A hospital business-based cost accounting management system

Abstract

The application relates to a hospital business-based cost accounting management system, which comprises an index extraction module, a formula configuration module and a distribution module.The index extraction module is used for extracting index data of calculation items in a dynamic formula corresponding to n-level cost distribution according to first instruction information input by a user in a third-party data source; the formula configuration module is used for obtaining final results of the calculation items in the dynamic formula corresponding to the n-level cost distribution according to the index data and a calculation priority order obtained in advance; and the distribution module is used for obtaining a result of the n-level cost distribution based on the dynamic formula corresponding to the n-level cost distribution, the final results of the calculation items in the dynamic formula corresponding to the n-level cost distribution, the calculation items in the dynamic formula corresponding to the n-level cost distribution and the index data.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to a cost accounting management system based on hospital operations. Background Technology

[0002] The existing cost accounting system mainly includes the following basic operations: acquiring data from the financial system; allocating data; and summarizing (or exporting) data.

[0003] Regarding the basic operations described above, the industry practice is as follows: Obtain data from the financial system: After exporting the data from the financial system, import it into the cost accounting system using Points of Interest (POIs) or by interface with the financial system to retrieve the basic allocation data. The acquired data is then converted to standard encoding, cleaned, and used as the basis for calculations in the cost accounting system. However, the financial system's indicators are limited, process data is incomplete, and real-time data acquisition is not achieved.

[0004] Cost allocation calculation relies entirely on the maintenance of basic indicator data, such as configuring fixed calculation formulas to achieve cost allocation (most hospitals on the market use level 3). The business data included in the allocation calculation is periodically summarized by relevant departments and added to the cost accounting system. The resulting data often deviates significantly from the actual data of each department within the hospital, lacking accuracy. The calculation process is executed after all data from each stage is obtained. During the allocation process, the execution time of the basic indicators included in the formula is directly added together, making the calculation time-consuming. The allocated data is then summarized by level, department, disease type, etc., and presented in a page view or report format. However, the allocated data cannot be used as parameters in other calculations, and its allocation method is relatively fixed. Therefore, currently available cost accounting systems do not have cost estimation functions. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a cost accounting management system based on hospital operations, which solves the technical problem that the cost accounting system in the prior art cannot perform cost estimation.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0009] This invention provides a cost accounting management system based on hospital operations, comprising:

[0010] The indicator extraction module is used to extract indicator data from a third-party data source based on the first instruction information input by the user, which is a pre-set indicator data of the calculation item in the dynamic formula corresponding to the n-level cost allocation.

[0011] The formula configuration module is used to obtain the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation based on the indicator data and the pre-acquired calculation priority order.

[0012] The allocation module is used to obtain the result of the n-level cost allocation based on the dynamic formula corresponding to the n-level cost allocation, the final result of the calculation items in the dynamic formula corresponding to the n-level cost allocation, the calculation items in the dynamic formula corresponding to the n-level cost allocation, and the indicator data.

[0013] Preferably, the cost accounting management system based on hospital operations further includes:

[0014] The cost estimation module, based on the results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series estimation model (TFT model) to obtain the results of the n+1-level cost allocation within a preset time period.

[0015] Preferably, the indicator extraction module extracts indicator data from a third-party data source based on the first instruction information input by the user, specifically including:

[0016] The indicator extraction module obtains the first instruction information input by the user; the first instruction information is to extract indicator data from a third-party data source, which is the calculation item in the dynamic formula corresponding to the n-level cost allocation.

[0017] The indicator extraction module determines whether the preset extraction conditions are met. If they are met, it extracts the indicator data of the calculation items in the dynamic formula corresponding to the n-level cost allocation from the third-party data source and saves the indicator data.

[0018] Preferably,

[0019] The pre-set extraction conditions are: the indicator extraction module receives a manually triggered extraction button from the user, or a pre-set time point is reached, or the first condition is met.

[0020] The first condition is that the calculation terms in the dynamic formula corresponding to the n-level cost allocation meet the time point at which they are calculated.

[0021] Preferably, the formula configuration module obtains the final result of the calculation item in the dynamic formula based on the indicator data and the pre-acquired calculation priority order, specifically including:

[0022] The formula configuration module verifies the indicator data, obtains qualified indicator data, and puts the qualified indicator data into the message queue MQ.

[0023] The formula configuration module monitors the qualified indicator data in the message queue MQ in real time and determines whether the pre-obtained calculation priority order is met. If it is met, the qualified indicator data in the message queue MQ is used to calculate the calculation item until all qualified indicator data in the message queue MQ has been calculated, and the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation is obtained.

[0024] Preferably,

[0025] The calculation priority order is determined in advance based on the calculation items in the pre-set dynamic formula corresponding to the n-level cost allocation and the pre-defined allocation level corresponding to the calculation items.

[0026] Preferably, the cost estimation module, based on the results of the n-level cost allocation and a pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series prediction model (TFT) to obtain the results of the n+1-level cost allocation within a preset time period, specifically including:

[0027] The results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation are input into the input layer of the pre-trained time series prediction model (TFT) to obtain the allocation results of the n+1 level.

[0028] Preferably,

[0029] The pre-trained time series prediction model TFT model is: a time series prediction model TFT model pre-trained using historical n-level amortization results training data of the nth level, and the resulting model.

[0030] Preferably,

[0031] The indicator extraction module is also used to collect historical data of the results of the nth level cost allocation based on the second instruction information input by the user.

[0032] The second indication information is the historical data of the results of cost allocation at level n collected by the indicator extraction module.

[0033] Preferably,

[0034] The cost estimation module is also used to accept historical data of the nth level cost allocation results input by the user, and input the historical data of the nth level cost allocation results into the trained estimation model TFT model. The trained estimation model TFT model outputs the nth level cost allocation results for the estimated time period.

[0035] (III) Beneficial Effects

[0036] The beneficial effects of this invention are as follows: The cost accounting management system based on hospital operations employs an indicator extraction module. Based on the first instruction information input by the user, it extracts pre-set indicator data from a third-party data source for the calculation items in the dynamic formula corresponding to n-level cost allocation. The formula configuration module, based on the indicator data and a pre-acquired calculation priority order, obtains the final result of the calculation items in the dynamic formula corresponding to n-level cost allocation. The allocation module, based on the dynamic formula corresponding to n-level cost allocation, the final result of the calculation items in the dynamic formula corresponding to n-level cost allocation, the calculation items in the dynamic formula corresponding to n-level cost allocation, and the indicator data, obtains the result of n-level cost allocation. Compared to existing technologies, this system can perform cost estimation for n-level cost allocation, thus improving work efficiency. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the structure of a cost accounting management system based on hospital operations according to the present invention;

[0038] Figure 2 This is a schematic diagram of a cost accounting management system based on hospital operations in an embodiment of the present invention. Detailed Implementation

[0039] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0041] Example 1

[0042] See Figure 1 This embodiment provides a cost accounting management system based on hospital operations, including:

[0043] The indicator extraction module is used to extract indicator data from a third-party data source based on the first instruction information input by the user, which is a pre-set indicator data of the calculation item in the dynamic formula corresponding to the n-level cost allocation.

[0044] The formula configuration module is used to obtain the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation based on the indicator data and the pre-acquired calculation priority order.

[0045] The allocation module is used to obtain the result of the n-level cost allocation based on the dynamic formula corresponding to the n-level cost allocation, the final result of the calculation items in the dynamic formula corresponding to the n-level cost allocation, the calculation items in the dynamic formula corresponding to the n-level cost allocation, and the indicator data.

[0046] See Figure 2 The cost accounting management system based on hospital business in this embodiment also includes: a cost estimation module, which, based on the results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series estimation model (TFT model) to obtain the results of the n+1-level cost allocation within a preset time period.

[0047] Example 2

[0048] Currently, hospital workload is generally allocated across three levels in the following manner:

[0049] (a) First-level apportionment

[0050] The costs of administrative and logistical departments (seven major items) are allocated to clinical, medical technology, and medical support departments based on the number of employees.

[0051] Cost allocated to each department = Number of employees in each clinical (medical technology, medical support) department / Total number of employees * Cost of administrative and logistical departments.

[0052] Note: The number of people includes staff of this institution and third-party personnel (excluding security and cleaning staff).

[0053] (ii) Secondary apportionment

[0054] The costs of medical support departments (seven major items) are allocated to clinical and medical technology departments based on workload.

[0055] 1. Outpatient billing costs – allocated based on the number of outpatient and emergency visits per department.

[0056] Cost allocated to each department = Number of outpatient and emergency visits in each department / Total number of outpatient and emergency visits * Cost at the outpatient billing office.

[0057] 2. Costs of the inpatient billing department – ​​allocated based on the number of admissions to each department.

[0058] Cost allocated to each department = Number of admissions to each department / Total number of admissions * Cost of inpatient billing department.

[0059] 3. Costs of the medical records statistics room – allocated based on the number of discharges from each department.

[0060] Cost allocated to each department = Number of discharges in each department / Total number of discharges * Cost of the medical records and statistics department.

[0061] 4. Costs of medical support departments such as supply rooms and intravenous fluid distribution centers – allocated according to the actual usage or expenses incurred by each department and the workload of internal services.

[0062] Cost allocated to each department = Workload of each department / Total workload * (Cost of supply room + static fluid distribution center, etc.)

[0063] (III) Three-tier apportionment

[0064] The costs of medical technology departments (seven major items) are allocated to clinical departments based on revenue.

[0065] Cost allocated to each department = Revenue of each department / Total revenue * Cost of medical technology departments

[0066] Note: Revenue includes outpatient and inpatient revenue.

[0067] See Figure 1 This embodiment provides a cost accounting management system based on hospital operations, including:

[0068] The indicator extraction module is used to extract indicator data from a third-party data source based on the first instruction information input by the user, which is a pre-set indicator data of the calculation item in the dynamic formula corresponding to the n-level cost allocation.

[0069] The indicator extraction module, based on the first instruction information input by the user, extracts indicator data from a third-party data source for the calculated items in the pre-set dynamic formula corresponding to the n-level cost allocation. Specifically, this includes:

[0070] The indicator extraction module obtains the first instruction information input by the user; the first instruction information is to extract indicator data from a third-party data source, which is the calculation item in the dynamic formula corresponding to the n-level cost allocation.

[0071] For example, a dynamic formula is a program-recognizable expression composed of multiple indicators with specific calculation and processing logic; such as a two-level amortization formula.

[0072] Cost allocated to each department = Number of admissions to each department / Total number of admissions * Cost of inpatient billing department.

[0073] Calculation item: An arithmetic expression that needs to be calculated separately after being decomposed by the dynamic formula.

[0074] For example, in the secondary allocation formula: number of admissions to each department / total number of admissions. This ratio needs to be calculated first.

[0075] Indicator data: The result values ​​obtained after the indicator sampling is completed.

[0076] For example, in the secondary allocation formula: total number of hospital admissions; is a personnel indicator with a value of xx people.

[0077] The indicator extraction module determines whether the preset extraction conditions are met. If they are met, it extracts the indicator data of the calculation items in the dynamic formula corresponding to the n-level cost allocation from the third-party data source and saves the indicator data.

[0078] The pre-set extraction conditions are: the indicator extraction module receives a manually triggered extraction button from the user, or reaches a pre-set time point, or meets the first condition (in fact, meeting the first condition means that real-time extraction is triggered by the dynamic formula (calculation item) during the amortization execution process).

[0079] The first condition is when the calculation item in the dynamic formula corresponding to the n-level cost allocation needs to be calculated.

[0080] The formula configuration module is used to obtain the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation based on the indicator data and the pre-acquired calculation priority order.

[0081] The formula configuration module obtains the final result of the calculation items in the dynamic formula based on the indicator data and the pre-acquired calculation priority order, specifically including:

[0082] The formula configuration module verifies the indicator data, obtains qualified indicator data, and puts the qualified indicator data into the message queue MQ.

[0083] Example of the verification process: For example, executing the secondary amortization calculation formula mentioned earlier:

[0084] Cost allocated to each department = Number of admissions to each department / Total number of admissions * Cost of inpatient billing department.

[0085] Based on historical data, the monthly total number of inpatients at this top-tier public hospital fluctuates between 2200 and 2800. If no data is available for this indicator (monthly total inpatients), or if the obtained data exceeds the threshold established by historical data, an alert will be issued, and the indicator will be manually reviewed and its inclusion or exclusion will be determined.

[0086] The formula configuration module monitors the qualified indicator data in the message queue MQ in real time and determines whether the pre-obtained calculation priority order is met. If it is met, the qualified indicator data in the message queue MQ is used to calculate the calculation item until all qualified indicator data in the message queue MQ has been calculated, and the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation is obtained.

[0087] For example, let's consider the secondary allocation calculation formula mentioned earlier:

[0088] Cost allocated to each department = Number of admissions to each department / Total number of admissions * Cost of inpatient billing department.

[0089] We will temporarily designate Department A as the department, and the allocation formula for Level 2 is as follows:

[0090] The cost of Department A = Number of admissions to Department A / Total number of admissions * Cost of inpatient billing. (Where the number of admissions to Department A, total number of admissions, and cost of inpatient billing are indicators).

[0091] Therefore, the calculation term of this formula is: number of admissions to Department A / total number of admissions (ratio coefficient).

[0092] In other words, the second-level allocation formula is:

[0093] Department A's cost = (ratio coefficient) * inpatient billing office cost.

[0094] Both of the above calculation items must obtain the final result value.

[0095] After the qualified indicator data is placed into the queue, the listening service continuously listens to see if it can match the calculation items of the local calculation trigger and satisfy the affixed expression after the current segment. If it does, the detailed item settlement in the calculation formula with higher priority weight will be calculated in turn to reduce the overall amortization calculation time.

[0096] The results calculated in the local calculation trigger will be used to verify the overall execution progress of the formula. If the final result value has been obtained, it will be written to the database for persistence.

[0097] The calculation priority order is determined in advance based on the calculation items and the allocation level corresponding to the calculation items in the pre-set dynamic formula corresponding to the n-level cost allocation.

[0098] For example, hospital operations are generally described in the following way at present:

[0099] (a) First-level apportionment

[0100] Cost allocated to each department = Number of employees in each clinical department / Total number of employees * Cost of administrative and logistical departments.

[0101] (ii) Secondary apportionment

[0102] Cost allocated to each department = Number of admissions to each department / Total number of admissions * Cost of inpatient billing department.

[0103] The costs allocated to the inpatient settlement department at the secondary level are the costs allocated to each department at the primary level (specific departments are selected).

[0104] The secondary allocation formula references the calculation result of the primary allocation formula. Therefore, both the primary and secondary allocation formulas are placed in a local calculation trigger for appended decomposition and weight judgment.

[0105] The decomposed expression is as follows:

[0106] The indicators are:

[0107] Number of staff in each clinical department (primary indicator).

[0108] Total number of employees (primary indicator).

[0109] Costs of administrative and logistical departments (primary indicator).

[0110] Admissions to each department (secondary indicator).

[0111] Total number of hospital admissions (secondary indicator).

[0112] The citation result is:

[0113] Costs of inpatient billing department (secondary level references primary level).

[0114] The calculation items are:

[0115] Number of employees in each clinical department / Total number of employees (secondary calculation item).

[0116] Number of admissions to each department / Total number of admissions (secondary calculation item).

[0117] Number of staff in each clinical department / Total number of staff * Cost of administrative and logistical departments (first-level calculation result).

[0118] Number of admissions to each department / Total number of admissions * Costs at the inpatient settlement office (secondary calculation result).

[0119] Weights are assigned based on their allocation level and calculation priority:

[0120] First-level indicator (1) > First-level calculation item (0.9) > First-level calculation result (0.8) > Second-level reference first-level (0.7) > Second-level indicator (0.6) > Second-level calculation item (0.5) > Second-level calculation result (0.4).

[0121] The above items are executed sequentially in the local computation trigger.

[0122] The decomposition items are generated (based on affixed decomposition + weight obtained based on allocation level).

[0123] The affixation decomposition method is used to process the pre-set dynamic formula corresponding to the n-level cost allocation to obtain the calculation items.

[0124] Determine whether each calculation item contains the allocation result of the level below level n.

[0125] If the calculation item includes allocation results below level n (the weighting coefficients are set according to the allocation level from low to high).

[0126] If the calculation item contains any indicators, then the calculation item needs to wait for the indicators to finish before it is triggered.

[0127] If the calculation item includes (indicator + allocation results below level n), then its priority is based on (setting weight coefficients according to allocation level from low to high, and the method of extracting and arranging indicators).

[0128] After sorting all the calculated items, assign corresponding weight coefficients.

[0129] For example, we can break down a complete dynamic formula.

[0130] It can be decomposed into:

[0131] Calculation items that include indicators, calculation items that include special symbols, and combined calculation items.

[0132] For example, the secondary allocation formula is

(a+b)*0.1

[0133] Where ab are indicators, and c is the first-level allocation result.

[0134] c belongs to the first-level allocation priority execution, with a weight coefficient of 1.

[0135] The calculation of the determination index in the calculator can take precedence over the result of c, and will not affect the secondary allocation result.

[0136] Therefore, given the availability of indicators a and b, they can be processed simultaneously with the first-level allocation. The calculation term (a+b) can be executed directly, with a weighting coefficient of 1.

[0137] However, the calculation term [(a+b)*0.1] can only be calculated after (a+b) has been executed, and the weight coefficient needs to be less than 1, tentatively set to 0.5.

[0138] The entire secondary allocation calculation formula [(a+b)*0.1] / c can only be calculated after [(a+b)*0.1] has been calculated, and the overall weight coefficient is 0.3.

[0139] Therefore, the pointer with a weight of 1 will be executed first. Then the pointer with a weight of 0.5 will be executed, and finally the pointer with a weight of 0.3 will be executed.

[0140] The allocation module is used to obtain the result of the n-level cost allocation based on the dynamic formula corresponding to the n-level cost allocation, the final result of the calculation items in the dynamic formula corresponding to the n-level cost allocation, the calculation items in the dynamic formula corresponding to the n-level cost allocation, and the indicator data.

[0141] Now assume a 4-level allocation formula for departmental personnel costs.

[0142] The reference value is the level 3 allocation formula (taking department A as the reference).

[0143] Department A's cost = Department A's revenue / Total revenue * Medical technology department's cost.

[0144] Its 4th level dynamic formula can be defined as (taking person B):

[0145] B personnel cost = A department cost (using 3-level allocation) / A department personnel total attendance hours * B personnel actual attendance hours.

[0146] After the Level 3 dynamic formula completes its calculation, the Level 4 dynamic formula references its result value. Finally, the final result of the Level 4 dynamic formula is obtained.

[0147] See Figure 2 The cost accounting management system based on hospital business in this embodiment also includes: a cost estimation module, which, based on the results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series estimation model (TFT model) to obtain the results of the n+1-level cost allocation within a preset time period.

[0148] The cost estimation module, based on the results of the n-level cost allocation and a pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series prediction model (TFT) to obtain the results of the n+1-level cost allocation within a preset time period, specifically including:

[0149] The results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation are input into the input layer of the pre-trained time series prediction model (TFT) to obtain the allocation results of the n+1 level.

[0150] The pre-trained time series prediction model TFT model is: a time series prediction model TFT model pre-trained using historical n-level amortization results training data of the nth level, and the resulting model.

[0151] The cost accounting management system based on hospital operations in this embodiment also includes:

[0152] The indicator extraction module is also used to collect historical data of the results of the nth level cost allocation based on the second instruction information input by the user.

[0153] The second indication information is the historical data of the results of cost allocation at level n collected by the indicator extraction module.

[0154] In this embodiment, the cost estimation module is also used to accept historical data of the results of the nth level cost allocation input by the user, and input the historical data of the results of the nth level cost allocation into the trained estimation model TFT model. The trained estimation model TFT model outputs the results of the nth level cost allocation for the estimated time period.

[0155] The larger the historical data volume, the smaller the loss in the estimation, and the closer it is to the actual value in the future. When an order arrives, the data that has already occurred can be added in.

[0156] For example, if the data currently available is from January to June, we need to estimate the data from July to September.

[0157] Possible options include: using data from January to June to forecast data for July; using data from February to July to forecast data for August; or using data from March to August to forecast data for September.

[0158] As we enter July, we have already obtained the real data for July. This real data can be added to the model to optimize its training structure. This will make the subsequent unknown data for August and September more realistic, reducing errors. The amount of real error in July will affect the model optimization.

[0159] This embodiment of a cost accounting management system based on hospital operations employs an indicator extraction module. Based on a user-input first instruction, the module extracts pre-defined indicator data from a third-party data source for calculation items in a dynamic formula corresponding to n-level cost allocation. A formula configuration module, based on the indicator data and a pre-acquired calculation priority order, obtains the final result of the calculation items in the dynamic formula corresponding to n-level cost allocation. An allocation module, based on the dynamic formula corresponding to n-level cost allocation, the final result of the calculation items in the dynamic formula, the calculation items in the dynamic formula, and the indicator data, obtains the result of n-level cost allocation. Compared to existing technologies, this system can perform cost estimation for n-level cost allocation, improving work efficiency.

[0160] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0162] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0163] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0164] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0165] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A cost accounting management system based on hospital operations, characterized in that, include: The indicator extraction module is used to extract indicator data of calculation items in the dynamic formula corresponding to n-level cost allocation from a third-party data source based on the first instruction information input by the user. Specifically, the indicator extraction module obtains the first instruction information input by the user; the first instruction information is to extract indicator data of calculation items in the dynamic formula corresponding to n-level cost allocation from the third-party data source; the indicator extraction module determines whether the preset extraction conditions are met, and if so, extracts the indicator data of the calculation items in the dynamic formula corresponding to n-level cost allocation from the third-party data source and saves the indicator data. The formula configuration module is used to obtain the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation based on the indicator data and the pre-acquired calculation priority order, specifically including: The formula configuration module verifies the indicator data, obtains qualified indicator data, and puts the qualified indicator data into the message queue MQ. The formula configuration module monitors the verified indicator data in the message queue MQ in real time and determines whether the pre-obtained calculation priority order is met. If it is met, the verified indicator data in the message queue MQ is used to calculate the calculation item until all verified indicator data in the message queue MQ has been calculated, thus obtaining the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation. The calculation priority order is determined in advance based on the pre-set calculation item in the dynamic formula corresponding to the n-level cost allocation and the pre-defined allocation level corresponding to the calculation item. The allocation module is used to obtain the result of the n-level cost allocation based on the dynamic formula corresponding to the n-level cost allocation, the final result of the calculation item in the dynamic formula corresponding to the n-level cost allocation, the calculation item in the dynamic formula corresponding to the n-level cost allocation, and the indicator data. The cost accounting management system based on hospital operations also includes: The cost estimation module, based on the results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series estimation model (TFT model) to obtain the results of the n+1-level cost allocation within a preset time period.

2. The cost accounting management system based on hospital operations according to claim 1, characterized in that, The pre-set extraction conditions are: the indicator extraction module receives a manually triggered extraction button from the user, or a pre-set time point is reached, or the first condition is met. The first condition is that the calculation terms in the dynamic formula corresponding to the n-level cost allocation meet the time point at which they are calculated.

3. The cost accounting management system based on hospital operations as described in claim 2, characterized in that, The cost estimation module, based on the results of the n-level cost allocation and a pre-set dynamic formula corresponding to the n+1-level cost allocation, and the index data of the calculation items in the dynamic formula corresponding to the n+1-level cost allocation, uses a pre-trained time series prediction model (TFT) to obtain the results of the n+1-level cost allocation within a preset time period, specifically including: The results of the n-level cost allocation and the pre-set dynamic formula corresponding to the n+1-level cost allocation are input into the input layer of the pre-trained time series prediction model (TFT) to obtain the allocation results of the n+1 level.

4. The cost accounting management system based on hospital operations according to claim 3, characterized in that, The pre-trained time series prediction model TFT model is: a time series prediction model TFT model pre-trained using historical n-level amortization results training data of the nth level, and the resulting model.

5. The cost accounting management system based on hospital operations according to claim 4, characterized in that, The indicator extraction module is also used to collect historical data of the results of the nth level cost allocation based on the second instruction information input by the user. The second indication information is the historical data of the results of cost allocation at level n collected by the indicator extraction module.

6. The cost accounting management system based on hospital operations according to claim 5, characterized in that, The cost estimation module is also used to accept historical data of the nth level cost allocation results input by the user, and input the historical data of the nth level cost allocation results into the trained estimation model TFT model. The trained estimation model TFT model outputs the nth level cost allocation results for the estimated time period.

Images