Fuel contract intelligent auditing method and system

Abstract

The invention relates to the technical field of fuel contract review, in particular to a fuel contract intelligent review method and system. Comprising the steps of establishing a semantic processing model according to historical parameters, and generating a preprocessing data packet of a to-be-examined contract according to the semantic processing model; generating an examination evaluation value of the contract to be examined according to the preprocessed data packet, and judging whether a secondary examination strategy is generated or not according to the examination evaluation value; and generating an income evaluation value of the contract to be examined according to the secondary examination strategy, and judging whether an early warning instruction is generated or not according to the income evaluation value. Through the preset semantic processing model, semantic analysis is performed on the to-be-examined contract, the format content in the to-be-examined contract is examined and corrected in time, the management efficiency of the to-be-examined contract is improved, meanwhile, the transaction content data in the to-be-examined contract is extracted through the semantic processing model, income examination is performed, and the efficiency of the to-be-examined contract is improved. The risk early warning capability of a fuel contract is improved, and the operation and maintenance cost of a power plant is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of fuel contract review, and in particular to a method and system for intelligent review of fuel contracts. Background Art

[0002] At present, many thermal power plants have not yet established a scientific and comprehensive fuel management and control system, lack effective supervision measures, and have not built an effective integrated fuel management and control information platform. There are "information islands" in the relevant business links of fuel management such as planning, procurement, scheduling, acceptance, settlement, coal yard, blending, and analysis, and the information in each link is not effectively organized and interconnected.

[0003] At present, the drafting process of fuel contracts is usually done manually, and the review process only focuses on the format of the fuel contract and the qualifications of the transaction parties. It is impossible to provide early warning of the potential benefits and performance risks of the contract, resulting in increasing operation and maintenance costs of power plants.

[0004] Application Contents The purpose of this application is: to solve the above technical problems, this application provides a fuel contract intelligent audit method and system, aiming to improve the management efficiency and risk prediction of fuel contracts and reduce the operation and maintenance costs of power plants.

[0005] In some embodiments of the present application, a preset semantic processing model is used to perform semantic analysis on the contract to be reviewed, and the format content in the contract to be reviewed is reviewed and corrected in a timely manner, thereby improving the management efficiency of the contract to be reviewed. At the same time, the semantic processing model is used to extract transaction content data in the contract to be reviewed, and a revenue review is performed to improve the risk warning capability for fuel contracts and reduce the operation and maintenance costs of power plants.

[0006] In some embodiments of the present application, by extracting the transaction data of the contract to be reviewed, combining the inventory forecast curve, the associated contract and the transaction environment parameters to accurately predict the benefits of the contract to be reviewed, and promptly terminate the fuel contract that will result in large losses, thereby avoiding the problem of increased power plant operation and maintenance costs caused by the fuel contract, and improving the management efficiency of the power plant.

[0007] In some embodiments of the present application, a method for intelligently reviewing a fuel contract is provided, comprising: Establish a semantic processing model based on historical parameters and generate a pre-processed data package of the contract to be reviewed based on the semantic processing model; Generate a review evaluation value for the contract to be reviewed based on the pre-processed data package, and determine whether to generate a secondary review strategy based on the review evaluation value; Generate a profit evaluation value for the contract to be reviewed based on the secondary review strategy, and determine whether to generate an early warning instruction based on the profit evaluation value.

[0008] In some embodiments of the present application, generating a review evaluation value for a contract to be reviewed based on a preprocessed data packet includes: Extracting initial review parameters of the contract to be reviewed from the preprocessed data packet; Generating a review evaluation value a based on the initial review parameters; a = e1 * Q1 * (µ 1i * j 1i) + e2 * Q2 * (µ 2i * j 2i) ; Where, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; is the number of first-level evaluation indicators; µ 1i is the influence factor of the i-th first-level evaluation indicator; j 1i is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; is the number of second-level evaluation indicators; µ 2i is the influence factor of the i-th second-level evaluation indicator; j 2i is the reference value of the i-th second-level evaluation indicator generated based on the initial review parameters.

[0009] In some embodiments of the present application, determining whether to generate a secondary review strategy based on the review evaluation value includes: Presetting a first review evaluation value threshold A1 and a second review evaluation value threshold A2; If a < A1, generating a secondary review strategy; If A1 ≤ a < A2, generating a first-level correction instruction, generating correction parameters for the contract to be reviewed according to the first-level correction instruction, and generating a secondary review strategy according to the correction result; If a > A2, generating a secondary correction instruction.

[0010] In some embodiments of the present application, generating a revenue evaluation value for the contract to be reviewed based on the secondary review strategy includes: Obtaining transaction data of the contract to be reviewed according to the preprocessed data packet; Setting a performance period according to the transaction data; Setting multiple time intervals within the performance period; Establishing a time interval sequence T, T = (t1, t2…t i …t m ), where, t i is the i-th time interval within the performance period; m is the number of time intervals within the performance period; Generating expected revenue values within each time interval; Establish the expected return value series F, F=(f1, f2…f i …f m ), where f i is the expected return value of the i-th time interval; Generate a profit evaluation value c based on the expected profit value sequence F.

[0011] In some embodiments of the present application, generating a profit evaluation value c according to the expected profit value sequence F includes: Generate the fulfillment probability for each time interval based on the preset fulfillment prediction model; Establish the performance probability series G, G=(g1, g2…g i …g m ), where gi is the probability of fulfillment in the i-th time interval, and ( gi)=1; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

[0012] In some embodiments of the present application, generating the expected return value in each time interval includes: Obtain inventory forecast curves within the fulfillment cycle, and associate contract and transaction environment parameters; Set t in sequence according to the time interval sequence T i is the target time interval; Generate the expected return value f for the target time interval; f=[ k i *d i ]; Among them, q is the number of benefit evaluation indicators; k i is the impact factor of the i-th benefit evaluation index; d i is the reference value of the i-th benefit evaluation indicator in the target time interval; Generate the expected return value for each time interval in turn.

[0013] In some embodiments of the present application, judging whether to generate a warning instruction according to the revenue evaluation value includes: Presetting a first revenue evaluation value threshold F1 and a second revenue evaluation value threshold F2; If f < F1, a first-level warning instruction is generated for the contract to be reviewed; If F1 < f < F2, a second-level warning instruction is generated for the contract to be reviewed; If f > F2, no warning instruction is generated for the contract to be reviewed.

[0014] In some embodiments of the present application, a fuel contract intelligent review system is provided, including: A central control unit for establishing a semantic processing model according to historical parameters; A data acquisition unit for obtaining all contracts to be reviewed; A monitoring unit for obtaining an inventory prediction curve, historical contract parameters, and transaction environment parameters; The central control unit includes: A first processing module for generating a preprocessing data packet for the contract to be reviewed according to the semantic processing model; A second processing module for generating a review evaluation value for the contract to be reviewed according to the preprocessing data packet, and judging whether to generate a secondary review strategy according to the review evaluation value; A review module for generating a revenue evaluation value for the contract to be reviewed according to the secondary review strategy, and judging whether to generate a warning instruction according to the revenue evaluation value.

[0015] In some embodiments of the present application, the second processing module is further configured to: Extract the initial review parameters of the contract to be reviewed according to the preprocessing data packet; Generate a review evaluation value a according to the initial review parameters; a = e1 * Q1 * (µ 1i * j 1i) + e2 * Q2 * (µ 2i * j 2i) ; Where, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; is the number of first-level evaluation indicators; µ 1i is the influence factor of the i-th first-level evaluation indicator; j 1i is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; is the number of second-level evaluation indicators; µ 2i is the influence factor of the i-th second-level evaluation indicator; j 2iis the reference value of the i-th secondary evaluation index generated based on the initial review parameters; Preset the first review evaluation value threshold A1 and the second review evaluation value threshold A2; If a < A1, generate a secondary review strategy; If A1 ≤ a < A2, generate a primary correction instruction, generate correction parameters for the contract to be reviewed according to the primary correction instruction, and generate a secondary review strategy according to the correction result; If a > A2, generate a secondary correction instruction.

[0016] In some embodiments of the present application, the review module is further configured to: Obtain the transaction data of the contract to be reviewed according to the preprocessed data packet; Set the performance period according to the transaction data; Set multiple time intervals within the performance period; Establish a time interval sequence T, T = (t1, t2…t i …t m ), where t i is the i-th time interval within the performance period; m is the number of time intervals within the performance period; Obtain the inventory prediction curve within the performance period, and associate the contract and transaction environment parameters; Set t i as the target time interval in sequence according to the time interval sequence T; Generate the expected revenue value f of the target time interval; f = k i *d i ; Where q is the number of revenue evaluation indicators; k i is the influence factor of the i-th revenue evaluation indicator; d i is the reference value of the i-th revenue evaluation indicator in the target time interval; Generate the expected revenue values of each time interval in sequence; Establish an expected revenue value sequence F, F = (f1, f2…f i …f m ), where f i is the expected revenue value of the i-th time interval; Generate the performance probability of each time interval according to the preset performance prediction model; Establish a performance probability sequence G, G = (g1, g2…g i …g m ), where gi is the performance probability of the i-th time interval, and ( gi) = 1; Generate the revenue evaluation value c; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

[0017] Compared with the prior art, the intelligent fuel contract audit method and system of the present application embodiment has the following beneficial effects: Through the preset semantic processing model, semantic analysis of the contracts to be reviewed is carried out, and the format content in the contracts to be reviewed is reviewed and corrected in a timely manner, thereby improving the management efficiency of the contracts to be reviewed. At the same time, the transaction content data in the contracts to be reviewed is extracted through the semantic processing model to conduct revenue review, improve the risk warning capability of fuel contracts, and reduce the operation and maintenance costs of power plants.

[0018] By extracting the transaction data of the contracts to be reviewed, combining it with inventory forecast curves, related contracts and transaction environment parameters, we can accurately predict the profits of the contracts to be reviewed, and promptly terminate fuel contracts that will result in large losses, avoiding the problem of increased power plant operation and maintenance costs caused by fuel contracts, and improving the management efficiency of power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a fuel contract intelligent audit method in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0020] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0021] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0022] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0023] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0024] like Figure 1 As shown, a fuel contract intelligent audit method according to a preferred embodiment of the present application is characterized by comprising: S101: Establishing a semantic processing model based on historical parameters, and generating a pre-processing data package of the contract to be reviewed based on the semantic processing model; S102: Generate a review evaluation value for the contract to be reviewed based on the pre-processed data packet, and determine whether to generate a secondary review strategy based on the review evaluation value; S103: Generate a benefit evaluation value for the contract to be reviewed according to the secondary review strategy, and determine whether to generate a warning instruction based on the benefit evaluation value.

[0025] Specifically, the review evaluation value of the contract to be reviewed is generated based on the preprocessed data package, including: Extracting initial review parameters of the contract to be reviewed based on the pre-processed data package; Generate an audit evaluation value a based on the initial audit parameters; a=e1*Q1* (µ 1i *j 1i) ]+e2*Q2* (µ 2i *j 2i) ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; is the number of first-level evaluation indicators; µ 1i is the impact factor of the i-th first-level evaluation index; j 1i is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; is the number of secondary evaluation indicators; µ2i is the influencing factor for the i-th secondary evaluation index; j 2i is the reference value of the i-th secondary evaluation index generated based on the initial review parameters.

[0026] Specifically, all parameters in the model are normalized by presetting a first fixed coefficient and a second fixed coefficient, so that each parameter in each model is within the same value range.

[0027] Specifically, the primary evaluation index refers to the evaluation index generated based on the general problems of the contract, including but not limited to: the number of typos in the contract, the number of incorrect punctuation marks, the number of incorrect expression paragraphs of non-core transaction content, and other parameters.

[0028] Specifically, the secondary evaluation index refers to the evaluation index generated based on the core transaction content of the contract, including but not limited to: whether there are errors in the subject matter, the deviation value of the transaction volume, whether there are errors in the transaction object, whether the performance terms are complete, and other parameters.

[0029] Specifically, the larger the review evaluation value, the more error content exists in the current contract to be reviewed. It is necessary to correct the error content in time to avoid contract omissions.

[0030] Specifically, it is judged whether to generate a secondary review strategy according to the review evaluation value, including: Presetting a first review evaluation value threshold A1 and a second review evaluation value threshold A2; If a < A1, generate a secondary review strategy; If A1 ≤ a < A2, generate a primary correction instruction, generate correction parameters for the contract to be reviewed according to the primary correction instruction, and generate a secondary review strategy according to the correction result; If a > A2, generate a secondary correction instruction.

[0031] Specifically, the primary correction instruction means that there are some error contents in the non-core content of the current contract to be reviewed, which need to be modified, and the transaction data of the corrected contract is reviewed according to the secondary review strategy. The secondary correction instruction means that there are major omissions in the current contract to be reviewed, and it needs to be redrafted.

[0032] It can be understood that in the above embodiments, by establishing a semantic processing model, semantic analysis is performed on the contract to be reviewed, and the format content in the contract to be reviewed is timely reviewed and corrected, improving the management efficiency of the contract to be reviewed and reducing the operation and maintenance costs of the power plant.

[0033] In the preferred embodiment of the present application, the income evaluation value of the contract to be reviewed is generated according to the secondary review strategy, including: Obtaining the transaction data of the contract to be reviewed according to the preprocessed data packet; Set fulfillment cycles based on transaction data; Set multiple time intervals within the fulfillment cycle; Establish a time interval sequence T, T=(t1, t2…t i …t m ), where t i is the i-th time interval in the performance period; m is the number of time intervals in the performance period; Generate expected return values for each time interval; Establish the expected return value series F, F=(f1, f2…f i …f m ), where f i is the expected return value of the i-th time interval; Generate a profit evaluation value c based on the expected profit value sequence F.

[0034] Specifically, the contract fulfillment period is generated based on the number of transactions in the contract to be reviewed. The fulfillment period is the fuel delivery time point. After processing the fulfillment period, early delivery time and delayed delivery time are added to generate the corresponding fulfillment cycle. Based on the fulfillment cycle, the corresponding time interval sequence is generated.

[0035] Specifically, the duration of each time interval is the same, and the duration of a single time interval is preferably one day.

[0036] Specifically, the profit evaluation value c is generated according to the expected profit value sequence F, including: Generate the fulfillment probability for each time interval based on the preset fulfillment prediction model; Establish the performance probability series G, G=(g1, g2…g i …g m ), where gi is the probability of fulfillment in the i-th time interval, and ( gi)=1; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

[0037] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter is within the same value range.

[0038] Specifically, by comprehensively analyzing the transaction transportation routes and transaction objects, a corresponding fulfillment prediction model is constructed. The fulfillment probability value refers to the possibility of delivering fuel in the time period corresponding to the current time interval.

[0039] Specifically, performance risk indicators include, but are not limited to, the number of historical defaults by the current transaction counterparty, the amount of fuel traded, the probability of delayed delivery, fuel quality risk, and other parameters. The influencing factors for each performance risk indicator can be set based on historical contract parameters. The value range for each performance risk indicator can also be set based on historical parameters. A higher reference value for each performance risk indicator indicates a lower likelihood of default in the current contract under review.

[0040] It is understandable that in the above embodiment, the transaction content data in the contract to be reviewed is extracted through the semantic processing model to conduct a revenue review, thereby improving the risk warning capability for fuel contracts and reducing the operation and maintenance costs of the power plant.

[0041] In a preferred embodiment of the present application, generating the expected return value in each time interval includes: Obtain inventory forecast curves within the fulfillment cycle, and associate contract and transaction environment parameters; Set t in sequence according to the time interval sequence T i is the target time interval; Generate the expected return value f for the target time interval; f=[ k i *d i ]; Among them, q is the number of benefit evaluation indicators; k i is the impact factor of the i-th benefit evaluation index; d i is the reference value of the i-th benefit evaluation indicator in the target time interval; Generate the expected return value for each time interval in turn.

[0042] Specifically, inventory costs and inventory pressure are calculated based on the inventory forecast curve for the time period corresponding to the target time interval. The probability of stockouts is calculated based on the associated contracts within the corresponding time period. The expected fuel price is generated based on the trading environment parameters within the corresponding time period, and the profit and loss is calculated based on the transaction price of the contract to be reviewed.

[0043] Specifically, a related contract refers to a fuel contract that has the same trading fuel category as the contract to be reviewed and has an overlapping performance time and target time interval.

[0044] Specifically, the revenue evaluation indicators include, but are not limited to, inventory cost indicators, stockout probability, the impact of stockouts on power plant production, and the revenue or loss brought about by transaction price fluctuations.

[0045] Specifically, the larger the revenue evaluation value, the smaller the possibility that the current contract under review will cause profit or loss to the power plant.

[0046] Specifically, judging whether to generate a warning instruction based on the revenue evaluation value includes: Presetting a first revenue evaluation value threshold F1 and a second revenue evaluation value threshold F2; If f < F1, a first-level warning instruction is generated for the contract under review; If F1 < f < F2, a second-level warning instruction is generated for the contract under review; If f > F2, no warning instruction is generated for the contract under review.

[0047] Specifically, the first-level warning instruction means that the current contract under review will cause a large cost loss to the power plant and the contract signing needs to be terminated immediately. The second-level warning instruction means that there is a large loss risk in the current contract under review and it needs to be handed over to experts for detailed risk assessment.

[0048] It can be understood that in the above embodiments, by extracting the transaction data of the contract under review, combining with the inventory prediction curve, associated contracts and transaction environment parameters, the revenue of the contract under review is accurately predicted, and the fuel contract that will cause large losses is terminated in time, avoiding the problem of increasing the operation and maintenance costs of the power plant due to fuel contracts, and improving the management efficiency of the power plant.

[0049] Based on another preferred embodiment of a fuel contract intelligent review method in any of the above preferred embodiments, in this preferred embodiment, a fuel contract intelligent review system is provided, including: A central control unit for establishing a semantic processing model according to historical parameters; A data acquisition unit for obtaining all contracts under review; A monitoring unit for obtaining the inventory prediction curve, historical contract parameters and transaction environment parameters; The central control unit includes: A first processing module for generating a preprocessing data packet for the contract under review according to the semantic processing model; A second processing module for generating a review evaluation value for the contract under review according to the preprocessing data packet, and judging whether to generate a second-level review strategy according to the review evaluation value; A review module for generating a revenue evaluation value for the contract under review according to the second-level review strategy, and judging whether to generate a warning instruction according to the revenue evaluation value.

[0050] In the preferred embodiment of the embodiment of the present application, the second processing module is further configured to: Extract the initial review parameters of the contract to be reviewed according to the preprocessed data packet; Generate a review evaluation value a according to the initial review parameters; a = e1 * Q1 * (µ 1i * j 1i) + e2 * Q2 * (µ 2i * j 2i) ; Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; Is the number of first-level evaluation indicators; µ 1i Is the influence factor of the i-th first-level evaluation indicator; j 1i Is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; Is the number of second-level evaluation indicators; µ 2i Is the influence factor of the i-th second-level evaluation indicator; j 2i Is the reference value of the i-th second-level evaluation indicator generated based on the initial review parameters; Preset a first review evaluation value threshold A1 and a second review evaluation value threshold A2; If a < A1, generate a secondary review strategy; If A1 ≤ a < A2, generate a primary correction instruction, generate correction parameters for the contract to be reviewed according to the primary correction instruction, and generate a secondary review strategy according to the correction result; If a > A2, generate a secondary correction instruction.

[0051] In the preferred embodiment of the embodiment of the present application, the review module is further configured to: Obtain the transaction data of the contract to be reviewed according to the preprocessed data packet; Set the performance period according to the transaction data; Set multiple time intervals within the performance period; Establish a time interval sequence T, T = (t1, t2…t i …t m ), wherein, t i Is the i-th time interval within the performance period; m is the number of time intervals within the performance period; Obtain the inventory prediction curve within the performance period, associate the contract and transaction environment parameters; Set t i As the target time interval in sequence according to the time interval sequence T; Generate the expected revenue value f of the target time interval; f = k i *d i ]; Among them, q is the number of benefit evaluation indicators; k i is the impact factor of the i-th benefit evaluation index; d i is the reference value of the i-th benefit evaluation indicator in the target time interval; Generate the expected return value of each time interval in turn; Establish the expected return value series F, F=(f1, f2…f i …f m ), where f i is the expected return value of the i-th time interval; Generate the fulfillment probability for each time interval based on the preset fulfillment prediction model; Establish the performance probability series G, G=(g1, g2…g i …g m ), where gi is the probability of fulfillment in the i-th time interval, and ( gi)=1; Generate a benefit evaluation value c; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

[0052] According to the first concept of this application, a semantic analysis is performed on the contract to be reviewed through a preset semantic processing model, and the format content in the contract to be reviewed is reviewed and corrected in a timely manner, thereby improving the management efficiency of the contract to be reviewed. At the same time, the transaction content data in the contract to be reviewed is extracted through the semantic processing model to conduct a revenue review, thereby improving the risk warning capability for fuel contracts and reducing the operation and maintenance costs of power plants.

[0053] According to the second concept of this application, by extracting the transaction data of the contract to be reviewed, combining the inventory forecast curve, the associated contract and the transaction environment parameters, the benefits of the contract to be reviewed are accurately predicted, and the fuel contracts that will result in large losses are terminated in time, thereby avoiding the problem of increased power plant operation and maintenance costs caused by fuel contracts and improving the management efficiency of power plants.

[0054] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A fuel contract intelligent audit method, characterized in that: It includes: Establish a semantic processing model based on historical parameters, and generate a preprocessing data packet for the contract to be reviewed according to the semantic processing model; Generate a review evaluation value for the contract to be reviewed according to the preprocessing data packet, and judge whether to generate a secondary review strategy according to the review evaluation value; Generate a revenue evaluation value for the contract to be reviewed according to the secondary review strategy, and judge whether to generate a warning instruction according to the revenue evaluation value.

2. The intelligent audit method for fuel contracts according to claim 1, characterized in that: Generate a review evaluation value for the contract to be reviewed according to the preprocessing data packet, including: Extract the initial review parameters of the contract to be reviewed according to the preprocessing data packet; Generate a review evaluation value a according to the initial review parameters; a=e1*Q1* (µ 1i *j 1i) ]+e2*Q2* (µ 2i *j 2i) ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; is the number of first-level evaluation indicators; µ 1i is the impact factor of the i-th first-level evaluation index; j 1i is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; is the number of secondary evaluation indicators; µ 2i is the impact factor of the i-th secondary evaluation index; j 2i is the reference value of the i-th secondary evaluation indicator generated based on the initial review parameters.

3. The intelligent audit method for fuel contracts according to claim 2, characterized in that: Judge whether to generate a secondary review strategy according to the review evaluation value, including: Preset a first review evaluation value threshold A1 and a second review evaluation value threshold A2; If a < A1, generate a secondary review strategy; If A1 ≤ a < A2, generate a first-level correction instruction, generate correction parameters for the contract to be reviewed according to the first-level correction instruction, and generate a secondary review strategy according to the correction result; If a > A2, generate a second-level correction instruction.

4. The intelligent audit method for fuel contracts according to claim 3, characterized in that: Generate a revenue evaluation value for the contract to be reviewed according to the secondary review strategy, including: Obtain the transaction data of the contract to be reviewed according to the preprocessing data packet; Set the performance period according to the transaction data; Set multiple time intervals within the performance period; Establish a time interval sequence T, T=(t1, t2…t i …t m ), where t i is the i-th time interval in the performance period; m is the number of time intervals in the performance period; Generate the expected revenue value for each time interval; Establish the expected return value series F, F=(f1, f2…f i …f m ), where f i is the expected return value of the i-th time interval; Generate a revenue evaluation value c according to the sequence F of expected revenue values.

5. The intelligent audit method for fuel contracts according to claim 4, characterized in that: Generate a revenue evaluation value c according to the sequence F of expected revenue values, including: Generate the performance probability for each time interval according to a preset performance prediction model; Establish the performance probability series G, G=(g1, g2…g i …g m ), where gi is the probability of fulfillment in the i-th time interval, and ( gi)=1; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

6. The intelligent audit method for fuel contracts according to claim 5, characterized in that: The generation of the expected revenue value for each time interval includes: Obtain the inventory prediction curve within the performance period, associate the contract and transaction environment parameters; Set t in sequence according to the time interval sequence T i is the target time interval; Generate the expected revenue value f for the target time interval; f=[ k i *d i ]; Among them, q is the number of benefit evaluation indicators; k i is the impact factor of the i-th benefit evaluation index; d i is the reference value of the i-th benefit evaluation indicator in the target time interval; Generate the expected revenue value for each time interval in sequence.

7. The intelligent audit method for fuel contracts according to claim 5, characterized in that: The judgment of whether to generate a warning instruction according to the revenue evaluation value includes: Preset a first revenue evaluation value threshold F1 and a second revenue evaluation value threshold F2; If f < F1, generate a first-level warning instruction for the contract to be reviewed; If F1 < f < F2, generate a second-level warning instruction for the contract to be reviewed; If f > F2, no warning instruction is generated for the contract to be reviewed.

8. A fuel contract intelligent audit system, using the fuel contract intelligent audit method according to any one of claims 1 to 7, characterized in that: It includes: A central control unit for establishing a semantic processing model according to historical parameters; A data acquisition unit for obtaining all contracts to be reviewed; A monitoring unit for obtaining the inventory prediction curve, historical contract parameters and transaction environment parameters; The central control unit includes: A first processing module for generating a preprocessing data packet for the contract to be reviewed according to the semantic processing model; A second processing module for generating a review evaluation value for the contract to be reviewed according to the preprocessing data packet, and judging whether to generate a secondary review strategy according to the review evaluation value; A review module for generating a revenue evaluation value for the contract to be reviewed according to the secondary review strategy, and judging whether to generate a warning instruction according to the revenue evaluation value.

9. The intelligent fuel contract audit system according to claim 8, characterized in that: The second processing module is also used for: Extracting the initial review parameters of the contract to be reviewed according to the preprocessing data packet; Generating a review evaluation value a according to the initial review parameters; a=e1*Q1* (µ 1i *j 1i) ]+e2*Q2* (µ 2i *j 2i) ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; is the number of first-level evaluation indicators; µ 1i is the impact factor of the i-th first-level evaluation index; j 1i is the reference value of the i-th first-level evaluation indicator generated based on the initial review parameters; is the number of secondary evaluation indicators; µ 2i is the impact factor of the i-th secondary evaluation index; j 2i is the reference value of the i-th secondary evaluation indicator generated based on the initial review parameters; Presetting a first review evaluation value threshold A1 and a second review evaluation value threshold A2; If a < A1, generate a secondary review strategy; If A1 ≤ a < A2, generate a first-level correction instruction, generate correction parameters for the contract to be reviewed according to the first-level correction instruction, and generate a second-level review strategy according to the correction result; If a > A2, generate a second-level correction instruction.

10. The intelligent fuel contract audit system according to claim 9, characterized in that: The review module is further configured to: Obtain the transaction data of the contract to be reviewed according to the preprocessed data packet; Set the performance period according to the transaction data; Set multiple time intervals within the performance period; Establish a time interval sequence T, T=(t1, t2…t i …t m ), where t i is the i-th time interval in the performance period; m is the number of time intervals in the performance period; Obtain the inventory prediction curve within the performance period, and associate the contract and transaction environment parameters; Set t in sequence according to the time interval sequence T i is the target time interval; Generate the expected revenue value f for the target time interval; f=[ k i *d i ]; Among them, q is the number of benefit evaluation indicators; k i is the impact factor of the i-th benefit evaluation index; d i is the reference value of the i-th benefit evaluation indicator in the target time interval; Generate the expected revenue values for each time interval in sequence; Establish the expected return value series F, F=(f1, f2…f i …f m ), where f i is the expected return value of the i-th time interval; Generate the performance probabilities for each time interval according to the preset performance prediction model; Establish the performance probability series G, G=(g1, g2…g i …g m ), where gi is the probability of fulfillment in the i-th time interval, and ( gi)=1; Generate the revenue evaluation value c; c=e3*Q3*[ g i *f i ]+e4*Q4*[ β i *h i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; r is the number of performance risk indicators; β i is the influencing factor of the i-th performance risk indicator; h i is the reference value of the i-th performance risk indicator generated based on the contract parameters.

Images