of the party to be paid using the attendance information includes: Submitting a salary payment application to the general contractor of the party to be paid wages based on the attendance information; In the general contractor, according to the wage payment application, the labor wages of the party to be paid are calculated using the following formula: Wherein, m represents the labor wage, q represents the workload of the attendance information, p represents the unit price per unit workload, m1 represents the wage calculated according to the q*p method, u represents the daily wage, v represents the number of working days, m2 represents the wage calculated according to the u*v method, w represents the monthly fixed wage, m3 represents the wage calculated according to the w method, a represents the basic wage, b represents the performance, and m4 represents the wage calculated according to the a*b method; On the basis of the labor wages, query the increase or decrease of the wages of the party to be paid; Determine the payroll to be issued by combining the labor wages and the wage increase or decrease; The three-party review of the wages to be issued to obtain the three-party reviewed wages includes: Obtaining the payroll party, subcontractor and general contractor of the payroll to be issued, and sending the payroll to be issued to the payroll party, the subcontractor and the general contractor respectively; The wage signatures of the wage slips to be issued are respectively confirmed at the party to be paid, the subcontractor and the general contractor, and the results of the wage signature confirmation are used as the three-party audited wages; The analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information includes: Extracting a salary influencing factor from the real-name authentication information and the attendance information, and dividing the salary influencing factor into a parent factor and a child factor; The absolute value difference between the parent factor and the child factor is calculated using the following formula: L=|ms| Wherein, L represents the absolute value difference, m represents the parent factor after initialization and averaging, and s represents the child factor after initialization and averaging; Selecting a minimum value and a maximum value from the absolute value differences; According to the minimum value and the maximum value, the correlation coefficient of the wage influencing factor is calculated using the following formula: Wherein, ξ represents the correlation coefficient, x represents the salary influencing factor, a represents the minimum value, b represents the maximum value, and ρ represents the resolution coefficient, which is 0.5; According to the correlation coefficient, selecting a target influencing factor from the wage influencing factors; Based on the target impact factor, the mapping degree of the virtual salary is calculated using the following formula: Among them, β j represents the mapping degree, α h Represents the hidden layer data of the BP neural network, x i represents the value of the target impact factor, θ h represents the bias from the input layer to the hidden layer, v ih represents the weight from the input layer to the hidden layer, w hj represents the weight from the hidden layer to the output layer, θ j represents the bias from the hidden layer to the output layer, i represents the serial number of the target influencing factor, d represents the number of the target influencing factors, h represents the serial number of the hidden layer data, and q represents the number of the hidden layer data; According to the mapping degree, the virtual salary is calculated using the following formula: I=β j *F Among them, I represents the virtual salary, β j represents the mapping degree, and F represents a mapping function from the mapping degree to the virtual salary; The step of storing the payment evidence stream on a blockchain to obtain a stored evidence stream includes: Determining a timestamp of the payment evidence stream, and determining a blockchain node component of the payment evidence stream based on the timestamp; Encrypting the blockchain node component to obtain an encrypted node component; Performing vector encoding on the encrypted node component to obtain an encoded node component; The blockchain node number of the encoding node component is calculated using the following formula: H(k)=n*(f*k%1) Wherein, H(k) represents the blockchain serial number of the encoding node component, n represents the total number of nodes in the blockchain, f represents a randomly selected number, 0≤f<1, and k represents the encoding node component; Storing the encoded node component in the blockchain corresponding to the blockchain node serial number; The step of clearing the wages of the party to be paid based on the stored evidence flow to obtain cleared wages includes: Constructing the wage payment requirements of the storage evidence flow at the general contractor of the party to be paid wages; Based on the salary payment requirements, the constructed salary payment instruction is transmitted to the bank unit of the general contractor, and a special salary payment account for the party to be paid is established; Based on the salary payment instruction and the salary payment special account, the salary is paid to the salary payment party at the bank unit to obtain the cleared salary; The final review of the cleared wages to obtain the final reviewed wages includes: Issue a wage receipt for the cleared wages, and transmit the wage receipt to the general contractor corresponding to the cleared wages; The wage receipt is signed and confirmed at the general contractor to obtain a signed and confirmed receipt, and a wage voucher and a bank payment journal for the signed and confirmed receipt are constructed; The wage payment voucher is signed and confirmed at the subcontractor corresponding to the general contractor to obtain a first confirmation result; Sign and confirm the bank payment log at the party to be paid wages corresponding to the general contractor to obtain a second confirmation result; The signed confirmation receipt, the first confirmation result and the second confirmation result are used as the final audited salary; In the preset blockchain, a visualized multi-dimensional report of the final audited salary is constructed, including: In the preset blockchain, extract the report base point and report structure of the final audited salary; Based on the report base point and the report structure, construct a multi-dimensional report of the final audited salary; Performing report visualization on the multi-dimensional report to obtain the visualized multi-dimensional report; The combination of the visualized multi-dimensional report, the real-name authentication information and the attendance information is used to review the abnormal situation of the funds of the final audited salary to obtain the abnormal audit result, including: Combining the visualized multi-dimensional report, the real-name authentication information and the attendance information, the expected value of the final audited salary is calculated using the following formula: P(Y)=p Wherein, E represents the expected value of the fund audit, w represents the length of a sampling time period for data sampling when detecting fund anomalies in the visualized multi-dimensional report, the real-name authentication information and the attendance information, T represents the total sampling time period, k represents the total number of time intervals that exceed the upper limit of fund transactions in a short period of time from i0 to i0+w-1, i0 represents the first time period of sampling, i represents the time period sequence number, and p represents Y j =1, Y represents the number of time intervals exceeding the upper limit of capital transactions in the short term, b k represents the binomial probability formula, where the time period contains multiple time intervals; When the expected value of the fund audit is less than the preset expected value, a first abnormal audit result is obtained; When the expected value of the fund review is not less than the preset expected value, querying the overlapping data of the final reviewed salary in the visualized multi-dimensional report, the real-name authentication information and the attendance information; Based on the overlapping data, a second abnormal audit result of the final audited salary is identified.

2. The method according to claim 1, characterized in that The real-name authentication of the personnel information is performed to obtain the real-name authentication information, including: Searching for ID card information in the personnel data, and extracting the ID card photo from the ID card information; Collect on-site photos of the party to be paid wages corresponding to the personnel information; Extracting features from the ID card photo and the on-site photo respectively to obtain ID card features and on-site photo features; The feature similarity between the ID card feature and the on-site shooting feature is calculated using the following formula: Where S represents the feature similarity between the ID card feature and the on-site shooting feature, x i Represents the identity card characteristics, y i represents the on-site shooting feature, i represents the sequence number of the feature, and k represents the total number of features; When the feature similarity is greater than a preset similarity, a real-name authentication success mark of the personnel information corresponding to the feature similarity is constructed, and the real-name authentication success mark is combined with the personnel information to obtain the real-name authentication information.

3. An intelligent salary audit device used in engineering projects, characterized in that: The device comprises: The salary calculation module is used to obtain the personnel information of the party to be paid wages under the engineering project, perform real-name authentication on the personnel information to obtain the real-name authentication information, collect the attendance information of the real-name authentication information, and use the attendance information to calculate the payroll to be paid of the party to be paid wages; A similarity calculation module is used to perform a three-party review of the salary to be issued to obtain a three-party reviewed salary, perform a three-party review of the salary to be issued to obtain a three-party reviewed salary, analyze the virtual salary of the party to be paid based on the real-name authentication information and the attendance information, and calculate the salary similarity between the three-party reviewed salary and the virtual salary; A step return module, used for returning to the step of obtaining the personnel information of the party to be paid wages under the engineering project when the salary similarity is less than a preset similarity; A blockchain storage module, used for constructing a payment evidence flow of the three-party review of the salary when the salary similarity is not less than a preset similarity, storing the payment evidence flow in blockchain, and obtaining a storage evidence flow; A salary review module, configured to perform salary clearing for the party to be paid based on the stored evidence flow to obtain cleared salary, and perform final salary review on the cleared salary to obtain final reviewed salary; An abnormality audit module is used to store the real-name authentication information, the attendance information and the final audited salary in a preset blockchain, construct a visual multi-dimensional report of the final audited salary in the preset blockchain, and audit the abnormal funds of the final audited salary in combination with the visual multi-dimensional report, the real-name authentication information and the attendance information to obtain an abnormality audit result; A result determination module, used to combine the final audited salary with the abnormal audit result to obtain the salary audit result under the engineering project; The method of calculating the payroll of the party to be paid using the attendance information includes: Submitting a salary payment application to the general contractor of the party to be paid wages based on the attendance information; In the general contractor, according to the wage payment application, the labor wages of the party to be paid are calculated using the following formula: Wherein, m represents the labor wage, q represents the workload of the attendance information, p represents the unit price per unit workload, m1 represents the wage calculated according to the q*p method, u represents the daily wage, v represents the number of working days, m2 represents the wage calculated according to the u*v method, w represents the monthly fixed wage, m3 represents the wage calculated according to the w method, a represents the basic wage, b represents the performance, and m4 represents the wage calculated according to the a*b method; On the basis of the labor wages, query the increase or decrease of the wages of the party to be paid; Determine the payroll to be issued by combining the labor wages and the wage increase or decrease; The three-party review of the wages to be issued to obtain the three-party reviewed wages includes: Obtaining the payroll party, subcontractor and general contractor of the payroll to be issued, and sending the payroll to be issued to the payroll party, the subcontractor and the general contractor respectively; The wage signatures of the wage slips to be issued are respectively confirmed at the party to be paid, the subcontractor and the general contractor, and the results of the wage signature confirmation are used as the three-party audited wages; The analyzing the virtual salary of the party to be paid based on the real-name authentication information and the attendance information includes: Extracting a salary influencing factor from the real-name authentication information and the attendance information, and dividing the salary influencing factor into a parent factor and a child factor; The absolute value difference between the parent factor and the child factor is calculated using the following formula: L=|ms| Wherein, L represents the absolute value difference, m represents the parent factor after initialization and averaging, and s represents the child factor after initialization and averaging; Selecting a minimum value and a maximum value from the absolute value differences; According to the minimum value and the maximum value, the correlation coefficient of the wage influencing factor is calculated using the following formula: Wherein, ξ represents the correlation coefficient, x represents the salary influencing factor, a represents the minimum value, b represents the maximum value, and ρ represents the resolution coefficient, which is 0.5; According to the correlation coefficient, selecting a target influencing factor from the wage influencing factors; Based on the target impact factor, the mapping degree of the virtual salary is calculated using the following formula: Among them, β j represents the mapping degree, α h Represents the hidden layer data of the BP neural network, x i represents the value of the target impact factor, θ h represents the bias from the input layer to the hidden layer, v ih represents the weight from the input layer to the hidden layer, w hj represents the weight from the hidden layer to the output layer, θ j represents the bias from the hidden layer to the output layer, i represents the serial number of the target influencing factor, d represents the number of the target influencing factors, h represents the serial number of the hidden layer data, and q represents the number of the hidden layer data; According to the mapping degree, the virtual salary is calculated using the following formula: I=β j *F Among them, I represents the virtual salary, β j represents the mapping degree, and F represents a mapping function from the mapping degree to the virtual salary; The step of storing the payment evidence stream on a blockchain to obtain a stored evidence stream includes: Determining a timestamp of the payment evidence stream, and determining a blockchain node component of the payment evidence stream based on the timestamp; Encrypting the blockchain node component to obtain an encrypted node component; Performing vector encoding on the encrypted node component to obtain an encoded node component; The blockchain node number of the encoding node component is calculated using the following formula: H(k)=n*(f*k%1) Wherein, H(k) represents the blockchain serial number of the encoding node component, n represents the total number of nodes in the blockchain, f represents a randomly selected number, 0≤f<1, and k represents the encoding node component; Storing the encoded node component in the blockchain corresponding to the blockchain node serial number; The step of clearing the wages of the party to be paid based on the stored evidence flow to obtain cleared wages includes: Constructing the wage payment requirements of the storage evidence flow at the general contractor of the party to be paid wages; Based on the salary payment requirements, the constructed salary payment instruction is transmitted to the bank unit of the general contractor, and a special salary payment account for the party to be paid is established; Based on the salary payment instruction and the salary payment special account, the salary is paid to the salary payment party at the bank unit to obtain the cleared salary; The final review of the cleared wages to obtain the final reviewed wages includes: Issue a wage receipt for the cleared wages, and transmit the wage receipt to the general contractor corresponding to the cleared wages; The wage receipt is signed and confirmed at the general contractor to obtain a signed and confirmed receipt, and a wage voucher and a bank payment journal for the signed and confirmed receipt are constructed; The wage payment voucher is signed and confirmed at the subcontractor corresponding to the general contractor to obtain a first confirmation result; Sign and confirm the bank payment log at the party to be paid wages corresponding to the general contractor to obtain a second confirmation result; The signed confirmation receipt, the first confirmation result and the second confirmation result are used as the final audited salary; In the preset blockchain, a visualized multi-dimensional report of the final audited salary is constructed, including: In the preset blockchain, extract the report base point and report structure of the final audited salary; Based on the report base point and the report structure, construct a multi-dimensional report of the final audited salary; Performing report visualization on the multi-dimensional report to obtain the visualized multi-dimensional report; The combination of the visualized multi-dimensional report, the real-name authentication information and the attendance information is used to review the abnormal situation of the funds of the final audited salary to obtain the abnormal audit result, including: Combining the visualized multi-dimensional report, the real-name authentication information and the attendance information, the expected value of the final audited salary is calculated using the following formula: P(Y)=p Wherein, E represents the expected value of the fund audit, w represents the length of a sampling time period for data sampling when detecting fund anomalies in the visualized multi-dimensional report, the real-name authentication information and the attendance information, T represents the total sampling time period, k represents the total number of time intervals that exceed the upper limit of fund transactions in a short period of time from i0 to i0+w-1, i0 represents the first time period of sampling, i represents the time period sequence number, and p represents Y j =1, Y represents the number of time intervals exceeding the upper limit of capital transactions in the short term, b k represents the binomial probability formula, where the time period contains multiple time intervals; When the expected value of the fund audit is less than the preset expected value, a first abnormal audit result is obtained; When the expected value of the fund review is not less than the preset expected value, querying the overlapping data of the final reviewed salary in the visualized multi-dimensional report, the real-name authentication information and the attendance information; Based on the overlapping data, a second abnormal audit result of the final audited salary is identified.

4. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent wage audit method applied to engineering projects as described in any one of claims 1 to 2.

5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent wage audit method applied to an engineering project as described in any one of claims 1 to 2 is implemented.

Images