Information management system based on financial operation data in medical industry

Abstract

The invention relates to an information management system based on medical industry financial operation data, and belongs to the technical field of financial information management. The system comprises a data transmission module which is used for obtaining a financial activity data set and transmitting the financial activity data set to a financial comprehensive accounting system through a data transmission model according to the financial activity data set; the time sequence adding module is used for obtaining financial operation data and obtaining financial activity time sequence data and financial operation time sequence data by adding timestamps according to the financial activity data set and the financial operation data; the data merging module is used for merging the financial activity time series data and the financial operation time series data to obtain a financial risk data set; the risk estimation module is used for obtaining risk early warning data through a financial risk estimation model according to the financial risk data set; and the budget optimization module is used for constructing a budget optimization model according to the risk early warning data, and obtaining financial budget optimization through solving according to the budget optimization model. And financial operation data information management is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial information management, and in particular relates to an information management system based on financial operation data of the medical industry. Background Art

[0002] In recent years, with the rapid development of information technologies such as big data, cloud computing, and the Internet of Things, the informatization of the medical field has ushered in a period of vigorous development. Against this background, the construction of hospital financial management informatization is particularly important. It can not only improve the level of refined management and work efficiency, but also ensure financial security and prevent potential risks. It plays an important role in promoting the modernization and scientificization of hospital management. Using big data and advanced data analysis tools, hospitals can conduct in-depth analysis of financial data and provide a scientific basis for management decisions. This data-driven decision-making model makes hospital financial management more accurate and forward-looking, which helps to optimize resource allocation, reduce operating costs, and improve financial benefits.

[0003] Although the hospital has established an information management system, there is a widespread problem of information islands. The functional subsystems are independent of each other and lack cross-departmental data sharing and linkage mechanisms. At the same time, the existing system is difficult to support the comprehensive analysis and deep mining of multi-dimensional financial data, and cannot meet the hospital's refined management and scientific decision-making. Therefore, the hospital urgently needs an intelligent and comprehensive information management system that can achieve deep integration of multi-dimensional data, provide intelligent financial risk estimation and optimize budget allocation, and improve hospital operating efficiency and service quality. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides an information management system based on financial operation data of the medical industry. The purpose of the present invention can be achieved through the following technical solutions: An information management system based on financial operation data of the medical industry, including a data transmission module, a time series addition module, a data merging module, a risk estimation module, and a budget optimization module: The data transmission module is used to obtain a financial activity data set and transmit it to a financial comprehensive accounting system through a data transmission model according to the financial activity data set; The time series adding module is used to obtain financial operation data and obtain financial activity time series data and financial operation time series data by adding timestamps according to the financial activity data set and the financial operation data; The data merging module is used to obtain a financial risk data set by merging the financial activity time series data and the financial operation time series data; The risk estimation module is used to obtain risk warning data according to the financial risk data set through a financial risk estimation model; The budget optimization module is used to construct a budget optimization model according to the risk warning data, and obtain financial budget optimization by solving the budget optimization model.

[0005] Preferably, the transmitting of the financial activity data set to the financial comprehensive accounting system through a data transmission model comprises: Encrypting the financial activity data set through a symmetric key encryption mechanism to obtain encrypted patient charge data, encrypted contract revenue data, encrypted material purchase data, encrypted salary data, and encrypted department cost data; According to the patient charge encrypted data, the contract income encrypted data, the material purchase encrypted data, the salary encrypted data, and the department cost encrypted data, data is divided into blocks to obtain grouped transmission data; By transmitting the packet transmission data to the financial comprehensive accounting system; Obtaining transmission decrypted data by data decryption according to the packet transmission data; The financial activity data set is obtained by performing a data integrity check on the transmitted decrypted data using a data integrity check function.

[0006] Preferably, obtaining risk warning data according to the financial risk data set through a financial risk estimation model includes: Obtaining financial risk decomposition data through an associated deconstruction model according to the financial risk data set; Obtaining complete data features of financial risk through a feature extraction model based on the financial risk decomposition data; The risk warning data is obtained through a linear layer according to the complete data characteristics of the financial risk.

[0007] Preferably, obtaining financial risk decomposition data through an associative deconstruction model according to the financial risk data set includes: Obtaining long-term risk factors, cyclical fluctuation factors, and random disturbance factors through a time series deconstruction model according to the financial risk data set; Obtaining time series propagation information through forward propagation according to the periodic fluctuation factor; Obtaining deep mining information through a deep mining model according to the periodic fluctuation factor; The financial risk decomposition data is obtained by combining the long-term risk factors and the deep mining information.

[0008] Preferably, the long-term risk factor, the cyclical fluctuation factor, and the random disturbance factor obtained by using a time series deconstruction model according to the financial risk data set include: Obtaining financial risk frequency domain data through fast Fourier transform according to the financial risk data set; Obtaining financial risk high-frequency data and financial risk low-frequency data through frequency decomposition according to the financial risk frequency domain data; The long-term risk factor, the cyclical fluctuation factor and the random disturbance factor are obtained by fast Fourier inverse transform according to the financial risk high-frequency data and the financial risk low-frequency data.

[0009] Preferably, obtaining the deep mining information through the deep mining model according to the periodic fluctuation factor includes: Obtaining a periodic amplitude through an attention mechanism according to the periodic fluctuation factor; Obtaining a periodic term by period encoding according to the periodic amplitude; The deep mining information is obtained by dimension conversion according to the periodic items.

[0010] Preferably, obtaining the complete data features of financial risk through a feature extraction model based on the financial risk decomposition data includes: Obtaining appropriate dimensional data for financial risk decomposition through dimensional conversion according to the financial risk decomposition data; Preset a convolution kernel, and obtain an initialized convolution kernel through linear interpolation, initialization, and normalization processing according to the convolution kernel; Decomposing the appropriate dimension data according to the financial risk to obtain the data to be convolved through the transformation model; The transformation model is expressed as: , Wherein, Fmin represents the transformation model, α1 and α2 are adaptive fusion parameters, F(X) represents Fourier transform, D(X) represents discrete cosine transform, and X represents the appropriate dimension data for financial risk decomposition; Performing a convolution operation on the data to be convolved through the initialized convolution kernel to obtain Fourier convolution data; Obtaining convolution data by inverse Fourier transform calculation according to the Fourier convolution data; Obtaining global feature information through an activation function according to the convolution data and the financial risk decomposition data; Obtaining local feature information through the PatchTST model according to the financial risk decomposition data; Obtaining complete feature data by splicing the global feature information and the local feature information; Obtaining a Pearson correlation weight by Pearson correlation calculation according to the complete feature data; Obtaining an attention weight through an attention mechanism according to the complete feature data; Obtaining a comprehensive weight by comprehensive weight calculation according to the attention weight and the Pearson correlation weight; The comprehensive weight calculation expression is: , in, W is the comprehensive weight, s is a trainable gating parameter, w a is the attention weight, w p is the Pearson correlation weight; The complete data characteristics of the financial risk are obtained by multiplying the comprehensive weight and the complete characteristic data.

[0011] Preferably, the step of constructing a budget optimization model according to the risk warning data and obtaining financial budget optimization by solving the budget optimization model through a solver includes: The budget optimization model expression is: , in, minutes Indicates taking the minimum value, Z represents the comprehensive optimization target, which is the weighted sum of expected loss and risk cost. α、β is the weight coefficient, i represents the i-th risk warning data, N Indicates the number of risk warning data. p i represents the risk probability distribution, L i (x i ) represents the expected loss function of the ith risk warning data under the allocated budget, C i (x i ) represents the risk cost function of the i-th risk warning data under the allocated budget, x i To allocate budget, c i represents the unit cost of the i-th risk warning data, B is the total budget, It represents the maximum loss value when there is no budget investment. c i is the cost growth factor, l i is the coefficient.

[0012] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the information management system based on financial operation data of the medical industry is implemented.

[0013] A storage medium containing computer executable instructions, which are used to execute the above-mentioned information management system based on financial operation data of the medical industry when executed by a computer processor.

[0014] The beneficial effects of the present invention are: (1) Through data encryption, packet transmission, integrity verification and timing processing, the secure transmission and efficient integration of financial data such as patient charges, contract income, material procurement, and salaries can be achieved, which facilitates the comprehensive accounting of the financial comprehensive accounting system and improves the efficiency of financial management.

[0015] (2) By constructing a financial risk data set and adopting a time series deconstruction model, feature extraction model and deep mining mechanism, we can comprehensively extract risk trends, seasonal patterns and noise characteristics, achieve accurate prediction and multi-dimensional analysis of financial risks, and provide a scientific basis for budget optimization.

[0016] (3) By comprehensively optimizing the objective function and combining the weighted minimization strategy of expected loss and risk cost, a scientific budget allocation plan is generated using the solver to achieve the rational allocation of financial resources, reduce risk costs, and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 The present invention is a flowchart of an information management system based on financial operation data of the medical industry. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0020] See also Figure 1 , an information management system based on financial operation data of the medical industry, including data transmission module, time series addition module, data merging module, risk estimation module, and budget optimization module: The data transmission module is used to obtain a financial activity data set and transmit it to a financial comprehensive accounting system through a data transmission model according to the financial activity data set; The time series adding module is used to obtain financial operation data and obtain financial activity time series data and financial operation time series data by adding timestamps according to the financial activity data set and the financial operation data; The data merging module is used to obtain a financial risk data set by merging the financial activity time series data and the financial operation time series data; The risk estimation module is used to obtain risk warning data according to the financial risk data set through a financial risk estimation model; The budget optimization module is used to construct a budget optimization model according to the risk warning data, and obtain financial budget optimization by solving the budget optimization model.

[0021] Specifically, the financial activity data set includes patient expense data, contract revenue data, material purchase data, salary data, and department expenditure data.

[0022] Specifically, the transmitting the financial activity data set to the financial comprehensive accounting system through the data transmission model includes: S101: Encrypt the financial activity data set through a symmetric key encryption mechanism to obtain encrypted patient charge data, encrypted contract revenue data, encrypted material purchase data, encrypted salary data, and encrypted department cost data; S102: Obtaining grouped transmission data by data block division according to the patient charge encrypted data, the contract income encrypted data, the material purchase encrypted data, the salary encrypted data, and the department cost encrypted data; S103: transmitting the packet transmission data to the financial comprehensive accounting system; S104: Decrypting the packet transmission data to obtain transmission decrypted data; S105: Performing data integrity verification through a data integrity verification function according to the transmission decrypted data to obtain the financial activity data set; The data integrity check function is expressed as: , in, Checksum is the data integrity check function, decrypted_data decrypting data for said transmission, checksum_value The correct data includes the financial activity data set.

[0023] Specifically, obtaining risk warning data through a financial risk estimation model according to the financial risk data set includes: S401: Obtaining financial risk decomposition data through an associated deconstruction model according to the financial risk data set; S402: Obtaining complete data features of financial risk through a feature extraction model according to the financial risk decomposition data; S403: Obtain the risk warning data through a linear layer according to the complete data characteristics of the financial risk.

[0024] Specifically, the association deconstruction model includes: S401-1: Obtaining long-term risk factors, cyclical fluctuation factors, and random disturbance factors through a time series deconstruction model according to the financial risk data set; S401-2: Obtaining time series propagation information through forward propagation according to the periodic fluctuation factor; S401-3: Obtaining deep mining information through a deep mining model according to the periodic fluctuation factor; S401-4: The financial risk decomposition data is obtained by combining the long-term risk factors and the deep mining information.

[0025] Specifically, the time series deconstruction model includes: Obtaining financial risk frequency domain data through fast Fourier transform according to the financial risk data set; Obtaining financial risk high-frequency data and financial risk low-frequency data through frequency decomposition according to the financial risk frequency domain data; The frequency decomposition is expressed as: , in, is the low-frequency data of financial risk, is the high-frequency data of financial risks, ZeroPad represents a zero-fill operation, X(f) represents the financial risk dataset, X low (f) is the low-frequency frequency domain data, W low (f) is a low-frequency window function, wherein the low-frequency window function defines a low-frequency range, X high (f) is the high frequency domain data, W high (f) is a high frequency window function, wherein the high frequency window function defines a high frequency range; The long-term risk factor, the cyclical fluctuation factor and the random disturbance factor are obtained by fast Fourier inverse transform according to the financial risk high-frequency data and the financial risk low-frequency data.

[0026] Specifically, the deep mining model includes: Obtaining a periodic amplitude through an attention mechanism according to the periodic fluctuation factor; Obtaining a periodic term by period encoding according to the periodic amplitude; The deep mining information is obtained by dimension conversion according to the periodic items.

[0027] Specifically, the feature extraction model includes: S402-1: Obtaining appropriate dimension data for financial risk decomposition through dimension conversion according to the financial risk decomposition data; S402-2: Preset a convolution kernel, and obtain an initialized convolution kernel by linear interpolation, initialization, and normalization according to the convolution kernel; S402-3: Decomposing the appropriate dimension data according to the financial risk to obtain Fourier data through a transformation model; The transformation model is expressed as: , Wherein, Fmin represents the transformation model, α1 and α2 are adaptive fusion parameters, F(X) represents Fourier transform, D(X) represents discrete cosine transform, and X represents the appropriate dimension data for financial risk decomposition; S402-4: performing a convolution operation on the data to be convolved through the initialized convolution kernel to obtain Fourier convolution data; S402-5: Obtain convolution data by performing inverse Fourier transform calculation according to the Fourier convolution data; S402-6: Obtaining global feature information through an activation function according to the convolution data and the financial risk decomposition data; S402-7: Obtaining local feature information through the PatchTST model according to the financial risk decomposition data; S402-8: Obtaining complete feature data by splicing the global feature information and the local feature information; S402-9: Obtaining a Pearson correlation weight by performing Pearson correlation calculation according to the complete feature data; The Pearson correlation calculation expression is: , Wherein, corr_weights is the Pearson correlation weight, softmax is the activation function, cor_coeff represents the Pearson correlation coefficient between features, matrix represents the inner product between features, nor represents the norm of the feature, and le-8 is a constant; S402-10: Obtaining an attention weight through an attention mechanism according to the complete feature data; S402-11: Obtaining a comprehensive weight by comprehensive weight calculation according to the attention weight and the Pearson correlation weight; The comprehensive weight calculation expression is: , in, W is the comprehensive weight, s is a trainable gating parameter, w a is the attention weight, w p is the Pearson correlation weight; S402-12: Obtain the complete data characteristics of the financial risk by multiplying the comprehensive weight and the complete characteristic data.

[0028] In this embodiment, the optimizer selected is Adam, the learning rate is 0.0001, the training rounds are 100 times, the batch size is 128, and the loss function is the mean square error loss function.

[0029] Specifically, the building of a budget optimization model according to the risk warning data, and obtaining financial budget optimization by solving the budget optimization model through a solver include: The budget optimization model expression is: , in, minutes Indicates taking the minimum value, Z represents the comprehensive optimization target, which is the weighted sum of expected loss and risk cost. α、β is the weight coefficient, i represents the i-th risk warning data, N Indicates the number of risk warning data. p i represents the risk probability distribution, L i (x i ) represents the expected loss function of the ith risk warning data under the allocated budget, C i (x i ) represents the risk cost function of the i-th risk warning data under the allocated budget, x i To allocate budget, c i represents the unit cost of the i-th risk warning data, B is the total budget, It represents the maximum loss value when there is no budget investment. c i is the cost growth factor, l i is the coefficient.

[0030] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0031] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0032] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0033] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An information management system based on financial operation data of the medical industry, characterized in that: Including data transmission module, time series addition module, data merging module, risk estimation module, and budget optimization module: The data transmission module is used to obtain a financial activity data set and transmit it to a financial comprehensive accounting system through a data transmission model according to the financial activity data set; The time series adding module is used to obtain financial operation data and obtain financial activity time series data and financial operation time series data by adding timestamps according to the financial activity data set and the financial operation data; The data merging module is used to obtain a financial risk data set by merging the financial activity time series data and the financial operation time series data; The risk estimation module is used to obtain risk warning data according to the financial risk data set through a financial risk estimation model; The budget optimization module is used to construct a budget optimization model according to the risk warning data, and obtain financial budget optimization by solving the budget optimization model.

2. The information management system based on medical industry financial operation data according to claim 1 is characterized in that: The transmitting of the financial activity data set to the financial comprehensive accounting system through the data transmission model includes: Encrypting the financial activity data set through a symmetric key encryption mechanism to obtain encrypted patient charge data, encrypted contract revenue data, encrypted material purchase data, encrypted salary data, and encrypted department cost data; According to the patient charge encrypted data, the contract income encrypted data, the material purchase encrypted data, the salary encrypted data, and the department cost encrypted data, data is divided into blocks to obtain grouped transmission data; By transmitting the packet transmission data to the financial comprehensive accounting system; Obtaining transmission decrypted data by data decryption according to the packet transmission data; The financial activity data set is obtained by performing a data integrity check on the transmitted decrypted data using a data integrity check function.

3. The information management system based on medical industry financial operation data according to claim 1 is characterized in that: The risk warning data obtained by using a financial risk estimation model according to the financial risk data set includes: Obtaining financial risk decomposition data through an associated deconstruction model according to the financial risk data set; Obtaining complete data features of financial risk through a feature extraction model based on the financial risk decomposition data; The risk warning data is obtained through a linear layer according to the complete data characteristics of the financial risk.

4. The information management system based on medical industry financial operation data according to claim 3 is characterized in that: The obtaining of financial risk decomposition data through an associated deconstruction model according to the financial risk data set includes: Obtaining long-term risk factors, cyclical fluctuation factors, and random disturbance factors through a time series deconstruction model according to the financial risk data set; Obtaining time series propagation information through forward propagation according to the periodic fluctuation factor; Obtaining deep mining information through a deep mining model according to the periodic fluctuation factor; The financial risk decomposition data is obtained by combining the long-term risk factors and the deep mining information.

5. The information management system based on medical industry financial operation data according to claim 4 is characterized in that: The long-term risk factors, cyclical fluctuation factors, and random disturbance factors obtained by using a time series deconstruction model according to the financial risk data set include: Obtaining financial risk frequency domain data through fast Fourier transform according to the financial risk data set; Obtaining financial risk high-frequency data and financial risk low-frequency data through frequency decomposition according to the financial risk frequency domain data; The long-term risk factor, the cyclical fluctuation factor and the random disturbance factor are obtained by fast Fourier inverse transform according to the financial risk high-frequency data and the financial risk low-frequency data.

6. The information management system based on financial operation data of the medical industry according to claim 4 is characterized in that: The step of obtaining the deep mining information through the deep mining model according to the periodic fluctuation factor includes: Obtaining a periodic amplitude through an attention mechanism according to the periodic fluctuation factor; Obtaining a periodic term by period encoding according to the periodic amplitude; The deep mining information is obtained by dimension conversion according to the periodic items.

7. The information management system based on medical industry financial operation data according to claim 3 is characterized in that: The complete data features of financial risk obtained by the feature extraction model according to the financial risk decomposition data include: Obtaining appropriate dimensional data for financial risk decomposition through dimensional conversion according to the financial risk decomposition data; Preset a convolution kernel, and obtain an initialized convolution kernel through linear interpolation, initialization, and normalization processing according to the convolution kernel; Decomposing the appropriate dimension data according to the financial risk to obtain the data to be convolved through the transformation model; The transformation model is expressed as: ， Wherein, Fmin represents the transformation model, α1 and α2 are adaptive fusion parameters, F(X) represents Fourier transform, D(X) represents discrete cosine transform, and X represents the appropriate dimension data for financial risk decomposition; Performing a convolution operation on the data to be convolved through the initialized convolution kernel to obtain Fourier convolution data; Obtaining convolution data by inverse Fourier transform calculation according to the Fourier convolution data; Obtaining global feature information through an activation function according to the convolution data and the financial risk decomposition data; Obtaining local feature information through the PatchTST model according to the financial risk decomposition data; Obtaining complete feature data by splicing the global feature information and the local feature information; Obtaining a Pearson correlation weight by Pearson correlation calculation according to the complete feature data; Obtaining an attention weight through an attention mechanism according to the complete feature data; Obtaining a comprehensive weight by comprehensive weight calculation according to the attention weight and the Pearson correlation weight; The comprehensive weight calculation expression is: ， in, W is the comprehensive weight, σ is a trainable gating parameter, w a is the attention weight, w p is the Pearson correlation weight; The complete data characteristics of the financial risk are obtained by multiplying the comprehensive weight and the complete characteristic data.

8. The information management system based on medical industry financial operation data according to claim 1 is characterized in that: The step of constructing a budget optimization model according to the risk warning data and solving the budget optimization model by a solver to obtain a financial budget optimization comprises: The budget optimization model expression is: ， in, min Indicates taking the minimum value, Z represents the comprehensive optimization target, which is the weighted sum of expected loss and risk cost. α、β is the weight coefficient, i represents the i-th risk warning data, N Indicates the number of risk warning data. p i represents the risk probability distribution, L i (x i ) represents the expected loss function of the i-th risk warning data under the allocated budget, C i (x i ) represents the risk cost function of the i-th risk warning data under the allocated budget, x i To allocate budget, c i represents the unit cost of the ith risk warning data, B is the total budget, It represents the maximum loss value when there is no budget investment. γ i is the cost growth factor, λ i is the coefficient.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, an information management system based on financial operation data of the medical industry as described in any one of claims 1-8 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the information management system based on financial operation data of the medical industry as described in any one of claims 1-8 when executed by a computer processor.

Images