Method for assigning values ​​to petroleum geological evaluation indicators

Through the combination of neural network algorithm and comparison area database, the problem of low efficiency and high subjectivity of index assignment in petroleum geological evaluation is solved, and more efficient and objective evaluation results are achieved, quantitative reference is provided, and the science of evaluation is enhanced. sex.

CN112132369BActive Publication Date: 2024-11-08CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910550011.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-06-24
Publication Date
2024-11-08
Estimated Expiration
2039-06-24

AI Technical Summary

Technical Problem

The index assignment efficiency in the existing petroleum geological evaluation is low, there is strong subjectivity and lack of quantitative reference, resulting in inconsistent evaluation results and poor objectivity.

Method used

The neural network algorithm and comparison area database are used to extract reference scores through geological parameters and evaluation standards, combined with manual assignment, improve the objectivity and efficiency of index assignment, and continuously enrich the database to enhance scientificity and accuracy.

Benefits of technology

It improves the work efficiency of evaluation index assignment, reduces the subjectivity of manual assignment, provides quantitative reference, enhances the objectivity and scientificity of evaluation, and reduces the differences in geological evaluation unit index assignment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112132369B_ABST
    Figure CN112132369B_ABST
Patent Text Reader

Abstract

The invention discloses a petroleum geological evaluation index assignment method, comprising: determining the type of geological unit to be evaluated, selecting geological parameters and evaluation criteria according to the type; applying a neural network algorithm to obtain a first reference score of the index to be evaluated according to various geological parameters and evaluation criteria through a pre-established neural network training sample library; obtaining a second reference score of the index to be evaluated through manual assignment using a pre-established comparison area database, taking the comparison area data as a reference and according to the evaluation criteria; when the difference between the first reference score and the second reference score is less than a set first threshold, selecting the first reference score or the second reference score as the score of the index to be evaluated; when the difference between the first reference score and the second reference score is greater than the first threshold, selecting the second reference score as the score of the index to be evaluated. The work efficiency of the evaluation index assignment is improved through the comparison area and neural network comprehensive assignment, and the scientificity and objectivity are increased.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of petroleum geology research, and more particularly to a petroleum geology evaluation index assignment method. Background Art

[0002] Oil and gas exploration and evaluation is a process of gradual deepening from the surface to the point, gradually unfolding from basin → zone → trap → reservoir. With the continuous deepening of exploration of oil and gas basins in my country, corresponding relatively complete evaluation systems and methods have been established for geological units of different levels [Guo Qiulin, Zhai Guangming, Shi Guangren. Improved zone comprehensive evaluation model and its implementation method. Acta Petrolei Sinica, 2004, 25(2)]. At present, the evaluation methods for basins, traps and reservoirs at home and abroad are relatively systematic and mature, and multiple versions of "Technical Specifications for Basin Evaluation (SY / T 5519-1996)" and "Technical Specifications for Trap Evaluation (SY / T 5520-1996)" have been launched. Although the algorithms and parameters used in the geological comprehensive evaluation of geological units of different levels are different, the evaluation process is to assign geological comprehensive indicators and then calculate the comprehensive score of the evaluation object through the indicator scores. Therefore, the process of assigning geological indicators to the object to be evaluated (evaluation unit) is the key process of geological comprehensive evaluation. In the past, when assigning evaluation indicators, the model of "offline review of geological data and online manual assignment" was adopted. That is, when assigning evaluation values, geological researchers first consulted relevant information, then further analyzed the content of the relevant information, combined with work experience, and finally gave evaluation indicator values.

[0003] This indicator assignment mode has the following disadvantages:

[0004] (1) The evaluation process involves the assignment of indicators for a large number of geological evaluation units, and researchers need to repeatedly review comparative data, which results in extremely low work efficiency.

[0005] (2) Manual assignment is highly subjective, and even the assignment of the same or similar geological evaluation unit indicators may have large differences;

[0006] (3) There is a lack of quantitative reference when assigning indicators.

[0007] Therefore, it is necessary to propose a petroleum geological evaluation index assignment method that can improve the efficiency of index assignment of petroleum geological evaluation units, enhance the objectivity of index assignment, and provide quantitative reference. Summary of the Invention

[0008] The purpose of the present invention is to propose a petroleum geological evaluation index assignment method to improve the index assignment efficiency of the petroleum geological evaluation unit, enhance the objectivity of the index assignment and provide a quantitative reference for the assignment.

[0009] To achieve the above object, the present invention proposes a petroleum geological evaluation index assignment method, comprising:

[0010] Step 1: Determine the type of the geological unit to be evaluated, and select corresponding geological parameters and evaluation criteria according to the type, wherein the geological unit to be evaluated corresponds to multiple indicators to be evaluated, and each indicator to be evaluated corresponds to multiple geological parameters;

[0011] Step 2: extracting the geological parameters of the indicator to be evaluated, and applying a neural network algorithm to obtain a first reference score of the indicator to be evaluated based on the geological parameters and the evaluation criteria through a pre-established neural network training sample library;

[0012] Step 3: selecting comparative area data corresponding to each of the geological parameters of the indicator to be evaluated from a pre-established comparative area database, and obtaining a second reference score of the indicator to be evaluated based on the comparative area data;

[0013] Step 4: When the difference between the first reference score and the second reference score is less than a set first threshold, the first reference score or the second reference score is selected as the score for the indicator to be evaluated; when the difference between the first reference score and the second reference score is greater than the first threshold, the second reference score is selected as the score for the indicator to be evaluated;

[0014] Step 5: Repeat steps 2 to 4 to obtain the score of each indicator to be evaluated corresponding to the geological unit to be evaluated.

[0015] Optionally, before step 1, the method further includes: establishing the comparison area database, and dissecting each geological indicator of at least one typical geological evaluation unit through geological analysis to obtain parameter values ​​and indicator scores of various geological parameters corresponding to each geological indicator, and adding various geological parameters and their parameter values ​​and indicator scores to the comparison area database.

[0016] Optionally, before step 1, the method further includes: establishing a neural network training sample library, and adding the geological parameters and parameter values ​​and index scores of the geological units evaluated in the early stage and the comparison area database to the neural network training sample library;

[0017] The neural network algorithm is trained using the neural network training sample library.

[0018] Optionally, step 2 further includes: when the number of sample data in the neural network training sample library is greater than or equal to a set second threshold, calculating the first reference score through the neural network algorithm.

[0019] Optionally, step 2 further includes: when the amount of sample data in the neural network training sample library is less than the second threshold, the first reference score is 0.

[0020] Optionally, step 4 further includes: when the first reference score is 0, using the second reference score as the score of the indicator to be evaluated.

[0021] Optionally, step 4 also includes: when the difference between the first reference score and the second reference score is less than the first threshold, adding the geological parameters and parameter values ​​corresponding to the indicator to be evaluated, as well as the first reference score, or the second reference score to the comparison area database and the neural network sample database.

[0022] Optionally, step 4 further includes: when the difference between the first reference score and the second reference score is greater than the first threshold, adding the geological parameters of the indicator to be evaluated and its parameter value and the second reference score to the neural network sample database.

[0023] Optionally, the neural network algorithm includes a back propagation neural network algorithm and a deep learning algorithm.

[0024] Optionally, the indicators to be evaluated include hydrocarbon source conditions, reservoir conditions and closure conditions; wherein the geological parameters corresponding to the hydrocarbon source conditions include source rock lithology, thickness, total organic carbon, organic matter maturity, and kerogen type.

[0025] The beneficial effects of the present invention are:

[0026] (1) The method of the present invention can be used for the evaluation of different exploration areas and different fields. The credibility of the evaluation results predicted by artificial intelligence (neural network algorithm) is high, which can replace manual assignment to a certain extent and improve the work efficiency of evaluation index assignment; through artificial intelligence assignment and comparison of area data, the comprehensive evaluation assignment has better objectivity, reduces the difference in the assignment of geological evaluation unit indicators with the same or similar geological parameters, and can provide a quantitative reference for the manual comprehensive index assignment.

[0027] (2) By adding the data of the evaluated geological units assigned each time into the comparison area database and the neural network training sample library, the geological index evaluation comparison area database and the neural network training sample library can be continuously enriched, thereby making the evaluation process more scientific and objective.

[0028] Some evaluation units with more detailed information can be added as comparison areas and neural network training sample data to enrich the comparison area database and neural network training sample database, which can significantly improve the objectivity and scientific nature of the evaluation.

[0029] The method of the present invention has other features and advantages that will be apparent from or will be described in detail in the accompanying drawings and subsequent detailed description incorporated herein, which together serve to explain the specific principles of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings, in which like reference numerals generally represent like components.

[0031] Figure 1 A step diagram of a petroleum geological evaluation index assignment method according to the present invention is shown.

[0032] Figure 2 The present invention shows an assignment flow chart of a petroleum geological evaluation index assignment method. DETAILED DESCRIPTION

[0033] The present invention will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention may be implemented in various forms and is not limited to the embodiments set forth herein. Rather, these embodiments are provided to make the present invention more thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0034] In this technical field, different evaluation systems often have some differences, but the geological parameter composition patterns of the indicators to be evaluated are similar. In geological comprehensive selection, multiple sets of comprehensive geological evaluation indicators are often applied. For example, conventional geological selection involves source conditions, reservoir conditions, and trap conditions. These indicators are composed of specific geological parameters (geological parameters). For example, the geological parameters of source conditions include: source rock lithology, thickness, total organic carbon (TOC), organic matter maturity (Ro), kerogen type, etc. The geological parameters of reservoir conditions include: reservoir lithology, reservoir physical properties, reservoir permeability, fracture development degree, etc. The geological parameters of trap conditions include: implementation degree, type, area, amplitude, target layer depth, etc. In order to more conveniently illustrate the scheme of the present invention, without losing generality, the specific implementation method of the present invention is explained by taking the source conditions as an example of assigning values ​​to the indicators to be evaluated.

[0035] Figure 1 A flowchart showing the steps of a petroleum geological evaluation index assignment method according to the present invention is shown. Figure 2 The present invention shows an assignment flow chart of a petroleum geological evaluation index assignment method.

[0036] like Figure 1 and Figure 2 As shown, a petroleum geological evaluation index assignment method according to the present invention includes:

[0037] Step 1: Determine the type of geological unit to be evaluated, and select the corresponding geological parameters and evaluation criteria according to the type, where the geological unit to be evaluated corresponds to multiple indicators to be evaluated, and each indicator to be evaluated corresponds to multiple geological parameters;

[0038] Step 2: Extract various geological parameters of an indicator to be evaluated, and apply the neural network algorithm to obtain the first reference score of the indicator to be evaluated based on various geological parameters and evaluation criteria through the pre-established neural network training sample library;

[0039] Step 3: Selecting comparison area data corresponding to various geological parameters of the indicator to be evaluated from a pre-established comparison area database, and obtaining a second reference score for the indicator to be evaluated based on the comparison area data;

[0040] Step 4: When the difference between the first reference score and the second reference score is less than the set first threshold, the first reference score or the second reference score is selected as the score of the indicator to be evaluated; when the difference between the first reference score and the second reference score is greater than the first threshold, the second reference score is selected as the score of the indicator to be evaluated;

[0041] Step 5: Repeat steps 2 to 4 to obtain the score of each indicator to be evaluated corresponding to the geological unit to be evaluated.

[0042] In one embodiment, before step 1, the method includes: establishing a comparison area database and a neural network training sample library.

[0043] Establishing the comparison area database involves geologically analyzing and dissecting each geological indicator of at least one typical geological evaluation unit to obtain the corresponding geological parameter values ​​and scores, and then adding each geological parameter, along with its values ​​and scores, to the comparison area database. In specific implementation, referencing the database's hydrocarbon source condition geological parameter data table (Table 1), geologically analyzing and dissecting the hydrocarbon source conditions of the typical geological evaluation unit, obtains the corresponding geological parameter values, and then enters these values ​​and scores into Table 1. In Table 1, exploration area, domain, lithology, and kerogen type are finite enumeration data types, while thickness, TOC, and Ro are numeric types. The comparison area data table for reservoir or trap condition geological parameters can be set with reference to Table 1.

[0044] Table 1: Data table of geological parameters of hydrocarbon source conditions in the comparison area database

[0045]

[0046] Establishing a neural network training sample library involves adding geological parameters, their values, and index scores from the database of previously evaluated geological evaluation units and comparison areas to the neural network training sample library; then using the neural network training sample library to train the neural network algorithm. Specifically, referring to Table 2, geological parameters, their values, and the evaluated geological index scores for previously evaluated geological evaluation units and dissected comparison areas are collected and classified to create a neural network training sample data table (Table 2). During the classification process, data tables are created based on enumeration types, and the neural network algorithm is trained based on the data in the training sample data table. The training sample data table for reservoir or trap condition geological parameters can be set up with reference to Table 2.

[0047] Table 2: Training sample data of hydrocarbon source condition geological parameters in the neural network sample database

[0048]

[0049] In step 1, the type of geological unit to be evaluated is determined, and corresponding geological parameters and evaluation criteria are selected based on the type. Specifically, each geological unit type corresponds to different evaluation parameters and evaluation criteria. Geological unit types include, but are not limited to, eastern clastic rock domain units, western clastic rock domain units, southern clastic rock domain units, marine clastic rock domain units, southern carbonate rock domain units, western carbonate rock domain units, shale oil domain units, and shale gas domain units. These can be further refined or combined based on actual research needs. Evaluation criteria are commonly used in the field. Evaluation criteria for different types of geological units include: Technical Specification for Basin Evaluation (SY / T 5519-1996), Technical Specification for Trap Evaluation (SY / T 5520-1996), Technical Specification for Reservoir Evaluation (SY / T 5521-1996), Single-Well Clastic Reservoir Evaluation (SY / T 5717-95), and Single-Well Carbonate Reservoir Evaluation (SY / T 6038-94). Those skilled in the art can select from a variety of evaluation criteria based on their specific circumstances, and these are not detailed here. The geological unit to be evaluated includes multiple indicators to be evaluated, and each indicator to be evaluated includes multiple geological parameters. In one example, the indicators to be evaluated of the geological unit to be evaluated include hydrocarbon source conditions, reservoir conditions and closure conditions, wherein the geological parameters of hydrocarbon source conditions include source rock lithology, thickness, total organic carbon, organic matter maturity, and kerogen type.

[0050] In step 2, various geological parameters of the indicator to be evaluated are extracted. Based on the geological parameters and evaluation criteria, a neural network algorithm is applied to a pre-established neural network training sample library to obtain a first reference score for the indicator to be evaluated. When the number of sample data in the neural network training sample library is greater than or equal to a set second threshold, the first reference score is calculated using the neural network algorithm. When the number of sample data in the neural network training sample library is less than the second threshold, the first reference score is 0. Specifically, the geological parameters of the hydrocarbon source conditions of the object to be evaluated are extracted, and the score of the indicator to be evaluated for the geological unit to be evaluated is calculated using an artificial intelligence neural network algorithm. The neural network algorithm can adopt existing mature algorithms such as back propagation neural networks (BPNs) and deep learning. With the sample library unchanged, a prediction model is established through a single training run and can be applied multiple times. In specific implementation, the second threshold can be set to 10. That is, when the sample library has fewer than 10 sample data, the predicted value is directly assigned a score of 0, indicating that the predicted value is not a reference value and the sample library needs to be increased. When the number of sample data exceeds (or equals) 10, the first reference score for the neural network prediction is assigned.

[0051] In step 3: through the pre-established comparison area database, select comparison area data with the same or similar geological parameters as the indicators to be evaluated, and use the comparison area data as a reference and according to the evaluation criteria to obtain a second reference score for the indicator to be evaluated through manual assignment. Specifically, by comparing the geological parameters of the indicator to be evaluated with those in the comparison area database, combined with the evaluation criteria, and referring to the score of the comparison area data, the score of the indicator to be evaluated (the second reference score) is manually given. It should be noted that in the process of manual assignment using the comparison area data, first, the parameter data of the evaluation indicators of the unit to be evaluated are retrieved, and then the parameter data and corresponding indicator scores of the corresponding indicators of the corresponding geological unit type are extracted from the comparison area database (such as extracting the same or similar comparison area data), and combined with the indicator assignment standard of the geological unit type, a reasonable score for the evaluation indicator of the unit to be evaluated is given through manual experience comparison and judgment.

[0052] In step 4: when the difference between the first reference score and the second reference score is less than the set first threshold, the first reference score or the second reference score is selected as the score of the indicator to be evaluated; when the difference between the first reference score and the second reference score is greater than the first threshold, the second reference score is selected as the score of the indicator to be evaluated. In the specific implementation process, it can be set that when the first reference score is 0 (indicating that the amount of data in the neural network sample library is too small to give a predicted first reference score), the second reference score is directly used as the score of the indicator to be evaluated, that is, when the first reference score calculated by the neural network is 0 or deviates greatly from the geological indicator score reflected by the actual geological parameters, the neural network predicted score is ignored. For example, when the first threshold is set to 0.1, that is, when the deviation between the first reference score and the second reference score exceeds ±0.2, the first reference score given by the neural network is ignored, and the second reference score is directly used as the final assignment of the indicator to be evaluated.

[0053] This step also includes: when the difference between the first reference score and the second reference score is less than a first threshold value (e.g., less than 0.1), adding the geological parameters corresponding to the geological indicator to be evaluated to the comparison area database and the neural network sample database; and adding the first reference score or the second reference score corresponding to the geological indicator to be evaluated to the comparison area database and the neural network sample database. When the difference between the first reference score and the second reference score is greater than the first threshold value, adding the geological parameters of the geological indicator to be evaluated to the neural network sample database; and adding the second reference score corresponding to the geological indicator to be evaluated to the neural network sample database. Specifically, when the first reference score and the second reference score are substantially consistent (the difference is less than 0.1), it indicates that the score predicted by the neural network algorithm (artificial intelligence) is substantially consistent with the manually calculated score, and the geological parameters corresponding to the evaluation indicator are relatively detailed. In this case, the geological parameters corresponding to the evaluation indicator assigned this time and the final score can be added to the comparison area database and the neural network training sample database. If the first reference score predicted by the neural network algorithm deviates significantly from the geological index score reflected by the actual geological parameters (the manually calculated second reference score), that is, the first reference score predicted by the neural network algorithm is inaccurate, indicating that the neural network training sample database lacks relevant data for this type of geological parameter. The geological parameters related to the geological unit to be evaluated can be added to the neural network training sample database as training sample data. When adding, the evaluation index score is manually assigned a second reference score. This method can continuously improve the comparison area database, increase the training data for the neural network algorithm, improve the accuracy of subsequent geological unit index assignments, and increase quantitative reference data.

[0054] The process of looping step 2 to step 4 can complete the assignment process of the remaining indicators to be evaluated in the geological unit to be evaluated, and the evaluation score of each geological indicator in the geological unit to be evaluated can be obtained.

[0055] To further illustrate this solution, this application also provides a specific application example of the petroleum geological evaluation index assignment method, which specifically includes the following contents:

[0056] Using the method of the present invention, we evaluated and assigned hydrocarbon source conditions for 10 geological evaluation units within the clastic rock domain of the eastern exploration area. The source rocks of these evaluated units are clastic rocks, primarily mudstones, and have kerogen types I and II. The pre-evaluation comparison area database included data from two relevant comparison areas (see Table 3). The neural network training sample database included data from seven Type I mudstone kerogen source rocks and three Type II source rocks within the clastic rock domain of the eastern exploration area, for a total of 10 training samples (see Table 4).

[0057] Table 3: Training sample data of hydrocarbon source geological parameters in the comparison area database

[0058]

[0059] Table 4: Training sample data of hydrocarbon source condition geological parameters in the neural network sample database

[0060]

[0061] After performing a single evaluation and assignment, we obtained hydrocarbon source condition scores for 10 evaluation units (Table 5). Overall, the comparison area provides a reference for geological indicator evaluation and assignment. The overall error between the scores predicted by the neural network algorithm and the comprehensive assignment is 0.03 < 0.1 (units 4, 9, and 10 are intelligent predictions after the training sample library is added). Furthermore, one more sample was added to the comparison area database (Table 6), and three more samples were added to the neural network training sample library (Table 7). Therefore, the combined use of the comparison area and the neural network algorithm for assignment has shown promising results.

[0062] Table 5: Comparison of the neural network algorithm and manual comprehensive assignment of hydrocarbon source conditions for the 10 geological evaluation units in the eastern exploration area

[0063]

[0064] Table 6: Comparison area data table of hydrocarbon source condition geological parameters in the comparison area database after assignment

[0065]

[0066] Table 7: Training sample data table of hydrocarbon source condition geological parameters in the neural network sample database after assignment

[0067]

[0068] The above examples show that:

[0069] (1) The application of the method of the present invention in the evaluation of 10 geological evaluation units in the clastic rock field of the eastern exploration area shows that the overall error between the predicted scores by the neural network algorithm (artificial intelligence) and the manual comprehensive assignment is 0.03<0.1. The artificial intelligence prediction results are highly credible and can replace manual assignment to a certain extent, thereby improving the work efficiency of evaluation index assignment.

[0070] (2) The method of the present invention can be applied to evaluate different exploration areas and different fields, and can continuously enrich the geological index evaluation comparison area database and the neural network training sample database, making the evaluation process more scientific and objective.

[0071] While various embodiments of the present invention have been described above, the above description is intended to be illustrative, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for assigning values ​​to petroleum geological evaluation indicators. It is characterized in that include: Step 1: Determine the type of the geological unit to be evaluated, and select corresponding geological parameters and evaluation criteria according to the type, wherein the geological unit to be evaluated corresponds to a plurality of indicators to be evaluated, and each indicator to be evaluated corresponds to a plurality of geological parameters; Step 2: extracting various geological parameters of the indicator to be evaluated, and applying a neural network algorithm to obtain a first reference score of the indicator to be evaluated according to various geological parameters and the evaluation criteria through a pre-established neural network training sample library; Step 3: selecting the comparison area data corresponding to each of the geological parameters of the indicator to be evaluated through a pre-established comparison area database, and obtaining a second reference score of the indicator to be evaluated based on the comparison area data; Step 4: When the difference between the first reference score and the second reference score is less than a set first threshold, the first reference score or the second reference score is selected as the score of the indicator to be evaluated; when the difference between the first reference score and the second reference score is greater than the first threshold, the second reference score is selected as the score of the indicator to be evaluated; Step 5: Repeat steps 2 to 4 to obtain the score of each of the indicators to be evaluated corresponding to the geological unit to be evaluated; Before step 1, the method further includes: establishing the comparison area database, dissecting each geological indicator of at least one typical geological evaluation unit through geological analysis to obtain parameter values ​​and index scores of various geological parameters corresponding to each geological indicator, and adding various geological parameters and their parameter values ​​and index scores to the comparison area database; establishing a neural network training sample library, and adding the geological parameters and their parameter values ​​and index scores in the evaluated geological units and the comparison area database to the neural network training sample library; Using the neural network training sample library to train the neural network algorithm; The step 2 further includes: when the number of sample data in the neural network training sample library is greater than or equal to a set second threshold, calculating the first reference score through the neural network algorithm; When the amount of sample data in the neural network training sample library is less than the second threshold, the first reference score is 0; The step 4 further comprises: when the difference between the first reference score and the second reference score is less than the first threshold, adding the geological parameter and parameter value corresponding to the indicator to be evaluated and the first reference score or the second reference score to the comparison area database and the neural network sample database; When the difference between the first reference score and the second reference score is greater than or equal to the first threshold, the geological parameters of the indicator to be evaluated and its parameter value and the second reference score are added to the neural network sample database.

2. The petroleum geology evaluation index assignment method according to claim 1, It is characterized in that The step 4 also includes: when the first reference score is 0, using the second reference score as the score of the indicator to be evaluated.

3. The petroleum geology evaluation index assignment method according to claim 1, It is characterized in that The neural network algorithm includes a back propagation neural network algorithm and a deep learning algorithm.

4. The petroleum geology evaluation index assignment method according to claim 1, It is characterized in that The indicators to be evaluated include hydrocarbon source conditions, reservoir conditions and closure conditions; wherein the geological parameters corresponding to the hydrocarbon source conditions include source rock lithology, thickness, total organic carbon, organic matter maturity and kerogen type.