An auxiliary method for drilling fluid formulation design based on formation information and well information

Abstract

The present invention discloses an auxiliary method for drilling fluid formula design based on formation information and well information, including: collecting drilling fluid case data; constructing a database for storing drilling fluid case data and building a model; preprocessing case feature data; assigning different weights to different features; defining a similarity calculation function; calculating the similarity of new case features and outputting recommendation results; and modifying and utilizing the recommendation results. Beneficial effects of the present invention: 1. By standardizing and organizing historical information, building a database to store drilling fluid case data and building a model, this efficient management of data improves the design efficiency of drilling fluid formulas. 2. The system constructs a similarity calculation function, calculates the similarity between new cases and historical cases, intelligently selects the optimal solution, and outputs the recommendation results, which greatly saves time and reduces costs.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling fluid proportioning, in particular to an auxiliary method for drilling fluid formulation design based on formation information and well information. Background Art

[0002] Drilling fluid formula design is one of the most important steps in drilling fluid engineering design. A successful drilling fluid formula design can effectively reduce the complexity of the wellbore and ensure efficient and safe drilling. When designing the drilling fluid formula for a well, the following factors are usually considered: the formation and lithology encountered, ground stress, formation temperature, well depth, well type, well type, wellbore structure, etc. Drilling fluid design generally includes the following steps: (1) Analyze the geological conditions. (2) Select the drilling fluid type. (3) Determine the drilling fluid density. (4) Determine the drilling fluid performance. Before designing the drilling fluid, in order to improve the design efficiency, it is usually first referred to the drilling fluid formula and performance indicators used in the drilled adjacent wells based on information such as the formation and well design. If there is a similar case that meets the requirements, it will be directly adopted. Drilling fluid well history reports and other materials summarize a large amount of complete drilling fluid information from existing wells. This includes formation information, basic well information data (such as well depth, well inclination, formation and lithology, and formation pressure coefficient), as well as data on drilling fluid formulations and drilling fluid properties. This information can serve as an important basis for drilling fluid design for undrilled wells. However, there is currently a lack of standardized documentation of drilling fluid historical information for existing wells, making it difficult to quickly find and reference relevant case studies when designing drilling fluid formulations. Furthermore, manually searching for historical cases and designing new cases significantly increases time costs. Therefore, the present invention organizes and summarizes drilling fluid historical data from drilling fluid well history reports and other materials and stores it in a database. Furthermore, based on this drilling fluid historical data, an auxiliary method for drilling fluid formulation design based on formation and well information is provided. This is of great significance for the efficient management of drilling fluid historical data and improving the efficiency of drilling fluid formulation design. Summary of the Invention

[0003] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0004] In view of the above problems and / or the problems existing in the existing drilling fluid formulation design, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to solve the problem of lack of standardized organization of historical information of drilling fluids of drilled wells and the problem that manual mixing of drilling fluids greatly increases the time cost.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an auxiliary method for drilling fluid formulation design based on formation information and well information, which comprises:

[0007] Collect drilling fluid case data;

[0008] Build a database to store drilling fluid case data and build models;

[0009] Preprocess case feature data;

[0010] Assign different weights to different features;

[0011] Define similarity calculation function;

[0012] Calculate the similarity of new case features and output recommendation results;

[0013] Modification and utilization of recommendation results.

[0014] As a preferred embodiment of the auxiliary method for designing drilling fluid formulation based on formation information and well information of the present invention, the collection of drilling fluid case data includes:

[0015] Drilling fluid well history report, drilling engineering report;

[0016] Well information: oil field, block, well depth, wellbore size, well type, well category;

[0017] Geological information: lithology, formation pressure coefficient, formation temperature;

[0018] Drilling fluid information: drilling fluid type, drilling fluid formula, main performance indicators;

[0019] The main performance indicators include: density, viscosity, YP value, API value, pH value, PV value;

[0020] The database construction includes building a drilling fluid case library based on MYSQL and establishing three sub-tables of well information, geological information and drilling fluid information respectively for storing drilling fluid historical data.

[0021] As a preferred embodiment of the auxiliary method for designing drilling fluid formulation based on formation information and well information of the present invention, the storing of drilling fluid case data and building of the model includes:

[0022] Input characteristics, including formation lithology, formation pressure coefficient, formation temperature, oil field name, block name, well type, well category, well depth, and wellbore size;

[0023] Output parameters include drilling fluid system, drilling fluid formula, and drilling fluid performance information;

[0024] Drilling fluid performance information includes drilling fluid density, viscosity, YP value, API value, pH value, and PV value.

[0025] As a preferred embodiment of the auxiliary method for drilling fluid formulation design based on formation information and well information of the present invention, the preprocessing of case feature data includes:

[0026] To encode single-value text features into 0-1, and to encode multi-value text features into multi-value; to normalize the data of numerical features.

[0027] As a preferred embodiment of the auxiliary method for drilling fluid formulation design based on formation information and well information of the present invention, the method of assigning different weights to different features includes:

[0028] Different weights are assigned to text attributes. Text attribute features include oil field W oilfeild 、Block W block 、Well type W type , wellbetsu W cat 、lithology W rock , satisfying W oilfeild +W block +W rock +W type +W cat =1;

[0029] Different weights are assigned to numerical attributes. The numerical attribute characteristics include the formation pressure coefficient W pre , formation temperature W temp , Jing Shen W depth Wellbore size W size , satisfying W depth +W pre +W temp +W size =1.

[0030] As a preferred solution of the auxiliary method for drilling fluid formulation design based on formation information and well information of the present invention, wherein: the definition of similarity calculation function includes:

[0031] Text type similarity: When the retrieved text attributes are the same as the text attributes corresponding to the case library, the similarity is set to 1, otherwise it is set to 0. The text type similarity calculation formula is:

[0032]

[0033] Where W i represents the weight of the i-th text attribute, C i and D iThey represent the text attributes of new cases and existing cases respectively, and k represents the value of the text attribute;

[0034] Numerical attribute similarity: Euclidean distance is used to calculate the similarity. The formula for calculating the numerical attribute similarity is:

[0035]

[0036] Among them, A and B represent the attributes of new cases and existing cases respectively, n represents the number of numerical attributes, and W i Represents the weight of the i-th attribute, and the sum of the attribute weights is 1;

[0037] Total case similarity = text attribute similarity + numerical attribute similarity, the formula is:

[0038] TotalSim=Sim(C i ,D i )+Sim(A,B).

[0039] As a preferred embodiment of the auxiliary method for drilling fluid formulation design based on formation information and well information described in the present invention, the method comprises calculating the similarity of new case features and outputting recommendation results, including calculating the overall similarity using the similarity calculation function based on the newly input retrieval features, matching the three cases with the highest similarity with the recommendation results, and recommending the drilling fluid type and drilling fluid formulation of the case with the highest similarity as the recommendation result. For the recommendation results of drilling fluid performance parameters, the average of each drilling fluid performance in the three cases is calculated as the recommendation result.

[0040] As a preferred embodiment of the auxiliary method for drilling fluid formulation design based on formation information and well information of the present invention, the modification and utilization of the recommended results include:

[0041] When the recommendation results meet the user's requirements, they can be used directly. If they do not meet the requirements, the recommendation results can be modified based on the actual situation by referring to the case similarity.

[0042] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor implements the steps of the above method when executing the computer program.

[0043] A computer-readable storage medium stores a computer program thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0044] The beneficial effects of the present invention are:

[0045] 1. By standardizing and organizing historical information, building a database to store drilling fluid case data and constructing models, this efficient data management improves the efficiency of drilling fluid formulation design.

[0046] 2. The system builds a similarity calculation function to calculate the similarity between new cases and historical cases, intelligently selects the optimal solution, and outputs the recommended results, greatly saving time and reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort. Among them:

[0048] Figure 1 This is a flow chart of an auxiliary method for designing a drilling fluid formulation based on formation information and well information in Example 1.

[0049] Figure 2 This is a flow chart for model construction of an auxiliary method for drilling fluid formulation design based on formation information and well information in Example 1. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0053] Example 1

[0054] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an auxiliary method for drilling fluid formulation design based on formation information and well information. The specific operation steps are as follows:

[0055] Step 1: Data collection. Collect basic data from drilling fluid well summary reports, drilling engineering reports, etc. to build a drilling fluid formula case library. A complete drilling fluid case specifically includes the following information: (1) geological information: oil field, block, lithology, formation pressure coefficient, formation temperature; (2) well information: oil field, block, well depth, wellbore size, well type, well category; (3) drilling fluid information: drilling fluid type, drilling fluid formula, main performance indicators (drilling fluid density, viscosity, YP value, API value, pH value, PV value). Some of the collected case data are shown in Table (1), Table (2), and Table (3):

[0056] Table (1) Well information table

[0057]

[0058] Table (2) Stratigraphic information table

[0059]

[0060] Table (3) Drilling fluid information table

[0061]

[0062]

[0063] Step 2: Data storage. Build a drilling fluid case library based on MYSQL and create a database DrilingFuild_Case_DB. To facilitate data management and ensure data integrity and uniformity, create three forms: 1) Well information table, named Well_Case; add a primary key ID to the form, set it to auto-increment and long integer; then add other fields in sequence, namely: oil field, block, well depth, wellbore size, well type, well category; 2) Formation information table, named Formation_Case; add a primary key ID to the form, set it to auto-increment and long integer; then add other fields in sequence, namely: lithology, formation pressure coefficient, formation temperature; 3) Drilling fluid information table, named DrilingFuild_Case; add a primary key ID to the form, set it to auto-increment and long integer; then add other fields in sequence, namely: drilling fluid type, drilling fluid formula, density, viscosity, YP value, API value, PH value, PV value. The specific setting types of each table and corresponding fields are shown in Table (4), Table (5), and Table (6):

[0064] Table (4): Well information table

[0065]

[0066]

[0067] Table (5): Stratigraphic information table

[0068] Field Code Field Name Field Type Is it a primary key? Can be empty ID Primary key ID Long integer (auto-increment) yes no formation_lithology Lithology Text no no pressure_coff Formation pressure coefficient Double precision no no formation_temp formation temperature Single precision no yes

[0069] Table (6): Drilling fluid information table

[0070] Field Code Field Name Field Type Is it a primary key? Can be empty ID Primary key ID Long integer (auto-increment) yes no Mud_type Drilling fluid type Text no yes Mud_formulation Drilling fluid formulation Text no no Density density Double precision no yes Viscosity Viscosity Single precision no yes YP YP value Single precision no yes API API Value Single precision no yes PH pH value Single precision no yes

[0071] Step 3: Build the model. Based on the case data in the database, use the pymysql module pymysql.connect method to establish a data export interface, and obtain data from the database to build a drilling fluid formula recommendation model. The input features of the drilling fluid formula recommendation system invented in this article specifically include well information and formation information, a total of 9 features, as follows: formation lithology, formation pressure coefficient, formation temperature, oil field name, block name, well type, well type, well depth, and wellbore size. The output parameters include drilling fluid system, drilling fluid formula, and drilling fluid performance information. Refer to the model construction flow chart Figure 2 .

[0072] First, the characteristic parameters of the original data are preprocessed, including:

[0073] 1) Feature extraction of text attributes. Text attributes include: oil field, block, well type, well category, and lithology. "Oil field", "block", "well type", and "well category" are all single-value text features, which are encoded as 0-1. "Lithology" is a multi-value feature and is encoded in the following way: if the feature value is one or more in the value range, the code of the corresponding position is 1, and the remaining bits are 0. For example, when the value of the "lithology" feature is "sandstone", the code is 000001; when the value is "sandstone, mudstone", the code is 000011; when the value is "sandstone, mudstone, carbonate rock", the code is "000111". The coding mapping relationship of each text feature is shown in the following table (7):

[0074] Table (7) Coding mapping table

[0075] Well Type coding Jingbie coding Lithology coding Naoi 0001 Exploration well 01 sandstone 000001 horizontal wells 0010 Development wells 10 mudstone 000010 Directional wells 0100 Carbonate rocks 000100 Extended reach wells 1000 Sandstone, mudstone 000011

[0076] 2) Preprocessing of numerical attributes. The input numerical features include: formation pressure coefficient, formation temperature, well depth, and wellbore size. To prevent certain attributes from having an excessive impact on the similarity calculation, a unified normalization process is performed (the normalization formula is shown in (1)) to map feature data of different ranges to the same interval [0, 1]. This is achieved using the MinMaxScaler function.

[0077] X=(X-X_min) / (X_max-X_min) (1)

[0078] Where: X_max represents the maximum value of the feature, and X_min represents the minimum value of the feature.

[0079] Step 4: Assign weights to different attributes. Different features have different degrees of influence on drilling fluid formulation design, so the feature parameters with greater influence on drilling fluid formulation design are given higher weights. This is to take their importance into account in the similarity calculation (the weights of each attribute can be customized by the user based on different geological information and well information). For the design of drilling fluid formulation, well depth, formation pressure coefficient, and formation temperature may be more important for recommending drilling fluid type, so they can be given higher weights.

[0080] A. The text attribute weights defined in this experiment are shown in Table (8) and satisfy: W oilfeild +W block +W rock +W type +W cat =1;

[0081] Table (8) Text attribute weight table

[0082] Text properties oilfield Block Stratigraphic lithology Well Type Jingbie Weight code <![CDATA[W oilfeild ]]> <![CDATA[W block ]]> <![CDATA[W rock ]]> <![CDATA[W type ]]> <![CDATA[W cat ]]> Weight value 0.1 0.1 0.5 0.1 0.1

[0083] B. The numerical attribute weights defined in this experiment are shown in Table (9) and satisfy the following relationship: W depth +W pre +W temp +W size =1;

[0084] Table (9) Numerical attribute weight table

[0085] Numeric attributes well deep Formation pressure coefficient formation temperature Wellbore size Weight code <![CDATA[W depth ]]> <![CDATA[W pre ]]> <![CDATA[W temp ]]> <![CDATA[W size ]]> Weight value 0.25 0.5 0.1 0.15

[0086] Step 5: Define the similarity calculation function. Use different methods to calculate the similarity of different types of attributes. The total similarity of the case = text feature similarity + numerical feature similarity. The details are as follows:

[0087] Calculation of text attribute similarity. For text features such as lithology, well type, well category, oilfield name, and block name, the following method is used to determine feature similarity: when the text attributes of the new case are the same as those in the case library, the similarity is set to 1; otherwise, it is set to 0. The total similarity of text attributes is shown in Equation (2).

[0088]

[0089] Where W i represents the weight of the i-th text attribute, Ci and Di represent the text attributes of new cases and existing cases respectively, and k represents the value of the text attribute.

[0090] Calculation of similarity of numerical attributes. For numerical attributes such as formation pressure coefficient, formation temperature, well depth, and wellbore size, the Euclidean distance is used to calculate the similarity. The calculation formula is shown in (3).

[0091]

[0092] Among them, A and B represent the attributes of new cases and existing cases respectively, n represents the number of numerical attributes, and W i represents the weight of the i-th attribute, and the sum of the attribute weights is 1. Therefore, the total similarity of the cases is as shown in formula (4).

[0093] TotalSim=Sim(C i ,D i )+Sim(A,B); (4)

[0094] Step 6: Similarity Calculation and Result Output. Based on all the characteristic parameters of the new case input, the similarity between each case and the search criteria is calculated using the similarity function defined in Step 5. The three cases with the highest similarity are matched. For drilling fluid type and formulation recommendations, the drilling fluid type and formulation of the case with the highest similarity are used as the recommended result. For drilling fluid performance recommendations, the average drilling performance parameters of these three cases are calculated as the recommended result. For further explanation, a specific test case is provided below.

[0095] Specifically: This test case is the recommended drilling fluid type, formula and drilling fluid performance requirements for the 3000m deep Dibei A well.

[0096] According to the formation information and well information of Dibei A Well: Dibei A Well is a pre-exploration well in the Kuche Depression of the Tarim Basin. The well type is a vertical well. According to the drilling engineering design, the 3000m section of Dibei A Well is a second opening wellbore with a wellbore size of 333.4mm. The geothermal gradient of this block is 0.027℃ / m. The formation pressure coefficient of the 2584-3020m well section is predicted to be 1.09-1.13. According to the lithologic description: the sandstone mudstone section is the well section 2550-2850m, with an estimated drilling thickness of 300m. The lithology is mainly brown-gray thick to medium-thick layered siltstone. Based on the above information, the characteristic information used to design the 3000m drilling formula is extracted, as shown in Table (10):

[0097] Table (10) Test case information table

[0098]

[0099] According to the weights of different attributes defined in step 4, the above case features are used to calculate the total similarity between the new case and the existing case using the similarity calculation function defined in step 5, and the three cases with the highest similarity are matched. For the recommendation of drilling fluid type and drilling fluid formula, the drilling fluid type and drilling fluid formula of the case with the highest similarity are used as the recommendation results. For the recommendation of drilling fluid properties, the average drilling fluid density and viscosity of these three cases are calculated as the recommendation results, and the overall similarity of the cases is output. The recommended drilling fluid formula design and requirements at 3000m in Dibei A well are shown in Table (11).

[0100] Table (11) Recommended results table

[0101]

[0102] The actual drilling fluid formula and performance parameters were compared with the recommended results. The comparison results are shown in Table (12):

[0103] Table (12) Comparison between recommended results and actual situation

[0104]

[0105] Step 8: Reuse or modify the recommended results. When the recommended results are the same as the input drilling fluid performance or meet the requirements, the recommended results can be used directly. If they do not meet the requirements, they can be modified.

[0106] Example 2

[0107] The second embodiment of the present invention is different from the first embodiment in that: in order to verify and illustrate the technical effects adopted in this method, this embodiment adopts a traditional technical solution and conducts comparative tests with the method of the present invention, and compares the test results by means of scientific demonstration to verify the real effect of this method.

[0108] To illustrate the advantages and auxiliary effects of the present invention, a specific comparative case is given below: Assume that when designing the Dibei A well, the drilling fluid type, formula, and performance data used in the most similar case were referenced and adopted. For the sake of comparison, the performance data obtained by the traditional design method and the performance data and actual use data obtained by the present invention are compared, as shown in Table (13) (It should be noted that the present invention method is based on the reference to the most similar case and takes the average value of the performance data of the first three most similar cases).

[0109] Table (13) Comparison between traditional method and our invented method

[0110]

[0111] It can be concluded from the above table that our invention has brought unexpected technical effects. Our invention not only improves the design efficiency of drilling fluid and reduces time cost, but also the performance accuracy of the formulated drilling fluid is much higher than that of traditional methods.

[0112] Example 3

[0113] One embodiment of the present invention is different from the previous two embodiments in that if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0114] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0115] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0116] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An auxiliary method for drilling fluid formulation design based on formation information and well information, characterized in that: include, Collect drilling fluid case data; Build a database to store drilling fluid case data and build models; Preprocess case feature data; Assign different weights to different features; Define the similarity calculation function; Calculate the similarity of new case features and output recommendation results; Modification and utilization of recommended results; The collection of drilling fluid case data includes: Drilling fluid well history report, drilling engineering report; Well information: oil field, block, well depth, well size, well type, well category; Geological information: lithology, formation pressure coefficient, formation temperature; Drilling fluid information: drilling fluid type, drilling fluid formula, main performance indicators; The main performance indicators include: density, viscosity, YP value, API value, pH value, PV value; The database construction includes: constructing a drilling fluid case library based on MYSQL to establish three sub-tables of well information, geological information and drilling fluid information respectively, for storing drilling fluid historical data; The storing of drilling fluid case data and building of models includes: Based on the case data in the database, the pymysql.connect method of the pymysql module is used to establish a data export interface, and data is obtained from the database to build a drilling fluid formula recommendation model; Input features into the recommended model, including formation lithology, formation pressure coefficient, formation temperature, oil field name, block name, well type, well category, well depth, and wellbore size; Output parameters include drilling fluid system, drilling fluid formula, and drilling fluid performance information; Drilling fluid performance information includes drilling fluid density, viscosity, YP value, API value, pH value, and PV value; The preprocessing of case feature data includes 0-1 encoding of single-value text features and multi-value encoding of multi-value text features; normalization of data of numerical features; The assigning of different weights to different features includes assigning different weights to text attributes, where the text attribute features include oilfield W oilfeild 、Block W block 、Well Type W type , wellbetsu W cat 、Lite W rock , satisfying W oilfeild + W block +W rock +W type + W cat =1; Different weights are assigned to numerical attributes. The numerical attribute characteristics include the formation pressure coefficient W pre , formation temperature W temp , Jing Shen W depth , Wellbore size W size , satisfying W depth + W pre + W temp + W size =1; The definition of similarity calculation function includes: Text type similarity: When the retrieved text attribute is the same as the text attribute corresponding to the case library, the similarity is set to 1, otherwise it is set to 0. The text type similarity calculation formula is: ； in, W i represents the weight of the i-th text attribute, C i and D i They represent the text attributes of new cases and existing cases respectively, and k represents the value of the text attribute; Numerical attribute similarity: The Euclidean distance is used to calculate the similarity. The formula for calculating the numerical attribute similarity is: ； Where A and B represent the attributes of new cases and existing cases respectively, and n represents the number of numeric attributes. W i represents the weight of the i-th attribute, and the sum of the attribute weights is 1; Total case similarity = text attribute similarity + numerical attribute similarity, the formula is: ； The calculating of the similarity of the new case features and outputting the recommendation results includes, according to the newly input retrieval features, calculating the overall similarity using the similarity calculation function, matching the three cases with the highest similarity with the recommendation results, and for the recommendation of the drilling fluid type and the drilling fluid formula, taking the drilling fluid type and the drilling fluid formula of the case with the highest similarity as the recommendation result, and for the recommendation result of the drilling fluid performance parameters, calculating the average of each drilling fluid performance in the three cases as the recommendation result; The modification and utilization of the recommendation results include: when the recommendation results meet the user's requirements, they can be directly used; if they do not meet the requirements, the recommendation results can be modified according to the actual situation with reference to the case similarity.

2. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to claim 1 are implemented.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images