CN115841181A

CN115841181A - Residual oil distribution prediction method, device, equipment and storage medium

Info

Publication number: CN115841181A
Application number: CN202211539957.4A
Authority: CN
Inventors: 王铁成; 董杰; 陈蕾; 金筱涵; 邱锋; 吴迪; 石玮仑; 赵艳江; 孙永光
Original assignee: Kunlun Digital Technology Co ltd; China National Petroleum Corp
Current assignee: Kunlun Digital Technology Co ltd; China National Petroleum Corp
Priority date: 2022-12-02
Filing date: 2022-12-02
Publication date: 2023-03-24
Anticipated expiration: 2042-12-02
Also published as: CN115841181B

Abstract

The application discloses a residual oil distribution prediction method, a residual oil distribution prediction device, residual oil distribution prediction equipment and a storage medium, and belongs to the technical field of oilfield development. The method comprises the steps of adjusting at least one oil reservoir parameter through a parameter adjusting interface to obtain a target oil reservoir numerical model; determining the comprehensive water content of the sample block along with the change of the time interval based on the target oil reservoir numerical model; acquiring oil production data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold; performing model training based on oil production data and water saturation of the sample block changing along with time intervals to obtain a residual oil distribution prediction model; and determining the residual oil distribution of the target block based on the residual oil distribution prediction model. Because the residual oil distribution prediction model is obtained by iterative training, the residual oil distribution can be accurately predicted by the residual oil distribution prediction model, so that the accuracy of residual oil distribution prediction is improved.

Description

Residual oil distribution prediction method, device, equipment and storage medium

Technical Field

The application relates to the technical field of oilfield development, in particular to a method, a device, equipment and a storage medium for predicting residual oil distribution.

Background

The distribution of the residual oil is the core problem of oil field development research, and the development direction of the oil field can be determined only under the condition of determining the distribution of the residual oil, so that how to adjust drilling, production measures and the like in the later oil field development process is determined. Therefore, how to predict the remaining oil distribution becomes a focus of attention.

In the related art, the remaining oil distribution of a block is simulated mainly by fitting data such as total oil reserve, produced oil amount, water yield and the like in the block. The accuracy of data fitting can directly influence the accuracy of the residual oil distribution, and when the accuracy of data fitting is low, the accuracy of residual oil distribution prediction is also low.

Disclosure of Invention

The embodiment of the application provides a method, a device, equipment and a storage medium for predicting residual oil distribution, which can improve the accuracy of residual oil distribution prediction. The technical scheme is as follows:

in one aspect, a method for predicting remaining oil distribution is provided, the method comprising:

displaying a model determination interface, the model determination interface comprising a plurality of model icons;

responding to the triggering operation of the target model icon, and displaying a parameter adjusting interface; the parameter adjustment interface comprises a plurality of reservoir parameters corresponding to the initial reservoir numerical model;

adjusting at least one reservoir parameter based on the parameter adjustment interface to obtain a target reservoir numerical model;

determining the comprehensive water content of the sample block along with the change of the time interval based on the target oil reservoir numerical model;

acquiring oil production data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold;

performing model training based on the oil extraction data and the water saturation of the sample block changing along with the time interval to obtain a residual oil distribution prediction model;

and determining the residual oil distribution of the target block based on the residual oil distribution prediction model.

In one possible implementation, the determining the integrated water cut of the sample block over the time interval based on the target reservoir numerical model includes:

predicting the comprehensive water content of the sample block after a first time interval based on a plurality of oil reservoir parameters corresponding to the target oil reservoir numerical model;

if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil deposit parameters corresponding to the target oil deposit numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

In another possible implementation manner, the determining the residual oil distribution of the target block based on the residual oil distribution prediction model includes:

displaying a first data acquisition interface;

acquiring oil production data of the target block based on the first data acquisition interface;

and inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block.

In another possible implementation, the remaining oil distribution of the target block includes an oil saturation of the target block;

inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block, wherein the step of obtaining the residual oil distribution of the target block comprises the following steps:

inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the water saturation of the target block;

and taking the difference between the second preset threshold and the water saturation as the oil saturation of the target block.

In another possible implementation manner, the parameter adjustment interface includes: a plurality of parameter adjustment options;

and adjusting at least one reservoir parameter based on the parameter adjustment interface to obtain a target reservoir numerical model, comprising:

determining an adjustment range and an adjustment step length of the at least one reservoir parameter based on the plurality of parameter adjustment options;

and adjusting the at least one oil reservoir parameter according to the adjustment range and the adjustment step length to obtain a plurality of target oil reservoir numerical models.

In another possible implementation manner, the performing model training based on the oil recovery data and the water saturation of the sample block changing with the time interval to obtain a residual oil distribution prediction model includes:

and taking the oil recovery data of each time interval of the sample block as a first training sample, taking the water saturation of each time interval of the sample block as a first training target, and performing model training based on the first training sample and the first training target to obtain the residual oil distribution prediction model.

determining a difference value between a second preset threshold value and the water saturation of the sample block at each time interval to obtain the oil saturation of the sample block at each time interval;

and taking the oil recovery data of each time interval of the sample block as a second training sample, taking the oil saturation of each time interval of the sample block as a second training target, and performing model training based on the second training sample and the second training target to obtain the residual oil distribution prediction model.

In another possible implementation manner, the method further includes:

displaying a second data acquisition interface;

acquiring historical oil production data and historical water saturation of the test block based on the second data acquisition interface;

inputting the historical oil recovery data into the residual oil distribution prediction model to obtain the test water saturation of the test block;

determining a difference between the test water saturation and the historical water saturation;

and if the difference value is within a preset range, determining that the residual oil distribution prediction model passes the test.

In another aspect, there is provided a residual oil distribution prediction apparatus, the apparatus including:

a first display module to display a model determination interface, the model determination interface including a plurality of model icons;

the second display module is used for responding to the trigger operation of the target model icon and displaying a parameter adjusting interface; the parameter adjustment interface comprises a plurality of reservoir parameters corresponding to the initial reservoir numerical model;

the adjusting module is used for adjusting at least one oil reservoir parameter based on the parameter adjusting interface to obtain a target oil reservoir numerical model;

the first determination module is used for determining the comprehensive water content of the sample block along with the change of the time interval based on the target oil reservoir numerical model;

the first acquisition module is used for acquiring oil production data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold value;

the training module is used for carrying out model training based on the oil production data and the water saturation of the sample block changing along with the time interval to obtain a residual oil distribution prediction model;

and the second determination module is used for determining the residual oil distribution of the target block based on the residual oil distribution prediction model.

In a possible implementation manner, the first determining module is configured to predict the comprehensive water content of the sample block after a first time interval based on a plurality of reservoir parameters corresponding to the target reservoir numerical model; if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil reservoir parameters corresponding to the target oil reservoir numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

In another possible implementation manner, the second determining module is configured to display a first data obtaining interface; acquiring oil production data of the target block based on the first data acquisition interface; and inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block.

the second determination module is used for inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the water saturation of the target block; and taking the difference between the second preset threshold and the water saturation as the oil saturation of the target block.

the adjusting module is used for determining an adjusting range and an adjusting step length of the at least one reservoir parameter based on the plurality of parameter adjusting options; and adjusting the at least one reservoir parameter according to the adjustment range and the adjustment step length to obtain a plurality of target reservoir numerical models.

In another possible implementation manner, the training module is configured to use the oil recovery data of the sample block at each time interval as a first training sample, use the water saturation of the sample block at each time interval as a first training target, and perform model training based on the first training sample and the first training target to obtain the residual oil distribution prediction model.

In another possible implementation manner, the training module is configured to determine a difference between a second preset threshold and the water saturation of the sample block at each time interval, so as to obtain the oil saturation of the sample block at each time interval; and taking the oil production data of each time interval of the sample block as a second training sample, taking the oil saturation of each time interval of the sample block as a second training target, and performing model training based on the second training sample and the second training target to obtain the residual oil distribution prediction model.

In another possible implementation manner, the apparatus further includes:

the third display module is used for displaying the second data acquisition interface;

the second acquisition module is used for acquiring historical oil production data and historical water saturation of the test block based on the second data acquisition interface;

the third determination module is used for inputting the historical oil recovery data into the residual oil distribution prediction model to obtain the test water saturation of the test block;

a fourth determination module for determining a difference between the test water saturation and the historical water saturation;

and the fifth determining module is used for determining that the residual oil distribution prediction model passes the test if the difference value is within a preset range.

In another aspect, an electronic device is provided, which includes a processor and a memory, where at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement any of the above-mentioned residual oil distribution prediction methods.

In another aspect, a computer readable storage medium is provided, in which at least one program code is stored, the at least one program code being loaded and executed by a processor to implement any of the above-mentioned residual oil distribution prediction methods.

In another aspect, a computer program product is provided, in which at least one program code is stored, the at least one program code being loaded and executed by a processor to implement the residual oil distribution prediction method of any one of the above.

The embodiment of the application provides a residual oil distribution prediction method, which comprises the steps of determining the comprehensive water content of a sample block through a numerical reservoir model, determining oil production data and water saturation of the sample block along with time interval change according to the comprehensive water content of the sample block, then carrying out model training to obtain a residual oil distribution prediction model, and predicting the residual oil distribution of a target block through the residual oil distribution prediction model. Because the residual oil distribution prediction model is obtained by iterative training, the residual oil distribution can be accurately predicted by the residual oil distribution prediction model, so that the accuracy of residual oil distribution prediction is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

FIG. 1 is a schematic diagram of an implementation environment of a method for predicting remaining oil distribution according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a residual oil distribution prediction model obtained by model training according to an embodiment of the present disclosure;

fig. 3 is an architecture diagram of a cloud platform provided in an embodiment of the present application;

fig. 4 is a schematic diagram of a residual oil distribution prediction model obtained through model training based on a cloud platform according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a model training through a long-term and short-term neural network to obtain a residual oil distribution prediction model according to an embodiment of the present application;

FIG. 6 is a flow chart of a method for predicting remaining oil distribution according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of a remaining oil distribution prediction apparatus according to an embodiment of the present application;

fig. 8 is a block diagram of a terminal according to an embodiment of the present disclosure;

fig. 9 is a block diagram of a server according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions and advantages of the present application more clear, the following describes the embodiments of the present application in further detail.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

It should be noted that information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals referred to in this application are authorized by the user or sufficiently authorized by various parties, and the collection, use, and processing of the relevant data is required to comply with relevant laws and regulations and standards in relevant countries and regions. For example, the oil recovery data, water saturation, oil saturation, and reservoir parameters referred to in this application are obtained under full authority.

Fig. 1 is a schematic diagram of an implementation environment of a remaining oil distribution prediction method according to an embodiment of the present application. Referring to fig. 1, the implementation environment includes: an electronic device may be provided as the terminal 101, or may be provided as the terminal 101 and the server 102. If the electronic devices are provided as the terminal 101 and the server 102, the terminal 101 and the server 102 may be connected via a wireless or wired network. In the embodiment of the present application, only electronic devices provided as the terminal 101 and the server 102 are described as an example.

If the electronic device is provided as the terminal 101 and the server 102, the server 102 performs model training to obtain a residual oil distribution prediction model, and then determines the residual oil distribution of the target block based on the residual oil distribution prediction model. The server 102 transmits the remaining oil distribution of the target block to the terminal 101, and the terminal 101 displays the remaining oil distribution of the target block.

The terminal 101 is at least one of a mobile phone, a tablet Computer, a Personal Computer (PC) device, an intelligent voice interaction device, and a vehicle-mounted terminal. The server 102 may be at least one of a server, a server cluster composed of a plurality of servers, a cloud server, a cloud computing platform, and a virtualization center.

Fig. 2 is a flowchart of a residual oil distribution prediction model obtained through model training according to an embodiment of the present application, executed by an electronic device, and referring to fig. 2, the method includes:

step 201: the electronic device displays a model determination interface.

In this step, the electronic device may display the model determination interface through the cloud platform. The electronic device may log in the cloud platform by logging in the target application, as in the following first implementation manner. The electronic device may also log in the cloud platform by logging in the target website, as in the following second implementation manner.

In a first implementation manner, a target application program is installed on the electronic device, and the electronic device displays a main interface of the target application program in response to the electronic device logging in the target application program. The electronic device jumps from the main interface to the model display interface.

In a second implementation manner, a browser is installed on the electronic device, and the electronic device can acquire target website information input in the browser, display a main interface of a target website based on the target website information, and then jump from the main interface to a model display interface.

In the two implementation manners, the main interface comprises a plurality of plates, the electronic device can determine the residual oil distribution plates from the plurality of plates, and in response to the trigger operation on the residual oil distribution plates, the electronic device logs in the residual oil distribution prediction platform and displays the residual oil distribution interface. The residual oil distribution interface comprises a model determination option, and in response to a triggering operation on the model determination option, the electronic equipment jumps to the model determination interface from the residual oil distribution interface, wherein the model determination interface comprises a plurality of model icons, and the model icons correspond to the shared model.

The cloud platform is described next. Referring to fig. 3, the cloud platform includes: the system comprises a data platform, a technical platform, a sharing model, an artificial intelligence platform and a residual oil distribution prediction platform. Wherein, data platform includes: the system comprises a data acquisition system, a data transmission system and a data storage and management system.

Introduction of data acquisition system: the data acquisition system is mainly used for acquiring data in two modes of automatic acquisition and manual acquisition, the acquired data mainly comprises data of two fields of shaft operation and oil and gas production, and related services of the data comprise engineering technology and development and production.

Introduction to data transmission systems: the data transmission system comprises two modes of wireless transmission and optical transmission. In the embodiment of the application, the electronic device may acquire the data by wireless transmission or optical transmission.

Introduction to data storage management systems: the data storage management system comprises a data processing framework, a data storage system and a data analysis system. The data processing framework is mainly used for processing data, and the data comprises historical data and real-time data.

The data storage system is used for storing the processed data. The types of data stored in the data storage system include structured data, unstructured data, and real-time data. Structured data, as used herein, refers to data that can be represented by data or a unified structure, such as numbers or symbols. Unstructured data refers to data that cannot be represented numerically or with a uniform structure, such as images, sound, and the like. The real-time data refers to a carrier of information obtained at the same time in the occurrence process and the development process of a certain thing and is used for representing raw materials of objective things without processing.

The data analysis system has the functions of high-speed retrieval, joint query and analysis and the like. The functions are mainly to provide various data service capabilities and efficiently support various applications after data processing and storage according to data in a dynamic library, a business library and a professional library and organization and processing of an analysis layer. The analysis layer is provided with an independent physical storage structure, consists of a high-speed index, an analysis library, a domain knowledge base and a model library, and provides data service release to the outside through a unified data service map.

Introduction of technical platform: the technical platform comprises: data middling stations, service middling stations and technical middling stations. The data center platform is used for settling the services and data of each service unit in the digital transformation process, constructing a data construction, management and use system comprising data technology, data processing, data operation and the like, realizing data enabling and is the core of a novel information application framework system. The service center is an extension of the background, and can realize extreme sharing of resources or capabilities. The technical middle station mainly provides various general services, such as icon components, message centers and the like.

Introduction of sharing model: the shared model comprises a geological model, a shaft model, a crack model, a stress model, an economic model, a pipe network model, an initial oil deposit numerical model and the like. The models are trained models and can be directly called.

Introduction of an artificial intelligence platform: the artificial intelligence platform comprises a big data analysis technology and an artificial intelligence professional algorithm. The artificial intelligence professional algorithm comprises a classification algorithm, a clustering algorithm, a Bayesian algorithm, a regression algorithm, an association algorithm, comprehensive evaluation, a time sequence, text mining, ensemble learning, collaborative filtering, automatic learning, deep learning, feature engineering and the like.

Introduction of a residual oil distribution prediction platform: the residual oil distribution prediction platform is mainly used for determining the distribution condition of residual oil, determining the development direction of an oil field through the residual oil distribution, and adjusting drilling, production measures and the like in the oil field development process.

In embodiments of the present application, the cloud platform may include other platforms besides the residual oil distribution prediction platform, for example, a drilling parameter determination platform, through which the electronic device may determine the drilling parameters.

Step 202: and responding to the triggering operation of the target model icon, and displaying a parameter adjusting interface by the electronic equipment.

The electronic equipment determines a target model icon from the plurality of model icons, and in response to a triggering operation on the target model icon, the electronic equipment displays a parameter adjustment interface which comprises a plurality of reservoir parameters and a plurality of parameter adjustment options corresponding to the initial reservoir numerical model. Wherein one reservoir parameter corresponds to one parameter adjustment option.

The electronic equipment can directly display a plurality of oil deposit parameters and can also display a plurality of oil deposit parameters in a classified mode. For example, referring to table 1, the electronic device classifies a plurality of reservoir parameters into three categories, namely, reservoir physical parameters, fluid parameters, and reservoir production control parameters.

TABLE 1

Step 203: and the electronic equipment adjusts at least one oil reservoir parameter based on the parameter adjusting interface to obtain a target oil reservoir numerical model.

In the step, the electronic equipment determines the adjustment range and the adjustment step length of at least one oil reservoir parameter based on a plurality of parameter adjustment options; and adjusting at least one oil deposit parameter according to the adjustment range and the adjustment step length to obtain a plurality of target oil deposit numerical models.

In the implementation mode, the electronic equipment determines at least one oil reservoir parameter from a plurality of oil reservoir parameters, and for each oil reservoir parameter in the at least one oil reservoir parameter, the electronic equipment determines the adjustment range and the adjustment step length of the oil reservoir parameter in response to the triggering operation of the parameter adjustment option corresponding to the oil reservoir parameter. The parameter adjustment interface further comprises an adjustment option, and under the condition that the adjustment range and the adjustment step length of each oil reservoir parameter in the at least one oil reservoir parameter are determined, the electronic equipment adjusts the at least one oil reservoir parameter according to the adjustment range and the adjustment step length of each oil reservoir parameter in the at least one oil reservoir parameter in response to the trigger operation of the adjustment option, so that a plurality of target oil reservoir numerical models are obtained.

For example, the at least one reservoir parameter is an instantaneous injection-production speed, the electronic device determines an adjustment range and an adjustment step length of the instantaneous injection-production speed, for example, the adjustment range of the instantaneous injection-production speed is x-y, and the adjustment step length is z, and then the electronic device adjusts the instantaneous injection-production speed within the adjustment range according to the adjustment step length to obtain a plurality of target reservoir numerical models. For example, the electronic device obtains 100 target reservoir numerical models by adjusting the instantaneous injection-production speed on the basis of the initial reservoir numerical model.

In addition, when the at least one reservoir parameter includes a plurality of reservoir parameters, the plurality of reservoir parameters may be reservoir parameters of the same type, or reservoir parameters of different types, which is not specifically limited.

Step 204: and the electronic equipment determines the comprehensive water content of the sample block along with the change of the time interval based on the target oil reservoir numerical model.

If the number of the target oil deposit numerical models is multiple, for each target oil deposit numerical model, the electronic equipment predicts the comprehensive water content of the sample block after the first time interval based on multiple oil deposit parameters corresponding to the target oil deposit numerical model; if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil reservoir parameters corresponding to the target oil reservoir numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

In the implementation manner, the electronic device may predict the comprehensive water content of the sample block after the first time interval through history fitting based on a plurality of reservoir parameters corresponding to the target reservoir numerical model, and then determine whether the comprehensive water content of the sample block after the first time interval reaches a first preset threshold. And if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, performing history fitting again, predicting the comprehensive water content of the sample block after the second time interval through the history fitting, and then determining whether the comprehensive water content of the sample block after the second time interval reaches the first preset threshold. And if the comprehensive water content of the sample block after the second time interval does not reach the first preset threshold, repeating the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

The first preset threshold may be set and changed as needed, which is not particularly limited. For example, the first preset threshold is 99.5%.

Step 205: and the electronic equipment acquires the oil production data and the water saturation of the sample block along with the time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold value.

In a possible implementation manner, after determining that the comprehensive water content of the sample block after the third time interval reaches the first preset threshold, the electronic device obtains the oil production data and the water saturation corresponding to the sample block in each time interval from the first time interval to the third time interval.

For example, if the first time interval is 1 month, the second time interval is 2 months, and the third time interval is 5 months, the electronic device obtains the oil production data and the water saturation of the sample block after 1 month, the oil production data and the water saturation after 2 months, the oil production data and the water saturation after 3 months, the oil production data and the water saturation after 4 months, and the oil production data and the water saturation after 5 months.

In another possible implementation manner, each time the electronic device determines the comprehensive water content, the electronic device obtains the oil production data and the water saturation corresponding to the time interval.

For example, the first time interval is 1 month, the electronic device determines the comprehensive water content of the sample block after 1 month, and acquires the oil production data and the water saturation of the sample block after 1 month while determining the comprehensive water content. And the second time interval is 2 months, the electronic equipment determines the comprehensive water content of the sample block after 2 months, and the oil production data and the water saturation of the sample block after 2 months are obtained while determining the comprehensive water content.

It should be noted that, after acquiring the oil recovery data and the water saturation of the sample block changing with the time interval, the electronic device may store the data in the sample database, and directly acquire the data from the sample database during the model training.

Step 206: and the electronic equipment performs model training based on the oil extraction data and the water saturation of the sample block changing along with the time interval to obtain a residual oil distribution prediction model.

In one possible implementation, the electronic device performs model training with water saturation as a training target. The process may be: the electronic equipment takes the oil extraction data of each time interval of the sample block as a first training sample, takes the water saturation of each time interval of the sample block as a first training target, and conducts model training based on the first training sample and the first training target to obtain a residual oil distribution prediction model.

In another possible implementation, the electronic device performs model training with oil saturation as a training target. The process may be: the electronic equipment determines the difference value of the second preset threshold value and the water saturation of the sample block at each time interval to obtain the oil saturation of the sample block at each time interval; and taking the oil extraction data of each time interval of the sample block as a second training sample, taking the oil saturation of each time interval of the sample block as a second training target, and performing model training based on the second training sample and the second training target to obtain a residual oil distribution prediction model. Referring to fig. 4, fig. 4 is a schematic diagram of a residual oil distribution prediction model obtained through model training based on a cloud platform.

According to the model training process, the training samples and the training targets are related to a time sequence, and based on the correlation, the electronic device can perform model training through a long-short-term neural network (LSTM). The neural network is a recurrent neural network, which comprises an input layer, a hidden layer and an output layer and is very suitable for processing problems highly related to time series. Referring to fig. 5, fig. 5 is a schematic diagram of a residual oil distribution prediction model obtained by model training through a long-term and short-term neural network with water saturation as a training target.

The second preset threshold may be set and changed as needed, which is not specifically limited. For example, the second preset threshold is 1.

In the embodiment of the application, after the electronic device obtains the residual oil distribution prediction model, the model can be tested through test data. If the residual oil distribution prediction model is obtained by taking the water saturation as a training target, the test process can be as follows: the electronic equipment displays a second data acquisition interface; acquiring historical oil production data and historical water saturation of the test block based on a second data acquisition interface; inputting historical oil extraction data into a residual oil distribution prediction model to obtain the test water saturation of the test block; determining a difference between the test water saturation and the historical water saturation; and if the difference value is within the preset range, determining that the residual oil distribution prediction model passes the test.

In this implementation, the remaining oil distribution interface further includes a test option, and the electronic device displays the second data acquisition interface in response to a trigger operation on the test option. The second data acquisition interface comprises a test data acquisition option, the electronic equipment acquires historical oil production data and historical water saturation in response to the triggering operation of the test data acquisition option, and then the historical oil production data is input into the residual oil distribution prediction model to obtain the test water saturation. The electronics determine whether the residual oil distribution prediction model passes the test by determining a difference between the test water saturation and the historical water saturation. And if the difference value between the residual oil distribution prediction model and the residual oil distribution prediction model is not in the preset range, determining that the residual oil distribution prediction model fails the test. And if the residual oil distribution prediction model fails to pass the test, the electronic equipment performs model training again until the test is passed.

The historical oil production data and the historical water saturation may be acquired by a data acquisition system of the cloud platform from other systems, or may be manually entered, which is not specifically limited.

Correspondingly, if the residual oil distribution prediction model is obtained by using the saturation as a training target, the test process may be as follows: the electronic equipment acquires historical oil production data and historical oil saturation of the test block; inputting historical oil extraction data into a residual oil distribution prediction model; obtaining the test oil saturation of the test block; and determining the difference between the tested oil saturation and the historical oil saturation, and determining that the residual oil distribution prediction model passes the test if the difference is within a preset range.

In the embodiment of the application, the comprehensive water content of the sample block is determined through a numerical reservoir model, oil production data and water saturation of the sample block changing along with time intervals are determined according to the comprehensive water content of the sample block, and then model training is carried out to obtain a residual oil distribution prediction model. Because the residual oil distribution prediction model is obtained by iterative training, the residual oil distribution can be accurately predicted by the residual oil distribution prediction model, so that the accuracy of residual oil distribution prediction is improved.

In addition, although the training sample is derived through the numerical reservoir model in the embodiment of the application, when the residual oil distribution prediction model is tested, the residual oil distribution prediction model is tested through historical real data, so that the prediction accuracy of the residual oil distribution prediction model can be demonstrated.

It should be noted that the electronic device of the residual oil distribution prediction model obtained by the model training and the electronic device that determines the residual oil distribution may be the same device or different devices, and are not particularly limited. Next, description will be given only by taking an electronic device that obtains a residual oil distribution prediction model by model training and an electronic device that specifies residual oil distribution as an example.

Fig. 6 is a flowchart of a remaining oil distribution prediction method provided in an embodiment of the present application, executed by an electronic device, and referring to fig. 6, the method includes:

step 601: the electronic device displays a first data acquisition interface.

The remaining oil distribution interface further comprises: and the electronic equipment displays a first data acquisition interface in response to the triggering operation of the prediction option.

Step 602: the electronic equipment acquires oil production data of the target block based on the first data acquisition interface.

The first data acquisition interface comprises a prediction data acquisition option, and the electronic equipment acquires the oil production data of the target block in response to the triggering operation of the prediction data acquisition option.

The oil extraction data of the target block may be acquired by the data acquisition system of the cloud platform from other systems, or may be manually entered into the data acquisition system, which is not specifically limited.

Step 603: and the electronic equipment inputs the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block.

If the residual oil distribution prediction model is obtained by taking the water saturation as a training target, in the step, the electronic equipment inputs the oil production data of the target block into the residual oil distribution prediction model to obtain the water saturation of the target block; and the electronic equipment takes the difference between the second preset threshold and the water saturation as the oil saturation of the target block, namely the residual oil distribution of the target block.

If the residual oil distribution prediction model is obtained by taking the oil saturation as a training target, in the step, the electronic equipment inputs the oil production data of the target block into the residual oil distribution prediction model to directly obtain the oil saturation of the target block, namely the residual oil distribution of the target block.

In this embodiment, the oil recovery data of the target block may be oil recovery data of the target block at a certain time, oil recovery data of the target block within a certain time range, or real-time oil recovery data of the target block.

If the oil production data of the target block is the oil production data of the target block at a certain moment, the electronic equipment obtains the residual oil distribution of the target block at the moment through the residual oil distribution prediction model, and the residual oil distribution of the target block at the moment is displayed on the display interface.

If the oil production data of the target block is the oil production data of the target block within a time range, the electronic device may obtain the remaining oil distribution of the target block within the time range. The electronic equipment can determine a change trend of the residual oil distribution of the target block based on the residual oil distribution of the target block in the time range, and display the change trend on the display interface.

If the oil production data of the target block is the real-time oil production data of the target block, the electronic equipment can obtain the real-time residual oil distribution of the target block, and the dynamic change of the residual oil distribution of the target block is displayed on the display interface in real time.

In the embodiment of the application, the electronic equipment builds a residual oil distribution prediction platform based on a cloud platform, oil production data in the oil field production process is recorded on the cloud platform, the residual oil distribution rule is researched on the cloud platform through a residual oil distribution prediction model, and the change trend of the residual oil distribution in a block is displayed or the dynamic change of the residual oil distribution is displayed in real time, so that powerful technical support can be provided for later development of the oil field, and cost reduction and efficiency improvement are realized to the greatest extent.

The embodiment of the application provides a residual oil distribution prediction method, which predicts the residual oil distribution of a target block through a residual oil distribution prediction model. Because the residual oil distribution prediction model is obtained by iterative training, the residual oil distribution can be accurately predicted by the residual oil distribution prediction model, so that the accuracy of residual oil distribution prediction is improved.

Fig. 7 is a schematic structural diagram of a remaining oil distribution prediction apparatus provided in an embodiment of the present application, and referring to fig. 7, the apparatus includes:

a first display module 701, configured to display a model determination interface, where the model determination interface includes a plurality of model icons;

a second display module 702, configured to display a parameter adjustment interface in response to a trigger operation on the target model icon; the parameter adjustment interface comprises a plurality of reservoir parameters corresponding to the initial reservoir numerical model;

an adjusting module 703, configured to adjust at least one reservoir parameter based on the parameter adjusting interface to obtain a target reservoir numerical model;

a first determining module 704, configured to determine, based on the target reservoir numerical model, a comprehensive water content of the sample block changing with a time interval;

the first obtaining module 705 is used for obtaining oil extraction data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold value;

the training module 706 is used for performing model training based on the oil production data and the water saturation of the sample block changing along with the time interval to obtain a residual oil distribution prediction model;

a second determining module 707, configured to determine the remaining oil distribution of the target block based on the remaining oil distribution prediction model.

In a possible implementation manner, the first determining module 704 is configured to predict the comprehensive water content of the sample block after the first time interval based on a plurality of reservoir parameters corresponding to the target reservoir numerical model; if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil reservoir parameters corresponding to the target oil reservoir numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

In another possible implementation manner, the second determining module 707 is configured to display a first data obtaining interface; acquiring oil production data of a target block based on a first data acquisition interface; and inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block.

In another possible implementation, the remaining oil distribution of the target zone includes an oil saturation of the target zone;

the second determining module 707 is configured to input the oil production data of the target block into the residual oil distribution prediction model to obtain the water saturation of the target block; and taking the difference between the second preset threshold and the water saturation as the oil saturation of the target block.

In another possible implementation, the parameter adjustment interface includes: a plurality of parameter adjustment options;

an adjusting module 703, configured to determine an adjusting range and an adjusting step length of at least one reservoir parameter based on the multiple parameter adjusting options; and adjusting at least one oil reservoir parameter according to the adjustment range and the adjustment step length to obtain a plurality of target oil reservoir numerical models.

In another possible implementation manner, the training module 706 is configured to use the oil recovery data of each time interval of the sample block as a first training sample, use the water saturation of each time interval of the sample block as a first training target, and perform model training based on the first training sample and the first training target to obtain a residual oil distribution prediction model.

In another possible implementation manner, the training module 706 is configured to determine a difference between a second preset threshold and the water saturation of the sample block at each time interval, so as to obtain the oil saturation of the sample block at each time interval; and taking the oil extraction data of each time interval of the sample block as a second training sample, taking the oil saturation of each time interval of the sample block as a second training target, and performing model training based on the second training sample and the second training target to obtain a residual oil distribution prediction model.

In another possible implementation manner, the apparatus further includes:

the second acquisition module is used for acquiring historical oil production data and historical water saturation of the test block based on a second data acquisition interface;

the third determination module is used for inputting historical oil recovery data into the residual oil distribution prediction model to obtain the test water saturation of the test block;

and the fifth determining module is used for determining that the residual oil distribution prediction model passes the test if the difference value is within the preset range.

The embodiment of the application provides a residual oil distribution prediction device, which determines the comprehensive water content of a sample block through an oil reservoir numerical model, determines the oil extraction data and the water saturation of the sample block along with the time interval change according to the comprehensive water content of the sample block, then performs model training to obtain a residual oil distribution prediction model, and predicts the residual oil distribution of a target block through the residual oil distribution prediction model. Because the residual oil distribution prediction model is obtained by iterative training, the residual oil distribution can be accurately predicted by the residual oil distribution prediction model, so that the accuracy of residual oil distribution prediction is improved.

If the electronic device is provided as a terminal, or the electronic device is provided as a terminal and a server, the structural block diagram of the terminal may refer to fig. 8. The terminal 800 may be a portable mobile terminal such as: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. The terminal 800 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

In general, the terminal 800 includes: a processor 801 and a memory 802.

The processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 801 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit) which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 801 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer-readable storage medium in the memory 802 is used to store at least one program code for execution by the processor 801 to implement the operations performed by the terminal in the remaining oil distribution prediction method provided by the method embodiments herein.

In some embodiments, the terminal 800 may further include: a peripheral interface 803 and at least one peripheral. The processor 801, memory 802 and peripheral interface 803 may be connected by bus or signal lines. Various peripheral devices may be connected to the peripheral interface 803 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 804, display 805, camera assembly 806, audio circuitry 807, and power supply 808.

The peripheral interface 803 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 801 and the memory 802. In some embodiments, the processor 801, memory 802, and peripheral interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 801, the memory 802, and the peripheral interface 803 may be implemented on separate chips or circuit boards, which is not limited by the present embodiment.

The Radio Frequency circuit 804 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 804 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 804 converts an electrical signal into an electromagnetic signal to be transmitted, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 804 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 804 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 805 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 805 is a touch display, the display 805 also has the ability to capture touch signals on or above the surface of the display 805. The touch signal may be input to the processor 801 as a control signal for processing. At this point, the display 805 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 805 may be one, disposed on a front panel of the terminal 800; in other embodiments, the display 805 may be at least two, respectively disposed on different surfaces of the terminal 800 or in a folded design; in other embodiments, the display 805 may be a flexible display disposed on a curved surface or a folded surface of the terminal 800. Even further, the display 805 may be arranged in a non-rectangular irregular pattern, i.e., a shaped screen. The Display 805 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 806 is used to capture images or video. Optionally, camera assembly 806 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, the main camera and the wide-angle camera are fused to realize panoramic shooting and a VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, camera assembly 806 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 807 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 801 for processing or inputting the electric signals to the radio frequency circuit 804 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 800. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 807 may also include a headphone jack.

Power supply 808 is used to power the various components in terminal 800. The power source 808 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power source 808 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, the terminal 800 also includes one or more sensors 809. The one or more sensors 809 include, but are not limited to: acceleration sensor 810, gyro sensor 811, pressure sensor 812, optical sensor 813, and proximity sensor 814.

The acceleration sensor 810 can detect the magnitude of acceleration in three coordinate axes of a coordinate system established with the terminal 800. For example, the acceleration sensor 810 may be used to detect components of gravitational acceleration in three coordinate axes. The processor 801 may control the display 805 to display the user interface in a landscape view or a portrait view based on the gravitational acceleration signal collected by the acceleration sensor 810. The acceleration sensor 810 may also be used for collection of motion data of a game or a user.

The gyro sensor 811 may detect a body direction and a rotation angle of the terminal 800, and the gyro sensor 811 may cooperate with the acceleration sensor 810 to collect a 3D motion of the user with respect to the terminal 800. Based on the data collected by the gyro sensor 811, the processor 801 may implement the following functions: motion sensing (such as changing the UI based on a tilt operation by the user), image stabilization while shooting, game control, and inertial navigation.

Pressure sensors 812 may be disposed on the side frames of terminal 800 and/or underlying display 805. When the pressure sensor 812 is disposed on the side frame of the terminal 800, a user's holding signal of the terminal 800 can be detected, and the processor 801 performs left-right hand recognition or shortcut operation based on the holding signal collected by the pressure sensor 812. When the pressure sensor 812 is disposed at a lower layer of the display screen 805, control of an operability control on the UI interface is realized by the processor 801 based on a pressure operation of the user on the display screen 805. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The optical sensor 813 is used to collect the ambient light intensity. In one embodiment, the processor 801 may control the display brightness of the display screen 805 based on the ambient light intensity collected by the optical sensor 813. Specifically, when the ambient light intensity is high, the display brightness of the display screen 805 is increased; when the ambient light intensity is low, the display brightness of the display 805 is reduced. In another embodiment, the processor 801 may also dynamically adjust the shooting parameters of the camera head assembly 806 based on the ambient light intensity collected by the optical sensor 813.

A proximity sensor 814, also known as a distance sensor, is typically disposed on the front panel of the terminal 800. The proximity sensor 814 is used to collect a distance between the user and the front surface of the terminal 800. In one embodiment, when the proximity sensor 814 detects that the distance between the user and the front surface of the terminal 800 is gradually decreased, the display 805 is controlled by the processor 801 to switch from a bright screen state to a dark screen state; when the proximity sensor 814 detects that the distance between the user and the front face of the terminal 800 is gradually increased, the processor 801 controls the display 805 to switch from the breath-screen state to the bright-screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not intended to be limiting of terminal 800 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

If the electronic device is provided as a server, wherein a block diagram of the server may be shown in fig. 9, the server 900 may generate a relatively large difference due to a difference in configuration or performance, and may include a processor (CPU) 901 and a memory 902, where the memory 902 stores at least one program code, and the at least one program code is loaded and executed by the processor 901 to implement the operation performed by the server in the residual oil distribution prediction method. Certainly, the server 900 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 900 may also include other components for implementing device functions, which are not described herein again.

In an exemplary embodiment, there is also provided a computer readable storage medium storing at least one program code, which is loaded and executed by a processor to implement the remaining oil distribution prediction method in the above embodiments.

In an exemplary embodiment, a computer program product is also provided, which stores at least one program code, which is loaded and executed by a processor to implement the residual oil distribution prediction method in the above-described embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for facilitating the understanding of the technical solutions of the present application by those skilled in the art, and is not intended to limit the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of predicting remaining oil distribution, the method comprising:

acquiring oil extraction data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold;

2. The method of claim 1, wherein determining the integrated water cut of a sample block over a time interval based on the target reservoir numerical model comprises:

if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil reservoir parameters corresponding to the target oil reservoir numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

3. The method of claim 1, wherein determining the residual oil distribution for the target block based on the residual oil distribution prediction model comprises:

displaying a first data acquisition interface;

4. The method of claim 3, wherein the remaining oil distribution of the target block comprises an oil saturation of the target block;

5. The method of claim 1, wherein the parameter adjustment interface comprises: a plurality of parameter adjustment options;

6. The method of claim 1, wherein the model training based on the oil recovery data and water saturation of the sample block over the time interval to obtain a residual oil distribution prediction model comprises:

7. The method of claim 1, wherein the model training based on the oil recovery data and water saturation of the sample block over the time interval to obtain a residual oil distribution prediction model comprises:

8. The method of claim 1, further comprising:

displaying a second data acquisition interface;

9. A residual oil distribution prediction apparatus, characterized in that the apparatus comprises:

the second display module is used for responding to the triggering operation of the target model icon and displaying a parameter adjusting interface; the parameter adjustment interface comprises a plurality of reservoir parameters corresponding to the initial reservoir numerical model;

the first acquisition module is used for acquiring oil production data and water saturation of the sample block along with time interval change under the condition that the comprehensive water content of the sample block reaches a first preset threshold;

10. The apparatus of claim 9, wherein the first determining module is configured to predict the integrated water cut of the sample block after a first time interval based on a plurality of reservoir parameters corresponding to the target reservoir numerical model; if the comprehensive water content of the sample block after the first time interval does not reach the first preset threshold, predicting the comprehensive water content of the sample block after the second time interval based on a plurality of oil deposit parameters corresponding to the target oil deposit numerical model, and repeatedly executing the step of predicting the comprehensive water content until the comprehensive water content of the sample block after the third time interval reaches the first preset threshold.

11. The apparatus of claim 9, wherein the second determining module is configured to display a first data acquisition interface; acquiring oil production data of the target block based on the first data acquisition interface; and inputting the oil production data of the target block into the residual oil distribution prediction model to obtain the residual oil distribution of the target block.

12. The apparatus of claim 11, wherein the remaining oil profile of the target zone comprises an oil saturation of the target zone;

13. The apparatus of claim 9, wherein the parameter adjustment interface comprises: a plurality of parameter adjustment options;

the adjusting module is used for determining an adjusting range and an adjusting step length of the at least one reservoir parameter based on the plurality of parameter adjusting options; and adjusting the at least one oil reservoir parameter according to the adjustment range and the adjustment step length to obtain a plurality of target oil reservoir numerical models.

14. The apparatus of claim 9, wherein the training module is configured to use oil recovery data of each time interval of the sample block as a first training sample, use water saturation of each time interval of the sample block as a first training target, and perform model training based on the first training sample and the first training target to obtain the residual oil distribution prediction model.

15. The apparatus of claim 9, wherein the training module is configured to determine a difference between a second preset threshold and the water saturation of the sample block at each time interval, and obtain the oil saturation of the sample block at each time interval; and taking the oil recovery data of each time interval of the sample block as a second training sample, taking the oil saturation of each time interval of the sample block as a second training target, and performing model training based on the second training sample and the second training target to obtain the residual oil distribution prediction model.

16. The apparatus of claim 9, further comprising:

17. An electronic device, comprising a processor and a memory, wherein the memory has stored therein at least one program code, which is loaded and executed by the processor, to implement the residual oil distribution prediction method according to any one of claims 1 to 8.

18. A computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded into and executed by a processor to implement the residual oil distribution prediction method according to any one of claims 1 to 8.

19. A computer program product having at least one program code stored therein, the at least one program being loaded and executed by a processor to perform the method of residual oil distribution prediction according to any one of claims 1 to 8.