CN109446538B

CN109446538B - Method for obtaining relation model of water injection and oil production well and method for determining yield and water injection amount

Info

Publication number: CN109446538B
Application number: CN201810644360.3A
Authority: CN
Inventors: 李志元; 翟莹莹; 郭琦
Original assignee: Beijing Gridsum Technology Co Ltd
Current assignee: Beijing Gridsum Technology Co Ltd
Priority date: 2018-06-21
Filing date: 2018-06-21
Publication date: 2021-08-17
Anticipated expiration: 2038-06-21
Also published as: WO2019242296A1; CN109446538A

Abstract

The embodiment of the invention discloses a method for obtaining a relation model of a water injection well and a production well and a method for determining yield and water injection quantity, which can obtain working parameters and production positions of all water injection wells and working parameters and production positions of all oil production wells in a first oil and gas field development block in a historical time period, use all the working parameters as training data, use the same production positions as constraint conditions, and perform machine learning on the working parameters of the water injection wells and the oil production wells at the same production positions in the training data to obtain the relation model of the water injection wells and the oil production wells in the first oil and gas field development block. The embodiment of the invention establishes the relation model of the water injection well and the oil production well through machine learning of the working parameters in the historical time period, and the model reflects the relation between the working parameters of each water injection well and the working parameters of each oil production well, so that the method can directly use the model to determine the yield of the oil production well or the water injection amount of the water injection well, and is simple and convenient.

Description

Method for obtaining relation model of water injection and oil production well and method for determining yield and water injection amount

Technical Field

The invention relates to the field of fossil fuel production, in particular to a method for obtaining a relation model of a water injection and oil production well and a method for determining yield and water injection quantity.

Background

The oilfield flooding development is the most common development mode for compensating the underground deficit caused by the extraction of crude oil and maintaining the oil yield of an oil well after the pressure of a reservoir falls in the middle and later periods of oilfield production. The oilfield flooding development mode is as follows: and injecting qualified water into a water injection well, introducing the injected water into the underground reservoir by the water injection well, and displacing the crude oil in the underground reservoir by the injected water. The oil well produces the injected water and the crude oil carried by the injected water to the ground.

It is obvious that the key of the water injection development of the oil field is that the relation between the water injection well and the oil production well is known through the matching of the water injection well and the oil production well, and the relation is particularly important for displacing crude oil in a reservoir stratum between the water injection well and the oil production well to the maximum extent. Because the movement of underground fluid cannot be observed and identified by naked eyes, the prior art generally analyzes and determines the relationship between a water injection well and a production well indirectly through two modes of tracer and interwell interference test.

However, the detection processes of the two modes are complex, and high-frequency monitoring cannot be realized.

Disclosure of Invention

In view of the above problems, the present invention has been made to provide a water injection and production well relationship model obtaining method and a production and water injection amount determining method that overcome or at least partially solve the above problems, the scheme being as follows:

a method for obtaining a relation model of a water injection well and a production well comprises the following steps:

obtaining the working parameters of each water injection well in a first oil and gas field development block in the historical time period and the production position where each water injection well is located, and obtaining the working parameters of each oil production well in the first oil and gas field development block in the historical time period and the production position where each oil production well is located, wherein the working parameters of each water injection well at least comprise: the water injection quantity, the working parameters of each oil production well at least comprise: yield;

using each working parameter as training data, using the same production position as a constraint condition, and performing machine learning on the working parameters of the water injection well and the oil production well of the same production position in the training data to obtain a relation model of the water injection well and the oil production well of the first oil and gas field development block, wherein the input parameters of the relation model of the water injection well and the oil production well comprise: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well comprise the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the water injection well and oil production well relation model comprise the yield, the output parameters of the water injection well and oil production well relation model comprise: the water injection amount.

Optionally, the operating parameters of the water injection well further include: at least one of production time, oil pressure, and casing pressure; and/or the working parameters of the oil production well further comprise: at least one of production time, water content, oil pressure, casing pressure and working fluid level height.

Optionally, the working parameters of the water injection well and the oil production well at the same production position in the training data are obtained after machine learning: and the influence weight of the working parameters of the water injection wells at the same production layer position in the first oil-gas field development block on the working parameters of the oil production wells.

A production well production determination method comprising:

obtaining planned water injection quantity of at least one water injection well in a first oil and gas field development block in a first time period;

and inputting the obtained planned water injection quantity into the water injection well and oil production well relation model obtained by any one of the water injection well and oil production well relation model obtaining methods, and obtaining the yield of at least one oil production well in the first oil and gas field development area block within the first time period output by the water injection well and oil production well relation model at this time.

Optionally, the method further includes:

adjusting a planned water injection rate for at least one water injection well within the first field development block over the first time period;

and inputting the adjusted planned water injection quantity into the water injection well and oil production well relation model obtained by any one of the water injection well and oil production well relation model obtaining methods, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model at this time.

Optionally, the method further includes:

determining the yield of the relation model of the water injection well and the oil production well, which meets the preset conditions, in the output yield;

and outputting the planned water injection quantity which is input into the relation model of the water injection well and the oil production well and corresponds to the determined yield.

Optionally, inputting the obtained planned water injection amount into the water injection well and oil production well relation model, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model this time, includes:

and inputting the obtained planned water injection amount into a relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in a first time period determined and output by the relation model of the water injection well and the oil production well according to the obtained influence weight and the planned water injection amount.

A method for determining the water injection amount of a water injection well comprises the following steps:

obtaining a projected production rate for at least one production well within a first field development block over a first time period;

and inputting each obtained planned yield into the water injection well and oil production well relation model obtained by any one of the water injection well and oil production well relation model obtaining methods, and obtaining the water injection quantity of at least one water injection well in the first oil and gas field development area block within the first time period output by the water injection well and oil production well relation model.

An apparatus for obtaining a model of a relationship between a water injection well and a production well, comprising: a parameter obtaining unit and a learning unit,

the parameter obtaining unit is used for obtaining the working parameters of each water injection well in a first oil and gas field development block in a historical time period and the production position of each water injection well, obtaining the working parameters of each oil production well in the first oil and gas field development block in the historical time period and the production position of each oil production well, wherein the working parameters of each water injection well at least comprise: the water injection quantity, the working parameters of each oil production well at least comprise: yield;

the learning unit is used for taking each working parameter as training data, taking the production position as the same constraint condition, and performing machine learning on the working parameters of the water injection well and the oil production well at the same production position in the training data to obtain a relation model of the water injection well and the oil production well of the first oil and gas field development block, wherein the input parameters of the relation model of the water injection well and the oil production well comprise: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well comprise the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the water injection well and oil production well relation model comprise the yield, the output parameters of the water injection well and oil production well relation model comprise: the water injection amount.

A production well production determination apparatus comprising: a first water injection amount obtaining unit and a first yield obtaining unit,

the first water injection quantity obtaining unit is used for obtaining the planned water injection quantity of at least one water injection well in a first oil and gas field development block in a first time period;

and the first yield obtaining unit is used for inputting each obtained planned water injection amount into the water injection well and oil production well relation model obtained by the water injection well and oil production well relation model obtaining device and obtaining the yield of at least one oil production well in the first oil and gas field development block within a first time period output by the water injection well and oil production well relation model at this time.

A water injection well injection rate determination apparatus comprising: a second yield obtaining unit and a second water injection amount obtaining unit,

the second yield obtaining unit is used for obtaining the planned yield of at least one oil production well in the first oil and gas field development block in the first time period;

and the second water injection quantity obtaining unit is used for inputting each obtained planned yield into the water injection well and oil production well relation model obtained by the water injection well and oil production well relation model obtaining device and obtaining the water injection quantity of at least one water injection well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model.

A storage medium including a stored program, wherein the program is executed to control a device in which the storage medium is located to execute the method for obtaining the relation model between the water injection well and the production well, or the program is executed to control the device in which the storage medium is located to execute the method for determining the production well production rate, or the program is executed to control the device in which the storage medium is located to execute the method for determining the water injection well water injection rate.

A processor for executing a program, wherein the program is operable to execute the above-mentioned method for obtaining a relation model between a water injection well and a production well, or the program is operable to execute the above-mentioned method for determining a production rate of a production well, or the program is operable to execute the above-mentioned method for determining a water injection amount of a water injection well.

By means of the technical scheme, the method for obtaining the relation model of the water injection well and the oil production well and the method for determining the yield and the water injection quantity can obtain the working parameters and the production position of each water injection well and the working parameters and the production position of each oil production well in the first oil and gas field development block in the historical time period, the working parameters are used as training data, the production positions are the same and used as constraint conditions, machine learning is carried out on the working parameters of the water injection well and the oil production well at the same production position in the training data, and the relation model of the water injection well and the oil production well in the first oil and gas field development block is obtained. The embodiment of the invention establishes the relation model of the water injection well and the oil production well through machine learning of the working parameters in the historical time period, and the model reflects the relation between the working parameters of each water injection well and the working parameters of each oil production well, so that the method can directly use the model to determine the yield of the oil production well or the water injection amount of the water injection well, and is simple and convenient. When the working parameters of the water injection well or the oil production well change, the invention can carry out machine learning in time according to new parameters so as to improve the relation model of the water injection well and the oil production well, and the invention realizes the high-frequency monitoring of the relation of the water injection well and the oil production well. The relation model of the water injection well and the oil production well can change along with the change of the working parameters of the water injection well and the oil production well in time, so that the invention can obtain more accurate yield of the oil production well according to the relation model of the water injection well and the oil production well.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart of a method for obtaining a relational model between a water injection well and a production well according to an embodiment of the invention;

FIG. 2 is a flow chart illustrating a method for producing well production determination provided by an embodiment of the present invention;

FIG. 3 is a flow chart of another method for producing well production determination provided by embodiments of the present invention;

FIG. 4 is a flow chart of another method for producing well production determination provided by embodiments of the present invention;

FIG. 5 is a flow chart of a method for determining water injection rate of a water injection well according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram illustrating a device for obtaining a relation model of a water injection well and a production well according to an embodiment of the present invention;

FIG. 7 is a schematic diagram showing the structure of a production well production rate determining apparatus according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of another production well production rate determining apparatus according to an embodiment of the present invention;

FIG. 9 is a schematic diagram showing the structure of another production well productivity determining apparatus according to the embodiment of the present invention;

fig. 10 is a schematic structural diagram illustrating a water injection amount determination device for a water injection well according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As shown in fig. 1, a method for obtaining a relation model between a water injection well and a production well according to an embodiment of the present invention may include:

s100, obtaining working parameters of each water injection well in a first oil and gas field development block in a historical time period and a production position where each water injection well is located, and obtaining working parameters of each oil production well in the first oil and gas field development block in the historical time period and a production position where each oil production well is located, wherein the working parameters of each water injection well at least comprise: the water injection quantity, the working parameters of each oil production well at least comprise: yield;

the oil and gas field development block is the minimum geological unit for oil and gas field development, and it can be understood that geological parameters of different oil and gas field development blocks can be the same or different. The invention can respectively construct a relation model of the water injection well and the oil production well aiming at each oil-gas field development block.

The length of the historical time period and the time interval of the historical time period may be set according to actual needs, and the present invention is not limited herein. Optionally, the present invention may use the time from the oil production start time to the current time of the first oil and gas field development block as the historical time period, so that the present invention puts all the working parameters into the training data, which may improve the richness of the training data, and further improve the accuracy of the relation model between the water injection well and the oil production well.

Wherein, besides the water injection amount, the working parameters of the water injection well can further comprise: at least one of production time, oil pressure, and casing pressure. And/or, in addition to production, the operating parameters of the production well may include: at least one of production time, water content, oil pressure, casing pressure and working fluid level height.

Optionally, the yield may include: fluid production and/or oil production.

It is understood that the production time may be a production time or a production cycle. When the production time is a production moment, the invention can collect the oil pressure, the sleeve pressure, the water content and the working fluid level height at the production moment. Specifically, the historical time period may include a plurality of the production times, and the time intervals between adjacent production times may be the same or different. Optionally, in the embodiment of the present invention, the water injection amount and the output within two adjacent production moments may be respectively determined as the water injection amount and the output corresponding to the later production moment of the two adjacent production moments. Therefore, the invention corresponds the collected working parameters with the production time, so that the relation of the working parameters corresponding to the production time can be learned and obtained, and further a relation model of the water injection well and the oil production well can be obtained.

When the production time is a production period, the water injection amount and the yield obtained by the method can be the water injection amount and the yield in the production period respectively. Specifically, at least one production cycle may be included in a historical period of time. The length of the production period may be one day, one week, one month, one quarter, etc., and preferably, one week. In a production period, the invention can collect the oil pressure, the sleeve pressure, the water content and the working fluid level height in the production period for a plurality of times at different moments, and determine the collected oil pressure, sleeve pressure, water content and working fluid level height as the oil pressure, sleeve pressure, water content and working fluid level height corresponding to the production period. Therefore, through the production period, the invention corresponds the working parameters, so that the relation of the working parameters corresponding to the production time can be learned and obtained, and further a relation model of the water injection well and the oil production well is obtained.

The oil pressure is the annular pressure of an oil pipe measured by a pressure gauge during production of the oil production well, and the casing pressure is the annular pressure between the oil pipe and the casing measured by the pressure gauge during production of the oil production well.

Wherein the liquid production amount is the yield of an oil-water mixture produced by the oil production well; the oil production is the yield of oil produced by the oil production well.

Wherein, the water content is the mass percentage of water in the oil-water mixture extracted by the oil extraction well.

The working fluid level height is the liquid level height between oil casing annuluses of the oil production well in the oil extraction process, and the working fluid level height reflects the stratum energy of the oil production well, namely the height of a liquid column with the pressure capable of supporting the height.

The inventor of the application finds that: the oil pressure/casing pressure of the water injection well has a certain influence relation with the working parameters of the oil production well, and the water injection quantity of the water injection well also has a certain influence relation with the water content, the oil pressure, the casing pressure and the working fluid level height of the oil production well, so that the invention can also put the various working parameters into training data. By enriching the types of the working parameters contained in the training data, the relation model of the water injection well and the oil production well obtained by machine learning of the invention is more in line with the actual situation, and the accuracy of the relation model of the water injection well and the oil production well can be effectively improved.

It is understood that a field is often made up of multiple reservoirs, where a reservoir is a rock formation having interconnected pores that allow for the storage and percolation of hydrocarbons therein. Oil field flooding development practitioners often label the horizons of each reservoir of an oil and gas field according to exploration data, for example: from top to bottom are respectively labeled: level 1, level 2, etc. The water injection well and the oil production well can only operate on one reservoir, and because different reservoirs are not connected, the water injection well and the oil production well which are positioned at the same production layer can be determined after the production layers of the water injection wells and the oil production wells are obtained, and then the relation model of the water injection wells and the oil production wells is obtained according to the working parameters.

S200, using each working parameter as training data, using the same production position as a constraint condition, and performing machine learning on the working parameters of the water injection well and the oil production well of the same production position in the training data to obtain a relation model of the water injection well and the oil production well of the first oil and gas field development block, wherein the input parameters of the relation model of the water injection well and the oil production well comprise: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well comprise the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the water injection well and oil production well relation model comprise the yield, the output parameters of the water injection well and oil production well relation model comprise: the water injection amount.

The training data in the embodiment of the present invention may only include: both the water injection rate and the production rate, and may also include a greater variety of operating parameters, such as: production time, water content, oil pressure, casing pressure, working fluid level height and the like. It can be understood that with the increase of the types of the working parameters in the training data, the method can obtain the relation model of the water injection well and the oil production well according to the relation among more working parameters, so that the accuracy of the obtained relation model of the water injection well and the oil production well is greatly improved.

By taking the same production position as a constraint condition for machine learning, the invention can only carry out machine learning on the influence relation of the working parameters of the water injection well and the oil production well at the same production position. Therefore, influence relations among working parameters of the water injection well and the oil production well at different production positions are eliminated, and the reduction of the accuracy of a relation model of the water injection well and the oil production well caused by learning of wrong influence relations is avoided.

The influence relationship of the working parameters of the water injection well and the oil production well is learned, so that the relation model of the water injection well and the oil production well can obtain the working parameters of the oil production well according to the working parameters of the water injection well and the working parameters of the oil production well. Namely: the input parameters of the water injection well and oil production well relation model can comprise: the output parameters of the model of relationship between the water injection well and the production well may include: production from at least one production well. Alternatively, the input parameters of the water injection well and oil production well relation model may include: the output parameters of the water injection well and production well relationship model may include: the water injection amount of at least one water injection well.

For ease of understanding, the training data used in the present invention is illustrated below by table 1:

TABLE 1

It is understood that the number corresponding to each water injection well in table 1 is the water injection amount and the number corresponding to each production well is the production. In practice, the technician may use the numbers shown in table 1 (e.g., water injection well 11) to number the water injection wells and the oil production wells to distinguish the different water injection wells and oil production wells. Of course, the technician may also use other ways to identify the injection well or the production well, and the invention is not limited herein.

Specifically, the training data provided in table 1 are the operating parameters of the water injection wells and the oil production wells in the first oil and gas field development block in n production cycles, and the production horizons of the water injection wells and the oil production wells in table 1 are the same.

In other embodiments of the present invention, the present invention may first process each obtained operating parameter, and then perform machine learning by using the processed data as training data. The processing performed by the present invention may include: filling the missing data value by using methods such as mean filling; invalid values in the culling data, and the like. The invalid data can be data obviously wrongly recorded or data unchanged for a long time according to the dimension level.

Specifically, the machine learning method used in the present invention may include: at least one of logistic regression, support vector machine, naive Bayes, decision trees, random forests and the like. In practical application, the embodiment of the invention can sequentially select one of the machine learning methods to perform machine learning on the training data so as to obtain the relation models of the water injection well and the oil production well corresponding to different machine learning methods. Then, the embodiment of the invention can carry out error detection on the relation model of each water injection well and each oil production well and takes the model with the minimum error as the relation model of the water injection well and the oil production well.

In practical application, after the relational model of the water injection well and the oil production well is obtained, the model can be subjected to accuracy inspection through inspection data, and when the accuracy of the relational model of the water injection well and the oil production well does not meet requirements, the model can be trained continuously until the accuracy of the model meets the requirements.

Specifically, the present invention may use a part of the operating parameters in the historical time period as training data, and use the remaining part of the operating parameters as inspection data.

Specifically, the method for performing accuracy inspection on the relation model between the water injection well and the oil production well in the embodiment of the invention may include:

inputting the working parameters of each water injection well in the inspection data into the relational model of the water injection well and the oil production well, and obtaining the working parameters of each oil production well output by the relational model of the water injection well and the oil production well;

calculating the error of the working parameters of each oil production well output by the relation model of the water injection well and the oil production well relative to the working parameters of each oil production well in the inspection data;

and when the error is larger than the preset error, adding new working parameters into the training data of the relation model of the water injection well and the oil production well, performing machine learning on the training data added with the new working parameters to obtain a new relation model of the water injection well and the oil production well, and then inspecting the new relation model of the water injection well and the oil production well through inspection data until the error is smaller than the preset error.

When the error of the working parameters of each oil production well output by the relational model of the water injection well and the oil production well relative to the working parameters of each oil production well in the inspection data is smaller than the preset error, the method can determine the inspection passing of the relational model of the water injection well and the oil production well, and can be used for obtaining the working parameters of the oil production well according to the working parameters of the water injection well.

Correspondingly, the invention can also input the working parameters of the oil production well in the inspection data into the relation model of the water injection well and the oil production well, and calculate the error of the working parameters of each water injection well output by the relation model of the water injection well and the oil production well relative to the working parameters of each water injection well in the inspection data, thereby carrying out the inspection.

Further, in the present invention, when calculating an error of the operating parameter of each production well outputted from the water injection well and production well relational model with respect to the operating parameter of each production well in the inspection data, it is possible to: calculating the error of the working parameters of the oil production well output by the relation model of the water injection well and the oil production well relative to the working parameters of the oil production well in the inspection data, thereby obtaining a plurality of errors; and then, carrying out operation (such as average operation) on the plurality of errors to obtain a comprehensive error, and comparing the comprehensive error with a preset error. Of course, the practical application is not limited to this one error determination method.

Because the reservoir oil-water relationship in the oilfield flooding development process is a real-time dynamic change process, the invention can timely obtain the working parameters generated in the recent historical time period and use the working parameters as training data to perform machine learning on the training data. Of course, when the geological parameters of the first oil and gas field development block are changed, the working parameters in the changed time period can be obtained and used as training data, and machine learning is carried out on the training data.

In other embodiments of the present invention, after performing machine learning on the working parameters of the water injection well and the oil production well at the same production level in the training data in step S200, the following may also be obtained: and the influence weight of the working parameters of the water injection wells at the same production layer position in the first oil-gas field development block on the working parameters of the oil production wells.

It will be appreciated that the above-mentioned impact weights may be determined from a relationship between changes in the operating parameters of each water injection well and changes in the operating parameters of each production well. Under the condition that the first water injection well, the second water injection well and the first oil production well are located at the same production position, when the first change amplitude of the working parameters of the first oil production well caused by the change of the working parameters of the first water injection well in the first amplitude is larger than the second change amplitude of the working parameters of the first oil production well caused by the change of the working parameters of the second water injection well in the first amplitude, the influence weight of the working parameters of the first water injection well on the working parameters of the first oil production well can be determined to be larger than the influence weight of the working parameters of the second water injection well on the working parameters of the first oil production well.

For example: the present invention performs machine learning on the training data shown in table 1, and determines the influence weight shown in table 2 from the relationship between the change in the operating parameter in each water injection well and the change in the operating parameter in each oil production well in table 1.

TABLE 2

Specifically, each figure in table 2 represents the influence weight of the operating parameter of the production well corresponding to the row in which the figure represents the influence weight on the operating parameter of the injection well corresponding to the column in which the figure represents the influence weight. The influence weight is a dimensionless parameter, and is selectable to any oil production well: the sum of the influence weights of the operating parameters of the water injection wells located at the same production level as the production well on the operating parameters of the production well can be 1.

The method for obtaining the relation model of the water injection well and the oil production well can obtain the working parameters and the production position of each water injection well and the working parameters and the production position of each oil production well in a first oil and gas field development block in a historical time period, uses the working parameters as training data, uses the same production position as a constraint condition, and performs machine learning on the working parameters of the water injection well and the oil production well at the same production position in the training data to obtain the relation model of the water injection well and the oil production well in the first oil and gas field development block. The embodiment of the invention establishes the relation model of the water injection well and the oil production well through machine learning of the working parameters in the historical time period, and the model reflects the relation between the working parameters of each water injection well and the working parameters of each oil production well, so the method can directly use the model to determine the yield of the oil production well, and is simple and convenient. When the working parameters of the water injection well or the oil production well change, the invention can carry out machine learning in time according to new parameters so as to improve the relation model of the water injection well and the oil production well, and the invention realizes the high-frequency monitoring of the relation of the water injection well and the oil production well. The relation model of the water injection well and the oil production well can change along with the change of the working parameters of the water injection well and the oil production well in time, so that the invention can obtain more accurate yield of the oil production well according to the relation model of the water injection well and the oil production well.

As shown in fig. 2, an embodiment of the present invention further provides a method for determining production well yield, which may include:

s001, obtaining planned water injection quantity of at least one water injection well in a first oil and gas field development block in a first time period;

it will be appreciated that the present invention can obtain the planned water injection for a water injection well when the water injection well to production well relationship model obtained by the method of the present invention illustrated in fig. 1 is used for production estimation. Because the oil pressure and the casing pressure of the water injection well frequently change along with the time and cannot be estimated (even if the estimation can be inaccurate), the invention can only obtain the planned water injection amount and input the planned water injection amount into the relation model of the water injection well and the oil production well.

The first time period may be a time period of the current time, such as the current day, or may be a time period in the future, such as the next day or the next month.

For example: for the water injection well-production well relationship model obtained by machine learning from the training data shown in table 1, the present invention can obtain the planned water injection amount for each water injection well as shown in table 3.

TABLE 3

And S002, inputting the obtained planned water injection quantity into the water injection well and oil production well relation model obtained by the water injection well and oil production well relation model obtaining method provided by the embodiment of the invention, and obtaining the yield of at least one oil production well in a first oil and gas field development block in a first time period output by the water injection well and oil production well relation model at this time.

In practical application, in step S002 of the present invention, other operating parameters of at least one oil production well in the first oil and gas field development block in the first time period of the output of the relationship model between the water injection well and the oil production well may also be obtained, such as: at least one of water content, oil pressure, casing pressure and working fluid level height.

It will be appreciated that since the water injection and production well relationship models have the same production horizon as constraints when machine learning is performed, the water injection and production well relationship models will determine the water injection and production wells that are at the same production horizon and determine the production of the production wells that are at the same production horizon as the water injection wells due to their projected water injection rates.

Step S002 may specifically include: and inputting the obtained planned water injection amount into a relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in a first time period determined and output by the relation model of the water injection well and the oil production well according to the planned water injection amount and the influence weight.

It can be understood that when the geological parameters of the first oil and gas field development block change (such as reservoir change caused by earthquake) or the development stage changes (such as entering the high water content oil production period from the medium water content oil production period), the invention can control the relation model of the water injection well and the oil production well to perform machine learning on the changed working parameters of the water injection well and the oil production well in the first oil and gas field development block, thereby improving the relation model of the water injection well and the oil production well, so that the relation model of the water injection well and the oil production well changes along with the change of the first oil and gas field development block. Therefore, the yield of the oil production well output by the relation model of the water injection well and the oil production well is more accurate.

As shown in fig. 3, another method for determining the production well yield according to the embodiment of the present invention may further include:

s003, adjusting the planned water injection quantity of at least one water injection well in the first oil and gas field development block in the first time period;

the planned water injection amount of each water injection well in step S003 may be adjusted in various ways, for example, the planned water injection amount of each water injection well is sequentially adjusted according to a preset adjustment sequence and an adjustment interval to obtain various different planned water injection amounts; the following steps are repeated: and randomly adjusting the planned water injection amount of each water injection well in a random adjustment mode.

And S004, inputting the adjusted planned water injection quantity into the water injection well and oil production well relation model obtained by the water injection well and oil production well relation model obtaining method provided by the embodiment of the invention, and obtaining the yield of at least one oil production well in a first oil and gas field development block in a first time period output by the water injection well and oil production well relation model at this time.

By adjusting the planned water injection amount, the invention can obtain the output of the oil production well corresponding to different planned water injection amounts, and can help oil field workers to select the required water injection amount according to the output of the oil production well.

As shown in fig. 4, another method for determining the production well yield according to the embodiment of the present invention may further include:

s005, determining the yield of the relation model of the water injection well and the oil production well, which meets the preset conditions, in the output yield;

wherein, the preset condition may be: maximum production or lowest cost per unit production, etc.

And S006, inputting the determined yield into the planned water injection amount in the relation model of the water injection well and the oil production well correspondingly, and outputting the planned water injection amount.

According to the embodiment of the invention, the planned water injection amount corresponding to the output meeting the preset condition can be automatically selected from the plurality of planned water injection amounts through the steps S005 and S006, manual selection by a user is not needed, and the method is simple and convenient.

For ease of understanding, the method shown in FIG. 4 is illustrated below:

the method comprises the steps of obtaining planned water injection quantity of each water injection well provided by a user, inputting the planned water injection quantity into a relation model of the water injection well and a production well, obtaining the output of the production well output by the relation model of the water injection well and the production well, and determining the sum of the output of each production well as the total output of the relation model of the water injection well and the production well;

the method comprises the steps of automatically adjusting planned water injection quantity provided by a user for multiple times, inputting the adjusted planned water injection quantity into a relation model of a water injection well and a production well, obtaining the output of the production well output by the relation model of the water injection well and the production well after the planned water injection quantity is input every time, and determining the sum of the output of each output production well as the total output of the relation model of the water injection well and the production well every time;

the invention compares all the total output, determines the maximum total output and outputs the planned water injection amount corresponding to the maximum total output.

It can be understood that the planned water injection output by the embodiment of the invention is the water injection when the total output is maximum, and a user can control the working parameters of each water injection well through the water injection output by the embodiment of the invention, so that the yield of the oil production well can be increased.

Of course, in other embodiments of the present invention, the planned production may also be input into a water injection well and production well relationship model to obtain a water injection amount corresponding to the planned production.

Corresponding to the method shown in fig. 2, as shown in fig. 5, an embodiment of the present invention further provides a method for determining a water injection amount of a water injection well, which may include:

s010, obtaining the planned yield of at least one oil production well in a first oil and gas field development block in a first time period;

and S011, inputting each obtained planned yield into the water injection well and oil production well relation model obtained by the water injection well and oil production well relation model obtaining method provided by the embodiment of the invention, and obtaining the water injection quantity of at least one water injection well in a first oil and gas field development block in a first time period output by the water injection well and oil production well relation model.

The method shown in fig. 5 is different from the method shown in fig. 2 in that: the method shown in fig. 5 inputs the planned production rate into the water injection well and oil production well relational model, and obtains the water injection rate output by the water injection well and oil production well relational model. And the method shown in fig. 2 inputs the planned water injection amount into the relation model of the water injection well and the oil production well, and obtains the output of the relation model of the water injection well and the oil production well.

The method shown in fig. 5 can enable a user to obtain the water injection amount of each water injection well required for realizing the planned yield, and is convenient for the user to control the working parameters of each water injection well according to the water injection amount output by the relation model of the water injection well and the oil production well, so that the planned yield is realized.

Corresponding to the method shown in fig. 1, as shown in fig. 6, an embodiment of the present invention further provides an apparatus for obtaining a relation model between a water injection well and a production well, which may include: a parameter obtaining unit 100 and a learning unit 200,

the parameter obtaining unit 100 is configured to obtain working parameters of each water injection well and a production position where each water injection well is located in a first oil and gas field development block in a historical time period, and obtain working parameters of each oil production well and a production position where each oil production well is located in the first oil and gas field development block in the historical time period, where the working parameters of each water injection well at least include: the water injection quantity, the working parameters of each oil production well at least comprise: yield;

Optionally, the yield may include: fluid production and/or oil production.

The learning unit 200 is configured to use each of the working parameters as training data, use the same production level as a constraint condition, perform machine learning on the working parameters of the water injection well and the oil production well at the same production level in the training data, and obtain a relationship model between the water injection well and the oil production well in the first oil and gas field development block, where the input parameters of the relationship model between the water injection well and the oil production well include: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well comprise the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the water injection well and oil production well relation model comprise the yield, the output parameters of the water injection well and oil production well relation model comprise: the water injection amount.

In other embodiments of the present invention, the learning unit 200 may further obtain, after performing machine learning on the working parameters of the water injection well and the oil production well at the same production level in the training data: and the influence weight of the working parameters of the water injection wells at the same production layer position in the first oil-gas field development block on the working parameters of the oil production wells.

The device for obtaining the relation model of the water injection well and the oil production well can obtain the working parameters and the production position of each water injection well and the working parameters and the production position of each oil production well in a first oil and gas field development block in a historical time period, uses the working parameters as training data, uses the same production position as a constraint condition, and performs machine learning on the working parameters of the water injection well and the oil production well at the same production position in the training data to obtain the relation model of the water injection well and the oil production well in the first oil and gas field development block. The embodiment of the invention establishes the relation model of the water injection well and the oil production well through machine learning of the working parameters in the historical time period, and the model reflects the relation between the working parameters of each water injection well and the working parameters of each oil production well, so the method can directly use the model to determine the yield of the oil production well, and is simple and convenient. When the working parameters of the water injection well or the oil production well change, the invention can carry out machine learning in time according to new parameters so as to improve the relation model of the water injection well and the oil production well, and the invention realizes the high-frequency monitoring of the relation of the water injection well and the oil production well. The relation model of the water injection well and the oil production well can change along with the change of the working parameters of the water injection well and the oil production well in time, so that the invention can obtain more accurate yield of the oil production well according to the relation model of the water injection well and the oil production well.

Corresponding to the method shown in fig. 2, as shown in fig. 7, an embodiment of the present invention further provides a production well yield determination apparatus, which may include: a first water injection amount obtaining unit 001 and a first yield obtaining unit 002,

the first water injection amount obtaining unit 001 is used for obtaining the planned water injection amount of at least one water injection well in a first oil and gas field development block in a first time period;

The first yield obtaining unit 002 is configured to input each obtained planned water injection amount into the water injection well and oil production well relational model obtained by the water injection well and oil production well relational model obtaining device provided in the embodiment of the present invention, and obtain the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relational model this time.

In practical applications, the first yield obtaining unit 002 may further obtain other operating parameters of at least one oil production well in the first oil and gas field development block in the first time period of the output of the relationship model between the water injection well and the oil production well, such as: at least one of water content, oil pressure, casing pressure and working fluid level height.

The first yield obtaining unit 002 can be specifically used for: and inputting the obtained planned water injection amount into a relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in a first time period determined and output by the relation model of the water injection well and the oil production well according to the planned water injection amount and the influence weight.

Corresponding to the method shown in fig. 3, as shown in fig. 8, another production well yield determination apparatus provided in the embodiment of the present invention may further include: a water injection amount adjusting unit 003 and a water injection amount input unit 004,

a water injection amount adjusting unit 003 for adjusting a planned water injection amount of at least one water injection well in the first field development block in the first time period;

the water injection amount adjusting unit 003 may adjust the planned water injection amount of each water injection well in a plurality of ways, for example, sequentially adjusting the planned water injection amount of each water injection well according to a preset adjustment sequence and adjustment intervals to obtain a plurality of different planned water injection amounts; the following steps are repeated: and randomly adjusting the planned water injection amount of each water injection well in a random adjustment mode.

The water injection amount input unit 004 is configured to input the adjusted planned water injection amount into the water injection well and oil production well relational model obtained by the water injection well and oil production well relational model obtaining device provided in the embodiment of the present invention, and obtain the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relational model this time.

Corresponding to the method shown in fig. 4, as shown in fig. 9, another production well yield determination apparatus provided in the embodiment of the present invention may further include: a yield judging unit 005 and a water injection amount output unit 006,

the yield judgment unit 005 is used for determining the yield of the water injection well and oil production well relation model meeting the preset conditions in the output yield;

And a water injection amount output unit 006 for outputting the planned water injection amount inputted into the water injection well and oil production well relation model corresponding to the determined yield.

According to the embodiment of the invention, the yield judgment unit 005 and the water injection output unit 006 can automatically select the planned water injection amount corresponding to the yield meeting the preset conditions from the multiple planned water injection amounts, so that the selection by a user is not needed, and the method is simple and convenient.

Corresponding to the method shown in fig. 6, as shown in fig. 10, an embodiment of the present invention further provides a device for determining a water injection amount of a water injection well, which may include: a second yield obtaining unit 010 and a second water injection amount obtaining unit 011,

the second production obtaining unit 010 is configured to obtain a planned production of at least one production well in the first field development block in a first time period;

the second water injection rate obtaining unit 011 is configured to input each obtained planned yield into the water injection well and oil production well relational model obtained by the water injection well and oil production well relational model obtaining device according to the embodiment of the present invention, and obtain the water injection rate of at least one water injection well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relational model.

The device shown in fig. 10 can enable a user to obtain the water injection amount of each water injection well required for realizing the planned yield, and is convenient for the user to control the working parameters of each water injection well according to the water injection amount output by the relation model of the water injection well and the oil production well, so that the planned yield is realized.

The water injection well and oil production well relation model obtaining device, the oil production well yield determining device and the water injection well water injection amount determining device all comprise a processor and a memory, the parameter obtaining unit, the learning unit, the first water injection amount obtaining unit, the first yield obtaining unit, the second water injection amount obtaining unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, a relation model of the water injection well and the oil production well is generated by adjusting kernel parameters, and the relation between the water injection well and the oil production well is monitored.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

An embodiment of the present invention provides a storage medium having stored thereon a program that, when executed by a processor, implements at least one of the water injection well and production well relationship model obtaining method, production well yield determination method, and water injection well water injection amount determination method.

The embodiment of the invention provides a processor for operating a program, wherein the program executes at least one of a water injection well and oil production well relation model obtaining method, an oil production well yield determining method and a water injection well water injection quantity determining method during operation.

The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:

A production well production determination method comprising:

and inputting the obtained planned water injection quantity into the relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the relation model of the water injection well and the oil production well.

Optionally, the method further includes:

and inputting the adjusted planned water injection amount into the relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the relation model of the water injection well and the oil production well.

Optionally, the method further includes:

Optionally, inputting the obtained planned water injection amount into the water injection well and oil production well relational model, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relational model this time, includes:

and inputting the obtained planned water injection amount into the relation model of the water injection well and the oil production well, and obtaining the yield of at least one oil production well in the first oil and gas field development block in a first time period determined and output by the relation model of the water injection well and the oil production well according to the influence weight and the planned water injection amount.

and inputting the obtained planned output into the relation model of the water injection well and the oil production well, and obtaining the water injection quantity of at least one water injection well in the first oil and gas field development block in the first time period output by the relation model of the water injection well and the oil production well.

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:

A production well production determination method comprising:

Optionally, the method further includes:

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for obtaining a relation model of a water injection well and a production well is characterized by comprising the following steps:

using part of the working parameters in the historical data as training data, using the same production position as a constraint condition, and performing machine learning on the working parameters of the water injection well and the oil production well of the same production position in the training data to obtain a relation model of the water injection well and the oil production well of the first oil and gas field development block, wherein the input parameters of the relation model of the water injection well and the oil production well comprise: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well are only the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the relation model of the water injection well and the oil production well are only the yield, the output parameters of the relation model of the water injection well and the oil production well comprise: the amount of water injected;

the rest of working parameters except the working parameters serving as the training data in the historical data are used as inspection data, and the working parameters of each water injection well in the inspection data are input into a relation model of the water injection well and the oil production well, so that the working parameters of each oil production well output by the relation model of the water injection well and the oil production well are obtained;

when the error is larger than the preset error, adding new working parameters into the training data of the relation model of the water injection well and the oil production well, and performing machine learning on the training data added with the new working parameters to obtain a new relation model of the water injection well and the oil production well, and then inspecting the new relation model of the water injection well and the oil production well through inspection data until the error is smaller than the preset error;

and when the error of the working parameters of each oil production well output by the relation model of the water injection well and the oil production well relative to the working parameters of each oil production well in the inspection data is smaller than the preset error, determining that the inspection of the relation model of the water injection well and the oil production well passes, and obtaining the final relation model of the water injection well and the oil production well.

2. The method of claim 1, wherein the operational parameters of the water injection well further comprise: at least one of production time, oil pressure, and casing pressure; and/or the working parameters of the oil production well further comprise: at least one of production time, water content, oil pressure, casing pressure and working fluid level height.

3. The method of claim 1 or 2, wherein the machine learning of the operating parameters of the water injection wells and the oil production wells of the same production horizon in the training data further yields: and the influence weight of the working parameters of the water injection wells at the same production layer position in the first oil-gas field development block on the working parameters of the oil production wells.

4. A method for determining production well production, comprising:

inputting each obtained planned water injection amount into the water injection well and oil production well relation model obtained in any one of claims 1 to 3, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model this time.

5. The method of claim 4, further comprising:

inputting the adjusted planned water injection amount into the relation model of the water injection well and the oil production well obtained in any one of claims 1 to 3, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the relation model of the water injection well and the oil production well.

6. The method of claim 5, further comprising:

7. The method according to any one of claims 4 to 6, wherein inputting the obtained planned water injection quantities into the water injection well and production well relational model obtained in claim 3, obtaining production of at least one production well in the first field development block during the first time period of the output of the current water injection well and production well relational model, comprises:

inputting each obtained planned water injection amount into the relation model of the water injection well and the oil production well obtained in the claim 3, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period determined and output by the relation model of the water injection well and the oil production well according to the influence weight obtained in the claim 3 and each planned water injection amount.

8. A method for determining the water injection amount of a water injection well is characterized by comprising the following steps:

inputting each planned production obtained into the water injection well and production well relational model obtained according to any one of claims 1 to 3, and obtaining the water injection amount of at least one water injection well in the first field development block within the first time period output by the water injection well and production well relational model.

9. A device for obtaining a relation model of a water injection well and a production well is characterized by comprising: a parameter obtaining unit and a learning unit,

the learning unit is used for using part of the working parameters in the historical data as training data, using the same production position as a constraint condition, performing machine learning on the working parameters of the water injection well and the oil production well of the same production position in the training data, and obtaining a relation model of the water injection well and the oil production well of the first oil and gas field development block, wherein the input parameters of the relation model of the water injection well and the oil production well comprise: the water injection amount or the yield; when the input parameters of the relation model of the water injection well and the oil production well are only the water injection quantity, the output parameters of the relation model of the water injection well and the oil production well comprise: the yield; when the input parameters of the relation model of the water injection well and the oil production well are only the yield, the output parameters of the relation model of the water injection well and the oil production well comprise: the amount of water injected;

the learning unit is further configured to: the rest of working parameters except the working parameters serving as the training data in the historical data are used as inspection data, and the working parameters of each water injection well in the inspection data are input into a relation model of the water injection well and the oil production well, so that the working parameters of each oil production well output by the relation model of the water injection well and the oil production well are obtained;

10. A production well production rate determining apparatus, comprising: a first water injection amount obtaining unit and a first yield obtaining unit,

the first yield obtaining unit is used for inputting each obtained planned water injection amount into the water injection well and oil production well relation model obtained according to claim 9, and obtaining the yield of at least one oil production well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model this time.

11. A water injection well injection rate determining apparatus, comprising: a second yield obtaining unit and a second water injection amount obtaining unit,

the second water injection amount obtaining unit is configured to input each obtained planned yield into the water injection well and oil production well relation model obtained in claim 9, and obtain the water injection amount of at least one water injection well in the first oil and gas field development block in the first time period output by the water injection well and oil production well relation model.

12. A storage medium comprising a stored program, wherein the program is executed to control a device in which the storage medium is located to execute the water injection well-to-oil well relation model obtaining method according to any one of claims 1 to 3, or the program is executed to control the device in which the storage medium is located to execute the oil well production determining method according to any one of claims 4 to 7, or the program is executed to control the device in which the storage medium is located to execute the water injection well water injection amount determining method according to claim 8.

13. A processor for running a program, wherein the program is run to perform the water injection well and production well relationship model obtaining method of any one of claims 1 to 3, or the program is run to perform the production well production determination method of any one of claims 4 to 7, or the program is run to perform the water injection well injection volume determination method of claim 8.