CN116028787A

CN116028787A - Data processing method and device, equipment and storage medium

Info

Publication number: CN116028787A
Application number: CN202111235800.8A
Authority: CN
Inventors: 李政
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Suzhou Software Technology Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Suzhou Software Technology Co Ltd
Priority date: 2021-10-22
Filing date: 2021-10-22
Publication date: 2023-04-28

Abstract

The embodiment of the application discloses a data processing method and device, equipment and a storage medium; the method comprises the following steps: determining a first fitness of each individual in the first geological dataset to which it belongs; transmitting the first geological data set to a second node so that the second node optimizes the first geological data set to obtain a first subset of the first geological data set; and determining a second fitness of each individual in the second geological dataset to which it belongs while waiting for the second node to return to the first subset; determining a third fitness for each individual in the received first subset; and sending the third fitness to the second node so that the second node carries out optimization processing on the first geological data set again until the optimization processing times meet the first convergence condition, and completing inversion of the first geological data set.

Description

Data processing method and device, equipment and storage medium

Technical Field

Embodiments of the present application relate to information technology, and relate to, but are not limited to, data processing methods and apparatuses, devices, and storage media.

Background

Seismic inversion is the process of imaging the spatial structure and physical properties of subsurface formations under the constraints of known geological laws and well drilling and logging information, based on seismic data observed in the earth's surface or well. The pre-stack inversion method selects seismic gather data before horizontal stacking, the gather contains rich amplitude-to-offset variation (Amplitude Variation with Offset, AVO) information, wherein three elastic parameters, namely longitudinal wave speed, transverse wave speed and density, are key parameters, and how to invert the elastic parameters more quickly is an important problem. In the related art, when elastic parameter inversion is performed on hundreds or thousands of acquired angle gathers, iteration is performed on the next angle gather after one iteration is completed on one angle gather. The method for sequentially iterating the calculation is longer in processing time and larger in power consumption.

Disclosure of Invention

In view of this, in the data processing method, device, equipment and storage medium provided in the embodiments of the present application, in the process of inverting each geological data set, iterative processing is performed on a plurality of geological data sets in parallel, so that the data processing time can be greatly shortened. The data processing method, the device, the equipment and the storage medium provided by the embodiment of the application are realized in the following way:

the data processing method provided by the embodiment of the application comprises the following steps: determining a first fitness of each individual in the first geological dataset to which it belongs; wherein the first set of geological data includes at least one individual measurement parameter; transmitting the first geological data set to a second node so that the second node optimizes the first geological data set to obtain a first subset of the first geological data set; and determining a second fitness of each individual in the second geological dataset to which it belongs while waiting for the second node to return to the first subset; wherein the second geological data set is a next geological data set to the first geological data set; determining a third fitness for each individual in the first subset received; and sending the third fitness to the second node so that the second node carries out optimization processing on the first geological data set again until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

The data processing device provided in the embodiment of the application includes: a determining module for determining a first fitness of each individual in a first geological data set to which each individual belongs; wherein the first set of geological data includes at least one individual measurement parameter; the sending module is used for sending the first geological data set to a second node so that the second node can optimize the first geological data set to obtain a first subset of the first geological data set; the determining module is further used for determining a second fitness of each individual in a second geological data set to which the second node belongs in the process of waiting for the second node to return to the first subset; wherein the second geological data set is a next geological data set to the first geological data set; the determining module is further configured to determine a third fitness of each individual in the received first subset; the sending module is further configured to send the third fitness to the second node, so that the second node performs optimization processing on the first geological data set again until the optimization processing times meet a first convergence condition, and inversion of the first geological data set is completed.

The other data processing method provided by the embodiment of the application comprises the following steps: receiving a first fitness of each individual in a first geological data set which the first node of first electronic equipment belongs to and the first geological data set; wherein the geological dataset comprises at least one individual measurement parameter; optimizing the first geological data set according to the first fitness of each individual to obtain a first subset of the first geological data set; transmitting the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first node belongs; and in the process of waiting for the first node to return to the third fitness, performing optimization processing on a second geological data set to obtain a third subset of the second geological data set; receiving a third fitness of each individual in the first subset to which the first node returns; and carrying out optimization processing on the first geological data set again according to the third fitness until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

Another data processing apparatus provided in an embodiment of the present application includes: the receiving module is used for receiving the first fitness of each body in the first geological data set and the first geological data set which are transmitted by the first node; wherein the geological dataset comprises at least one individual measurement parameter; the processing module is used for carrying out optimization processing on the first geological data sets according to the first fitness of each individual to obtain a first subset of the first geological data sets; a sending module, configured to send the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first node belongs; the processing module is further configured to perform optimization processing on a second geological data set in a process of waiting for the first node to return to the third fitness, so as to obtain a third subset of the second geological data set; the receiving module is further configured to receive a third fitness of each individual in the first subset to which the first node returns; and the processing module is further used for carrying out optimization processing on the first geological data set again according to the third adaptability until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

The electronic device provided by the embodiment of the application comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor realizes the method described by the embodiment of the application when executing the program.

The computer readable storage medium provided in the embodiments of the present application stores a computer program thereon, which when executed by a processor implements the method provided in the embodiments of the present application.

In this embodiment of the present application, after the first node sends the determined first fitness of each individual in the first geological data set to the second node, the first node is in an idle state when waiting for the second node to return to the first subset obtained by optimizing the first geological data set, and at this time, the first node continuously determines the second fitness of each individual in the second geological data set (i.e., the next geological data set different from the first geological data set), so as to avoid resource waste caused by the idle state generated by the first node. In the inversion process of each geological data set, the method for carrying out iterative processing on a plurality of geological data sets in parallel can greatly shorten the data processing time.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the technical aspects of the application.

Fig. 1 is a schematic implementation flow chart of a data processing method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an implementation flow of another data processing method according to an embodiment of the present application;

FIG. 3 is a schematic diagram illustrating an implementation flow of a further data processing method according to an embodiment of the present application;

fig. 4 is a schematic implementation flow chart of an intelligent optimization algorithm provided in an embodiment of the present application;

FIG. 5 is a schematic diagram of a distributed framework in a one-dimensional case;

FIG. 6 is a schematic diagram of a two-dimensional and three-dimensional distributed framework;

FIG. 7 is a schematic diagram of a data processing apparatus according to an embodiment of the present application;

FIG. 8 is a schematic diagram of another data processing apparatus according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

For the purposes, technical solutions and advantages of the embodiments of the present application to be more apparent, the specific technical solutions of the present application will be described in further detail below with reference to the accompanying drawings in the embodiments of the present application. The following examples are illustrative of the present application, but are not intended to limit the scope of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

It should be noted that the term "first/second/third" in reference to the embodiments of the present application is used to distinguish similar or different objects, and does not represent a specific ordering of the objects, it being understood that the "first/second/third" may be interchanged with a specific order or sequence, as permitted, to enable the embodiments of the present application described herein to be implemented in an order other than that illustrated or described herein.

The embodiment of the application provides a data processing method, which is applied to a first node in first electronic equipment, wherein the first electronic equipment can be various types of computer equipment with information processing capability in the implementation process, and for example, the computer equipment can comprise a desktop computer, a notebook computer, a palm computer and the like; the electronic device may also be a mobile terminal, for example, the mobile terminal may include a mobile phone, a vehicle-mounted computer, a tablet computer, a POS machine, or the like. The functions performed by the method may be performed by a processor in an electronic device, which may of course be stored in a computer storage medium, as will be seen, comprising at least a processor and a storage medium.

Fig. 1 is a schematic flowchart of an implementation of a data processing method according to an embodiment of the present application, as shown in fig. 1, the method may include the following steps 101 to 105:

in step 101, the first node determines a first fitness of each individual in the belonging first geological dataset.

In the application implementIn one example, each geological dataset contains a plurality of individuals, each individual corresponding to a plurality of sets of measured parameters, e.g., using G _i ＝(V _P1 ,V _s1 ,ρ ₁ ,V _P2 ,V _s2 ,ρ ₂ ,...V _Pn ,V _sn ,ρ _n ) To represent the position vector of the ith individual, where (V) _p ,V _s ρ) is a set of measurement parameters. The first node first initializes the position of each individual before calculating the first fitness of each individual in the first geological data set, wherein the position vector of each individual is composed of measurement parameters; and then, the first node calculates the fitness of the individuals in the obtained first geological data set according to a preset objective function (namely, fitness function), so as to obtain the first fitness of each individual in the first geological data set.

In some embodiments, the geological dataset is corner gather (common depth point, CDP) data.

Step 102, the first node sends the first geological data set to a second node of the second electronic device, so that the second node optimizes the first geological data set to obtain a first subset of the first geological data set.

The first electronic device and the second electronic device may be the same device or different devices. After receiving the first geological data set sent by the first node and the first fitness of each individual contained in the first geological data set, the second node can perform optimization processing on the first geological data set according to the first fitness of each individual in the first geological data set to obtain at least one first subset of the first geological data set after division and a first candidate individual (namely, the individual with the best fitness of the first subset) in each first subset, so that one iteration is completed. In some embodiments, step 102 may be implemented by performing steps 302 through 304 as follows.

Step 103, the first node determines a second fitness of each individual in the second geological data set to which the second node belongs while waiting for the second node to return to the first subset.

It will be appreciated that after the first node transmits the first fitness to the second node, it may take some time for the second node to optimize the first geological data set, while the first node is in an idle state, which may wait for the second node to return to the first subset to continue determining the third fitness of the individuals in each of the first subsets. Therefore, in the embodiment of the present application, in order to avoid resource waste caused by the first node being idle, and improve the system operation speed, the first node may continuously determine the second fitness of each individual in the second geological data set (i.e. the next geological data set different from the first geological data set) while waiting for the second node to return to the first subset.

For example, the electronic device receives three geological data sets and sorts them according to the received sequence, the first received geological data set is called a first geological data set, and the electronic device processes them preferentially; the second received geological data set is referred to as a second geological data set, which is the next geological data set to the first geological data set; the third received geological data set is referred to as a third geological data set, which is the next geological data set to the second geological data set.

In some embodiments, the first node transmits the obtained second fitness and second geological data set for each individual to the second node; and in waiting for the second node to return to the second subset, performing the following steps 1031 to 1032:

step 1031, if the first node does not receive the third subset returned by the second node, determining a fourth fitness of each individual in the third geological dataset to which the first node belongs; the second subset is obtained by the first node performing optimization processing on the first geological data set again according to the third fitness of each individual, and the third subset is obtained by the first node performing optimization processing on the second geological data set according to the second fitness of each individual.

After determining the second fitness of each individual in the second geological data set, the first node sends the second fitness of each individual in the second geological data set to the second node, where the second node may have the following two cases:

(1) The second node is performing an optimization process on the first geological data set according to the first fitness of each individual to obtain a first subset, but the process is not performed, i.e. the second node does not return the first subset to the first node; accordingly, the second node does not perform optimization processing on the received second geological data set, and the first node cannot receive a third subset, which is returned by the second node and obtained by performing optimization processing on the second geological data set according to the second fitness of each individual. At this time, the first node is in the idle state again, and then the fourth fitness of each individual in the third geological data set can be continuously determined, so that resource waste is avoided.

(2) The second node, upon receiving the second geological dataset and the second fitness of each individual it contains, has completed the process of optimizing the first geological dataset according to the first fitness of each individual, i.e. has obtained the first subset, and returns the first subset to the first node. The second node continues to optimize the second geological dataset according to the second fitness while the first node determines a third fitness for each individual in the first subset; if the second node has not performed the optimization of the second data set after the first node has completed the validation of the third fitness of each individual in the first subset, the determination of the fourth fitness of each individual in the third geological data set may be continued in order to avoid wastage of the first node from idleness.

Step 1032, if the first node receives the third subset returned by the second node, determining a fifth fitness of each individual in the third subset to which the first node belongs.

Of course, if the first node receives the third subset returned by the second node, the fifth fitness of each individual in the third subset is directly determined. When calculating the fitness of the individual, the first node preferably calculates the fitness of the individual returned by the second node.

Step 104, the first node determines a third fitness of each individual in the first subset returned by the received second node.

And 105, the first node sends the third fitness to the second node so that the second node carries out optimization processing on the first geological data set again until the optimization processing times meet the first convergence condition, and inversion of the first geological data set is completed.

After receiving the first fitness and the first geological data set, the second node performs optimization processing on the first geological data set to obtain a first subset; the first subset is returned to the first node, and the first node determines the third fitness of the first subset, and then an iteration is completed; in the next iteration, the first node sends the third fitness to the second node, the second node performs optimization processing on the first geological data set again according to the third fitness after receiving the third fitness, and returns the obtained next subset of the first geological data set to the first node, and the steps are continuously circulated until the optimization times of the first geological data set meet the first convergence condition, so that the iteration processing of the first geological data set is completely completed. The first convergence condition may be determined according to actual needs, for example, the first convergence condition is that the number of optimization times reaches 4000 times, or the first convergence condition is that the number of optimization times reaches 5000 times.

The embodiment of the application provides a data processing method, which is applied to a second node in a second electronic device, wherein the second electronic device can be various types of computer devices with information processing capability in the implementation process, and for example, the computer devices can comprise a desktop computer, a notebook computer, a palm computer and the like; the electronic device may also be a mobile terminal, for example, the mobile terminal may include a mobile phone, a vehicle-mounted computer, a tablet computer, a POS machine, or the like. The second electronic device and the first electronic device may be the same device or different devices. The functions performed by the method may be performed by a processor in an electronic device, which may of course be stored in a computer storage medium, as will be seen, comprising at least a processor and a storage medium.

Fig. 2 is a schematic flowchart of an implementation of a data processing method according to an embodiment of the present application, as shown in fig. 2, the method may include the following steps 201 to 206:

step 201, a second node receives a first fitness of each individual in a first geological data set and a first geological data set which are transmitted by a first node of a first electronic device; wherein the geological dataset comprises at least one individual measured parameter.

In this embodiment of the present application, the first node performs fitness calculation on the individuals in the obtained first geological data set in at least one geological data set according to a preset objective function (i.e., fitness function), obtains a first fitness of each individual in the first geological data set, and sends the first fitness and the first geological data set to the second node. In each geological dataset, a plurality of individuals are included, each individual having its corresponding at least one measured parameter.

In some embodiments, the geological dataset is angular gather data and the measured parameter is a pre-stack seismic data AVO elastic parameter comprising at least one of longitudinal wave velocity, transverse wave velocity, and density.

In step 202, the second node performs optimization processing on the first geological dataset according to the first fitness of each individual, so as to obtain a first subset of the first geological dataset.

After receiving the first geological data set sent by the first node and the first fitness of each individual contained in the first geological data set, the second node can perform optimization processing on the first geological data set according to the first fitness of each individual in the first geological data set to obtain at least one first subset of the first geological data set after division and a first candidate individual (namely, the individual with the best fitness of the first subset) in each first subset, so that one iteration is completed. In some embodiments, step 202 may be implemented by performing steps 302 through 304 as follows.

The second node sends the first subset to the first node, step 203, to cause the first node to determine a third fitness of each individual in the first subset to which it belongs.

In the next iteration, the second node sends the first subset obtained by the optimization processing to the first node to obtain a third fitness of each individual in the first subset.

In step 204, the second node performs optimization processing on the second geological data set while waiting for the first node to return to the third fitness, so as to obtain a third subset of the second geological data set.

The first node has calculated a second fitness for each individual in the second geological data set while it is in an idle state before calculating a third fitness for each individual in the first subset, and sent the second fitness and the second geological data set to the second node. It can be appreciated that, after the first node receives the first subset, it takes a certain time to calculate the third fitness of each individual in the first subset, which cannot immediately send the third fitness to the second node, so that the second node is in an idle state at that moment, so that at this moment, the second node may perform optimization processing on the second geological data set according to the received second fitness, thereby avoiding resource waste caused by the idle state of the second node. In the inversion process of each geological data set, the method carries out iterative processing on a plurality of geological data sets in parallel, thereby greatly shortening the data processing time and improving the running speed of the system.

Step 205, the second node receives a third fitness of each body in the first subset to which the first node returns;

and 206, the second node carries out optimization processing on the first geological data set again according to the third adaptability until the optimization processing times meet the first convergence condition, and inversion of the first geological data set is completed.

In some embodiments, step 206 may be implemented by steps 2061 to 2063 as follows:

step 2061, performing optimization processing on the first geological data set again according to the third fitness to obtain a third subset of the first geological data set;

step 2062, continuing to perform optimization processing on the first geological data set again according to the individual fitness of the subset of the first geological data set obtained by the kth-1 iteration to obtain a fourth subset and corresponding candidate individuals; where k is the number of optimization processes.

In the embodiment of the application, the second node completes one-time optimization processing on the first geological data set, namely, a subset corresponding to the current optimization processing and candidate individuals in each subset can be obtained. In determining the candidate individuals of each fourth subset, the individual with the best fitness (meeting the first condition) is selected from each individual of each fourth subset as the candidate individual corresponding to the current fourth subset. And when the first geological data set is optimized in the next iteration, obtaining a new subset and candidate individuals in each new subset, and obtaining a fourth subset and candidate individuals in each fourth subset, which are generated by optimizing the first geological data set in the final iteration, until the optimizing times meet the first convergence condition.

Step 2063, selecting a target individual meeting the first condition from a plurality of different candidate individuals, and taking the measurement parameter corresponding to the target individual as the target inversion parameter of the first geological data set to finish inversion of the first geological data set.

The second node is capable of obtaining candidate individuals in each fourth subset of the first geological dataset upon completion of a final iteration of the first geological dataset, and the second node is selected from the candidate individuals of the fourth subset upon determination of the target individual.

Of course, the process of optimizing the second geological data set by the second node until the number of times of optimizing the second geological data set satisfies the first convergence condition is the same as the process of optimizing the first geological data set by the second node. Accordingly, when selecting the target individual in the second geological data set, it is also selected from the fourth subset of candidate individuals resulting from the final iteration of the second geological data set.

In some embodiments, if the first node takes a long time to calculate the fitness of each individual, and the second node cannot receive the data set which can be subjected to the optimization processing for a long time, the second node may also be used as a calculating node (i.e. the first node), that is, the burden of calculating the fitness of each individual by the first node is shared by the second node.

In the embodiment of the application, the second node is in an idle state in the process of waiting for the first node to return to the third fitness, and at this time, the second node can perform optimization processing on the second geological data set according to the received second fitness, so that resource waste caused by idle generation of the second node is avoided. In the inversion process of each geological data set, the method for carrying out iterative processing on a plurality of geological data sets in parallel can greatly shorten the data processing time and improve the running speed of the system.

Fig. 3 is a schematic flowchart of an implementation of a data processing method according to an embodiment of the present application, as shown in fig. 3, the method may include the following steps 301 to 310:

step 301, a second node receives a first fitness of each body in a first geological data set and a first geological data set, wherein the first fitness and the first geological data set are of each body and are sent by a first node;

in step 302, the second node determines a distance between each individual and other individuals according to the measurement parameters of the individuals in the first geological dataset, and obtains a first distance.

In an embodiment of the present application, the first distance is a euclidean distance between a certain individual and all other remaining individuals in the geological dataset, the euclidean distance being determined according to a measured parameter of the individual. After determining the Euclidean distance of each individual from the other individuals, a Euclidean distance matrix is constructed from the Euclidean distances.

In some embodiments, step 302 is implemented by performing steps 3021 to 3022 as follows:

in step 3021, the second node ranks the first fitness of each individual in the first geological dataset to obtain a ranked first geological dataset.

The second node first ranks each individual in the first geological dataset according to the first fitness of each individual, thereby obtaining a ranked first geological dataset. The order may be an ascending order or a descending order, and is not limited thereto.

In step 3022, the second node determines, according to the measurement parameters of the individuals in the first geological dataset after sorting, the distances between each individual and other individuals, and obtains the first distance.

It will be appreciated that the unordered individuals in the first geological data set are transformed into ordered individuals after ordering the individuals by fitness. In this way, when calculating the distance between each individual and other individuals, the distance of each individual from the subsequent individual can be calculated in turn, thereby avoiding repeated calculation.

In step 303, the second node divides the first geological dataset according to each first distance, resulting in a first subset of the first geological dataset.

When the second node optimizes the first geological data set, the first geological data set is firstly subjected to division processing to obtain at least one first subset, and then candidate individuals with optimal fitness are selected from the first subset. In the embodiment of the application, when the second node performs the division processing on the first geological data set, the first geological data set is divided based on a first distance between each individual and other individuals.

In some embodiments, step 303 is implemented by performing steps 3031 through 3033 as follows:

step 3031, the second node searches for an individual whose first distance from the i+1st individual to the last individual in the sorted first geological data set meets a first condition; establishing connection between the ith individual and the corresponding individual meeting the first condition; wherein i is greater than 0 and less than or equal to the total number of individuals of the first geological data set; the first fitness of the (i+1) th individual is greater than the first fitness of the (i) th individual; the first condition is that the distance is nearest or less than a first threshold; and traversing in sequence to complete connection establishment of each individual in the first geological data set after the sorting and the corresponding individual meeting the condition.

In this embodiment of the present application, each individual in the first data set is connected with another individual that satisfies the first condition, so that an edge can be formed, and the edge distance is a first distance determined in advance between the individual and another individual that satisfies the first condition, and at this time, the edge distance can be found out from the euclidean distance matrix.

Taking the ith individual as an example, when determining the individual which meets the first condition with the ith individual in the first geological data set (the fitness is superior to the ith individual and is closest to the first distance of the ith individual), since the individuals in the first geological data set are already ordered according to the fitness, if the individuals are ordered in ascending order, the fitness from the (i+1) th individual to the last individual is superior to the ith individual, and then the individual closest to the first distance of the ith individual is only needed to be searched from the (i+1) th individual to the last individual. It can be seen that this way of determining is relatively simple and orderly, and it is possible to avoid traversing each individual in the first geological data set, but only by searching for a part of the individuals.

Step 3032, disconnecting the connection with the connected individual if the first distance of the ith individual from the connected individual is greater than the second threshold.

The second threshold is based on each individual andthe corresponding edge distances after the individual connection meeting the conditions are determined, after each edge distance is obtained, the average value mu dist of the edge distances can be calculated, and a parameter is set

Will be

As a second threshold.

If a first distance between an individual and its corresponding conditional individual is greater than a second threshold, it is stated that the individual is farther from the conditional individual, which should be categorized into two different subsets. Therefore, it is necessary to disconnect the connection between those individuals whose edge distances are greater than the second threshold value and their corresponding individuals who meet the condition.

Step 3033, until a determination is made as to whether the first distance between each individual in the sorted first geological data set and the connected individual is greater than a second threshold, the connected individuals are taken as a first subset.

Traversing each individual in the ordered first geological data set in sequence, determining whether the edge distance of each individual after being connected with the corresponding individual meeting the first condition is larger than a second threshold value, and if so, disconnecting. In this way, the distance between the plurality of individuals that can ultimately be connected together is relatively short, which can be taken as a subset, thereby enabling the partitioning of the first geological dataset in this way. The partitioning method has relatively simple, efficient and versatile characteristics.

Of course, the process of the second node in optimizing the subsequent geological data set and determining the corresponding subset is the same as the process of the second node in optimizing the first geological data set.

Step 304, the second node determines candidate individuals in each first subset according to the first fitness of the individuals in the first subset;

step 305, the second node sends the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first node belongs;

step 306, the second node performs optimization processing on the second geological data set according to the second fitness of each body in the second geological data set to which the first node belongs in the process of waiting for the first node to return to the third fitness, so as to obtain a third subset of the second geological data set and candidate individuals in each third subset;

step 307, the second node receives the third fitness of each body in the first subset to which the first node returns;

step 308, the second node performs optimization processing on the first geological data set again according to the third adaptability to obtain a second subset of the first geological data set and candidate individuals in each second subset; and obtaining candidate individuals of the fourth subset of the first geological data set until the optimization times meet the first convergence condition.

In each iteration, candidate individuals of the subset of the first geological data set obtained at the time of the iteration are determined, not only in relation to the result of the time of the iteration, but also in relation to the candidate individuals obtained at the last iteration. In some embodiments, the first node performs optimization processing on the first geological data set again according to the fitness of the individuals of the subset of the first geological data set obtained by the kth-1 iteration to obtain the current subset and the corresponding candidate individuals, and performs the following steps 3081 to 3082:

in step 3081, the second node performs optimization processing on the first geological data set again according to the fitness of the individuals of the subset of the first geological data set obtained by the k-1 th iteration, so as to obtain a fourth subset and the corresponding good individuals.

Taking the kth iteration as an example for illustration, after the kth-1 iteration is completed, the second node obtains subsets of the first geological data set corresponding to the kth-1 iteration, the fitness of the individuals in each subset, and according to the fitness of the individuals in the subsets, the kth optimization processing is performed on the first geological data set again, so as to obtain the kth corresponding subset and the good individuals in each subset (namely, the individuals with the optimal fitness in each subset).

In step 3082, the second node determines, as candidate individuals of the fourth subset, those having fitness satisfying the second condition among candidate individuals of the subset of the first geological dataset and the excellent individuals of the current subset obtained by the kth-1 iteration.

Comparing the fitness of candidate individuals of the subset of the first geological data set obtained by the k-1 iteration with the fitness of good individuals in the subset obtained by the k iteration, and selecting the individuals with better fitness from the fitness to be the candidate individuals finally obtained by the k iteration. When selecting individuals with better fitness, selecting the first half of individuals after ascending arrangement; the selection method is not limited, and more preferable individuals may be selected for comparing the fitness of the candidate individuals and the excellent individuals in the similar subsets, respectively.

In step 309, the second node determines a degree of correlation between the measured parameters and the actual measured parameters of the candidate individuals of the fourth subset of the first geological dataset.

It should be noted that each individual in the geological data set is obtained by combining a plurality of sets of measurement parameters, that is, the measurement parameters corresponding to the candidate individual obtained by final calculation are obtained by combining infinite longitudinal wave speeds, transverse wave speeds and densities. Therefore, there are cases where the candidate individual obtained by calculating the three parameters with errors and the two parameters with errors are the same, and one parameter has the same candidate individual obtained by calculating the errors. Therefore, the target individual is selected from the measurement parameters of the candidate individuals through the correlation of the measurement parameters of the candidate individuals and the actual measurement parameters, so that the obtained measurement parameters of the target individual are more convincing.

In the embodiment of the application, after the candidate individual obtained by the final iteration of the first geological data set is determined, the correlation degree between the measurement parameters of the candidate individual obtained by inversion and the actual measurement parameters can be measured by calculating the difference between the average value of the multiple groups of measurement parameters of the candidate individual and the standard value of the actual measurement parameters.

In step 310, the second node selects a target individual from the candidate individuals according to the correlation degree of each candidate individual, and takes the measurement parameter corresponding to the target individual as the target inversion parameter.

After the correlation degree corresponding to each candidate individual is obtained, the score value of each candidate individual is calculated according to the correlation degree, and the candidate individual with the larger score value is selected as the target individual.

In some embodiments, after obtaining the target inversion parameters of the first geological dataset, in order to improve the accuracy of the inversion, the following steps 401 to 404 may be further performed:

step 401, determining a generated geological record corresponding to the target inversion parameter by a second node according to the target inversion parameter;

step 402, the second node determines whether a difference value between the actual geological record corresponding to the first geological data set and the generated geological record meets a third condition;

After obtaining the target individual, the second node models through a forward model, such as Aki & Richard approximate equation, according to inversion parameters of the target individual, so as to calculate a corresponding generated geological record; then, the second node compares the generated geological record with the actual geological record corresponding to the first geological data set, determines whether the difference value of the generated geological record and the actual geological record meets a third condition, and can set an error threshold value, and if the difference value of the generated geological record and the actual geological record is larger than the error threshold value, the third condition is considered not to be met; if the difference is less than the error threshold, then a third condition is deemed satisfied.

Step 403, if the difference value does not meet the third condition, sending the target inversion parameter to the first node, so that the first node updates the parameter of the objective function according to the target inversion parameter to obtain an updated objective function, and executing the methods in steps 101 to 105 according to the updated objective function;

step 404, the second node executes the methods in steps 201 to 207 or steps 301 to 310 according to the fitness returned by the first node based on the updated objective function, and obtains a new objective inversion parameter until the difference obtained according to the new objective inversion parameter meets a third condition.

If the difference value meets a third condition, the target individual obtained after the first geological data set is processed is correct, and inversion can be finished; if the difference does not meet the third condition, indicating that the target individual obtained after the first geological data set is processed is error, and continuing to determine a new target individual so that the difference between the generated geological record and the actual geological record meets the third condition. In the process of redefining a new target individual, the objective function for determining the fitness of each individual in the first node may be updated according to the currently obtained measurement parameters of the target individual, and the methods in steps 101 to 105 are performed according to the updated objective function, and then, in the first node, the methods in steps 201 to 207 or 301 to 310 are performed based on the fitness returned by the updated objective function.

The seismic inversion is a process of imaging the space structure and physical properties of the underground rock stratum under the constraint of known geological laws and drilling and logging information according to the seismic data observed in the earth surface or the well, and is an important component in the geophysical inversion problem. The pre-stack inversion method selects seismic gather data before horizontal stacking, wherein the gather contains rich AVO information, and three elastic parameters of longitudinal wave speed, transverse wave speed and density are key parameters. The three elastic parameters can reflect the saturation condition of underground oil and gas laterally, and inversion of the pre-stack seismic data AVO elastic parameters mainly performs inversion on the three elastic parameters (namely measurement parameters). The seismic inversion problem has the characteristics of nonlinearity, multiple solutions, large scale and the like.

In the related art, the method for inverting the AVO elastic parameters of the pre-stack seismic data comprises linear inversion and nonlinear inversion. The linear inversion is a method for linearizing the problem of AVO elastic parameter inversion of pre-stack seismic data, and most of the problems faced in geophysical inversion are nonlinear inversion problems. However, since nonlinear inversion is much more complex and difficult than linear inversion, nonlinear inversion problems are typically linearized or pseudo-linearized in solving an objective function, and linear inversion is performed, mainly by creating an initial model. The nonlinear inversion method mainly solves the problem of inversion of elastic parameters of pre-stack seismic data AVO by using an intelligent optimization algorithm in a mode of combining the intelligent optimization algorithm, such as a genetic algorithm, a particle swarm algorithm, a differential evolution algorithm and the like. The current pre-stack seismic data AVO elastic parameter inversion is carried out by constructing an fitness function, carrying out iterative optimization on the fitness function by using an optimization algorithm, and selecting one value with the maximum or minimum fitness value as an optimal value and taking the value as a final value when the error reaches a specified range.

The linear inversion is early in starting and has a mature algorithm and a mature evaluation system, but the linear inversion method often has the problems of monotonous algorithm, strong dependence on an initial model and the like, if the initial model is improperly selected, local optimum is involved, even the initial model is not converged, the nonlinear problem is often difficult to linearize, and the two problems restrict the application of the linearization method to a great extent. Nonlinear inversion methods using intelligent optimization algorithms have some drawbacks due to the intelligent optimization algorithms themselves, such as huge computation and easy sinking into local optima; moreover, in general, these intelligent optimization algorithms often only obtain one optimal solution, and are not necessarily globally optimal solutions.

Based on this, in the embodiment of the application, a multi-mode optimization method based on the nearest optimal cluster (Nearest better clustering) of Euclidean distance and a distributed parallel method are used to solve the inversion of the elastic parameters of the pre-stack seismic data AVO. The clustering method has the characteristics of relative simplicity, effectiveness and universality, can be combined with an intelligent optimization algorithm, can solve the nonlinearity of inversion, divides and clusters a population through Euclidean distance to obtain a plurality of local optimal solutions and global optimal solutions, and selects the optimal solutions according to specific comparison aiming at the solutions, so that the multi-solution property of the inversion problem is well solved. As the inversion proceeds from one-dimensional lines to two-dimensional planes and three-dimensional volumes, the amount of data increases gradually, and the computation time increases, the use of distributed techniques to solve this large-scale problem is a necessary choice.

The most recent optimal cluster divides the entire population into clusters, and the algorithm is based on one assumption that: the optimal feasible solution in the local area approximates the optimal solution of the area, and the distance between optimal individuals in different areas is far greater than the average of the distances from all individuals to their nearest better neighbors.

The main steps of the most recent optimal clustering algorithm are as follows:

step 1, firstly, sorting according to fitness values of each individual in a population, and after sorting, calculating Euclidean distance (namely first distance) between each individual and each individual, and constructing a Euclidean distance matrix.

Step 2, each individual is then connected to the nearest better individual except the best individual, thereby forming an edge, through which all the individuals are connected together to form a spanning tree.

Step 3, finally, calculating the average value of all the edge distances, recording as mu dist, and setting a parameter

Length is greater than +.>

The edges of the (i.e. first condition) are removed so that the population is divided into clusters, each connected cluster corresponding to a sub-population.

The clustering method has the characteristics of relative simplicity, effectiveness and universality, can be combined with an intelligent optimization algorithm, and takes a particle swarm algorithm as an example, and the algorithm steps combined with the particle swarm algorithm are as follows in steps 1 to 10:

And step 1, initializing. And determining the population scale N of the particle swarm, and determining the maximum iteration number T. The velocity and position of each particle are initialized.

And 2, adapting the degree value. The fitness value of each particle is calculated from the fitness function (i.e., the objective function) of the algorithm.

And 3, finding the optimal value. Setting the current fitness value of all particles as the initial optimal value pbest of the particles _i . And compareThe initial optimal solution with particles determines the optimal value gbest for the whole population.

And 4, sorting according to the fitness value of each individual in the population, calculating the Euclidean distance between each individual after sorting, and constructing an Euclidean distance matrix.

Step 5, each individual is connected with the nearest better individual, so that an edge is formed.

Step 6, calculating the average value of all the edge distances to be mu dist, and setting the length to be greater than

Is used to divide the population into a plurality of populations.

And 7, searching the optimal individuals in each population.

And 8, for individuals in different populations, updating the speed and the position of each particle according to a particle group speed position updating formula, and calculating the fitness value of each updated particle.

And 9, searching individual optimal. Comparing the new fitness value of each particle with the optimal fitness value pbest of the particle _i Taking the optimal result as pbest _i 。

Step 10, repeating the steps 4 to 9 in a circulating way until the set iteration times are reached, and ending the algorithm.

The method is characterized in that an algorithm combining the latest optimal clustering method and the intelligent optimization algorithm is applied to the inversion problem of the pre-stack seismic AVO elastic parameters, and the specific steps are as follows:

step 1, reading actual seismic data (namely actual geological records) and logging data.

Step 2, setting population scale n, maximum iteration times T and controlling parameters

An inversion objective function is determined, an initial iteration number t=0, and a population is initialized.

And step 3, calculating the fitness value of each particle according to the objective function of the algorithm.

Step 4, setting the current fitness value of all the particles as the initial optimal value pbest of the particles _i And comparing the initial optimal solutions of all particles to determine the optimal value gbest of the whole population.

And 5, sorting according to the fitness value of each individual in the population, calculating the Euclidean distance between each individual after sorting, and constructing the Euclidean distance matrix.

Step 6, each individual is connected with the nearest better individual, so that an edge is formed.

Step 7, calculating the average value of all the edge distances, recording as mu dist, and setting the length to be greater than

Is used to divide the population into a plurality of populations.

And 8, searching the optimal individuals (i.e. candidate individuals) in each population.

And 9, for individuals in different populations, updating the speed and the position of each particle according to a particle group speed position updating formula. And calculates the fitness value of each particle after updating.

And step 10, searching individual optimal. Comparing the new fitness value of each particle with the optimal fitness value pbest of the particle _i Taking the optimal result as pbest _i 。

And 11, circularly repeating the steps 5 to 9 until the set iteration times are reached, and ending the algorithm.

Through continuous iterative operation, the computing population is continuously divided into different search areas for searching, and finally the effect of searching a plurality of local and global optimal solutions is achieved.

The problem of inversion of elastic parameters of pre-stack earthquake AVO is a multi-solution problem, in the case of one dimension, the obtained calculation result is a curve, the two dimension is from line to surface, the three dimension is from surface to body, in order to avoid the situation of combined explosion, therefore, a plurality of local and global optimal solutions for reverse performance also need to be further selected, and the most suitable solution is selected as a final solution.

In the inversion process, forward modeling is continuously relied on for calculation. As shown in fig. 4, a schematic implementation flow chart of an intelligent optimization algorithm is provided, the intelligent optimization algorithm on the right is used as an optimizer to generate elastic parameters including longitudinal wave velocity, transverse wave velocity and density involved in a forward model, the left uses a pre-stack inversion theoretical model as a forward model (such as Aki & Richard approximation equation) used in inversion problem to model, and calculates corresponding seismic data (i.e. to generate geological records) according to the elastic parameters, and compares the corresponding seismic data with actually detected seismic data (i.e. actual geological records).

Due to the non-unique characteristics of the inversion problem, the same set of inversion seismic data is finally calculated and obtained by combining infinite longitudinal wave speeds, transverse wave speeds and densities. Therefore, there are cases where the inversion seismic data obtained by calculating the three parameters with errors is the same as the inversion seismic data obtained by calculating the two parameters with errors, and one parameter with errors is the same. In order to better evaluate the quality of the inversion result of the optimization algorithm on the pre-stack AVO elastic parameters, the correlation condition of the three parameters of the inversion and the actual three parameters is measured by using the statistical common pearson moment correlation coefficient at the end of inversion.

If there are two variables: x, Y, the correlation coefficient function (Pearson product-moment correlation coefficient) expression established here is shown in equation 1 below:

wherein X is _i Is the standard value of one parameter in three elastic parameters, Y _i Is the inversion value corresponding to the value,

each being an average of a set of values corresponding to the elastic parameter.

Because the seismic data solving process is quite complex, the smaller the objective function value is, the higher the correlation coefficient of the three parameters is not necessarily, and the higher the correlation coefficient of the three parameters is, the smaller the objective function value is also not necessarily, and a solution with relatively small objective function value and relatively high correlation coefficient is expected. In the pre-stack AVO elastic parameter inversion problem, there are three elastic parameters and one objective function, so there are four evaluation indexes. The above clustering algorithm is used for continuously iterating operation, a plurality of local optimal solutions and global optimal solutions are obtained through the objective function, and the solutions are further selected through the correlation coefficients of the three elastic parameters.

A multi-index selection method is used here to determine which of the final solutions is, one for each correlation coefficient.

For the multi-index problem, the weight of each index needs to be obtained first, where the weight of the index is determined by using the method of mean square error, and the method is as follows in steps 1 to 3:

Step 1, calculating each index Y _j Is shown in the following formula 2:

step 2, calculating an index Y _j Is shown in the following equation 3:

step 3, determining an index Y _j Is shown in the following formula 4:

and obtaining the weight of each correlation coefficient according to the method, and finally selecting the maximum scoring solution as the inversion result (namely the target individual) according to the calculation result.

The problem of solving the pre-stack AVO elastic parameter inversion by using a multi-mode optimization algorithm is increased along with the increase of the dimension, and the following distributed computing framework is proposed.

The multi-mode optimization algorithm takes a population as a unit, in the continuous iterative optimization process, the population is continuously divided into different search areas according to the algorithm, and once for each iteration, the population is divided again, and only one CDP angle gather is involved in one-dimensional condition, so that the distributed framework in one-dimensional condition is shown in figure 5.

Under the one-dimensional condition, the algorithm operation node (namely the second node) performs algorithm operation, namely clustering operation and the like, and then the divided sub-populations are distributed into the sub-population nodes (namely the first node), wherein the sub-population nodes are mainly responsible for calculating the fitness value. And after the sub-population nodes finish calculation, returning the fitness value to the algorithm operation node, and repeating the steps until the termination condition of the algorithm is met.

Two-dimensional pre-stack AVO elastic parameter inversion requires inversion of a subsurface parameter profile for an entire plane, and involves multiple CDP angle gathers, requiring a large number of one-dimensional operations, three-dimensional inversion of subsurface distribution for an entire region from surface and volume on a two-dimensional basis. Both two-dimensional and three-dimensional are one-dimensional computing operations of a plurality of CDP angle gathers, the three-dimensional situation is just larger than the two-dimensional data volume, the two-dimensional and three-dimensional distributed frames are the same as the two-dimensional frames on the frame, and the two-dimensional and three-dimensional distributed frames are shown in figure 6.

The allocation angle gather node is responsible for allocating CDP angle gathers and for the algorithmic operation of a portion of the CDP angle gathers. The computing nodes are divided into two types, one is a node for computing fitness values, and the other is a node for processing distributed CDP angle gather data and executing a multimode optimization algorithm. The specific calculation flow is as follows in step 1 to step 4:

and step 1, reading actual seismic data and logging data.

Step 2, the distribution angle gather node firstly divides the obtained multiple CDP angle gather data (namely geological data sets), and downloads the data to a node (namely a second node) executing a multimode optimization algorithm, and reserves a part of CDP angle gather data to carry out multimode optimization operation.

And 3, after the CDP angle gather data are distributed, the node performs multimode optimization calculation on each CDP angle gather data, and the divided sub-population data are transmitted to the node (namely the first node) for calculating the fitness value.

And 4, after each node calculates the fitness value of each sub-population, transferring the data into the node of the upper-layer incoming data to perform multimode optimization algorithm operation, and repeating the operation until all CDP angle gather data are completely calculated.

In the embodiment of the application, a parallel computing framework for inversion of pre-stack seismic AVO elastic parameters is provided; the multi-mode optimization method of the nearest optimal cluster based on Euclidean distance is used for solving the problem of multi-solution of inversion of the AVO elastic parameters of the pre-stack earthquake, and a plurality of local optimal solutions and global optimal solutions are obtained; and a specific solution selection criterion is proposed for a plurality of locally optimal and globally optimal solutions of the inverse performance.

In the embodiment of the application, on one hand, the parallel technology is used for accelerating inversion of the pre-stack seismic AVO elastic parameters. The intelligent optimization algorithm is often an iterative algorithm, the calculation of gene operation and fitness is realized through iteration, in one-dimensional case, such iterative consumption events are acceptable, but if the problem rises to two dimensions or three dimensions, the calculation of hundreds of CDP angle gathers is involved, and if the calculation is also performed in an iterative mode, the time consumption is huge and unacceptable; the use of parallelization techniques can significantly reduce computation time, although it can be time consuming, but has significantly improved over iterative computation. On the other hand, the inversion of the elastic parameters of the pre-stack earthquake AVO is solved by using a multimode optimization technology. In the prior solving process, a theoretical global optimal solution is often obtained, and the solution is not necessarily the global optimal solution due to various reasons such as algorithm performance, and the problem is a multi-solvability problem, a plurality of global optimal solutions exist, and further result judgment is facilitated by finding out all the global and local optimal solutions; in addition, the solutions may not have large difference in fitness value, but the forward curve can not be well fitted, so the solution is selected by a multi-attribute selection method in combination with the correlation coefficient, and the obtained solution is more convincing than the solution obtained by the prior method.

Based on the foregoing embodiments, the embodiments of the present application provide a data processing apparatus, where the apparatus includes each module included, and each unit included in each module may be implemented by a processor; of course, the method can also be realized by a specific logic circuit; in an implementation, the processor may be a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.

Fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application, as shown in fig. 7, where, the apparatus 700 includes a determining module 701, a sending module 702, and a receiving module 703, where: a determining module 701, configured to determine a first fitness of each individual in the first geological dataset to which each individual belongs; wherein the first set of geological data includes at least one individual measurement parameter; a sending module 702, configured to send the first geological data set to a second node, so that the second node performs optimization on the first geological data set to obtain a first subset of the first geological data set; the determining module 701 is further configured to determine, while waiting for the second node to return to the first subset, a second fitness of each individual in the second geological dataset to which the second node belongs; wherein the second geological data set is a next geological data set to the first geological data set; the determining module 701 is further configured to determine a third fitness of each individual in the received first subset; the sending module 702 is further configured to send the third fitness to the second node, so that the second node performs optimization processing on the first geological dataset again until the number of optimization processing times meets a first convergence condition, and inversion of the first geological dataset is completed.

In some embodiments, the receiving module 703 is further configured to receive a second subset returned by the second node; wherein the second subset is obtained by carrying out optimization processing on the first subset of the first geological data set again by the second node; the determining module 701 is configured to determine, while waiting for the second node to return to the second subset, a fourth fitness of each individual in the third geological dataset to which the second node belongs if the third subset returned by the second node is not received; wherein the third subset is obtained by optimizing the second geological data set by the second node; the third geological data set is a next geological data set to the second geological data set; and if the third subset returned by the second node is received, determining a fifth fitness of each body in the third subset to which each body belongs, so as to complete inversion of the second geological data set through the second node based on the fifth fitness.

Fig. 8 is a schematic structural diagram of another data processing apparatus according to an embodiment of the present application, as shown in fig. 8, the apparatus 800 includes a receiving module 801, a processing module 802, a sending module 803, and a selecting module 804, where: a receiving module 801, configured to receive a first fitness of each individual in a first geological data set to which the first node belongs and the first geological data set; wherein the geological dataset comprises at least one individual measurement parameter; a processing module 802, configured to perform optimization processing on the first geological data set according to a first fitness of each individual, so as to obtain a first subset of the first geological data set; a sending module 803, configured to send the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first subset belongs; the processing module 802 is further configured to, in waiting for the first node to return to the third fitness, perform optimization processing on the second geological data set according to a second fitness of each body returned by the first node in the second geological data set to which the first node belongs, so as to obtain a third subset of the second geological data set; the receiving module 801 is further configured to receive a third fitness of each individual in the first subset to which the first node returns; the processing module 802 is further configured to perform optimization processing on the first geological dataset again according to the third fitness until the number of optimization processing times meets a first convergence condition, and complete inversion of the first geological dataset.

In some embodiments, the processing module 802 is configured to perform optimization on the first geological data set again according to the third fitness to obtain a second subset of the first geological data set; the processing module 802 is further configured to continue performing optimization processing on the first geological data set again according to the fitness of the individuals of the subset of the first geological data set obtained by the kth-1 iteration, to obtain a fourth subset and corresponding candidate individuals; wherein k is the number of optimization processing times; the processing module 802 is configured to select a target individual that meets a first condition from a plurality of different candidate individuals, and take a measurement parameter corresponding to the target individual as a target inversion parameter of the first geological dataset, so as to complete inversion of the first geological dataset.

In some embodiments, the data processing apparatus includes a determining module and a dividing module, where the determining module is configured to determine, according to measurement parameters of individuals in the first geological dataset, a distance between each individual and other individuals, to obtain a first distance; dividing the first geological data set according to each first distance to obtain a first subset of the first geological data set; the dividing module is used for determining candidate individuals in each first subset according to the first fitness of the individuals in the first subset.

In some embodiments, the data processing apparatus further includes a ranking module, configured to rank a first fitness of each individual in the first geological data set, to obtain a ranked first geological data set; the determining module is further configured to determine a distance between each individual and other individuals according to the measurement parameters of the individuals in the first geological dataset after sorting, so as to obtain a first distance.

In some embodiments, the data processing apparatus further comprises a search module and a connection module, the search module configured to search for an individual whose first distance from the i+1st individual of the ordered first geological dataset satisfies a first condition from the last individual; the connection module is used for establishing connection between the ith individual and the corresponding individual meeting the first condition; until connection establishment of each individual in the first geological data set after the sorting and the corresponding individual meeting the condition is sequentially traversed; wherein i is greater than 0 and less than or equal to the total number of individuals of the first geological data set; the first fitness of the (i+1) th individual is greater than the first fitness of the (i) th individual; the first condition is that the distance is nearest or less than a first threshold; disconnecting the connection with the connected individual if the first distance between the ith individual and the connected individual is greater than a second threshold; and until the judgment of whether the first distance between each individual in the first geological data set after the sorting and the connected individual is larger than a second threshold value is traversed, taking the connected individuals as a first subset.

In some embodiments, the processing module 802 is further configured to re-perform optimization processing on the first geological data set according to the fitness of the individuals of the subset of the first geological data set obtained in the k-1 th iteration, to obtain a fourth subset and a corresponding good individual; wherein k is the total number of optimization processing times; and the determining module is used for determining the candidate individuals of the subset of the first geological data set obtained by the k-1 th iteration and the individuals with the fitness meeting the second condition in the excellent individuals of the fourth subset as the candidate individuals of the fourth subset.

The description of the apparatus embodiments above is similar to that of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

It should be noted that, in the embodiments of the present application, the division of modules by the data processing apparatus shown in fig. 7 and fig. 8 is schematic, and is merely a logic function division, and there may be another division manner in actual implementation. In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. Or in a combination of software and hardware.

It should be noted that, in the embodiment of the present application, if the method is implemented in the form of a software functional module, and sold or used as a separate product, the method may also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or part contributing to the related art, and the computer software product may be stored in a storage medium, including several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.

An embodiment of the present application provides an electronic device, fig. 9 is a schematic diagram of hardware entities of the electronic device in the embodiment of the present application, as shown in fig. 9, where the electronic device 900 includes a memory 901 and a processor 902, where the memory 901 stores a computer program that can be run on the processor 902, and the processor 902 implements steps in the method provided in the embodiment described above when executing the program.

It should be noted that the memory 901 is configured to store instructions and applications executable by the processor 902, and may also cache data (for example, image data, audio data, voice communication data, and video communication data) to be processed or already processed by each module in the processor 902 and the electronic device 900, which may be implemented by a FLASH memory (FLASH) or a random access memory (Random Access Memory, RAM).

The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method provided in the above embodiment.

The present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the steps of the method provided by the method embodiments described above.

It should be noted here that: the description of the storage medium and apparatus embodiments above is similar to that of the method embodiments described above, with similar benefits as the method embodiments. For technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in some embodiments" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application. The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments. The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.

The term "and/or" is herein merely an association relation describing associated objects, meaning that there may be three relations, e.g. object a and/or object B, may represent: there are three cases where object a alone exists, object a and object B together, and object B alone exists.

It should be noted that, in this document, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments are merely illustrative, and the division of the modules is merely a logical function division, and other divisions may be implemented in practice, such as: multiple modules or components may be combined, or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or modules, whether electrically, mechanically, or otherwise.

The modules described above as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules; can be located in one place or distributed to a plurality of network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated in one processing unit, or each module may be separately used as one unit, or two or more modules may be integrated in one unit; the integrated modules may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read Only Memory (ROM), a magnetic disk or an optical disk, or the like, which can store program codes.

Alternatively, the integrated units described above may be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or part contributing to the related art, and the computer software product may be stored in a storage medium, including several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.

The methods disclosed in the several method embodiments provided in the present application may be arbitrarily combined without collision to obtain a new method embodiment.

The features disclosed in the several product embodiments provided in the present application may be combined arbitrarily without conflict to obtain new product embodiments.

The features disclosed in the several method or apparatus embodiments provided in the present application may be arbitrarily combined without conflict to obtain new method embodiments or apparatus embodiments.

The foregoing is merely an embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A data processing method, wherein the method is applied to a first node of a first electronic device, comprising:

determining a first fitness of each individual in the first geological dataset to which it belongs; wherein the first set of geological data includes at least one individual measurement parameter;

transmitting the first geological data set to a second node of second electronic equipment, so that the second node optimizes the first geological data set to obtain a first subset of the first geological data set; and

determining a second fitness of each individual in a second geological dataset to which the second node belongs while waiting for the second node to return to the first subset; wherein the second geological data set is a next geological data set to the first geological data set;

Determining a third fitness for each individual in the first subset received;

and sending the third fitness to the second node so that the second node carries out optimization processing on the first geological data set again until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

2. The method of claim 1, wherein after said transmitting said third fitness to said second node, said method further comprises:

receiving a second subset returned by the second node; wherein the second subset is obtained by carrying out optimization processing on the first subset of the first geological data set again by the second node;

wherein, in the process of waiting for the second node to return to the second subset, if a third subset returned by the second node is not received, determining a fourth fitness of each individual in a third geological data set to which the second node belongs; wherein the third subset is obtained by optimizing the second geological data set by the second node; the third geological data set is a next geological data set to the second geological data set;

And if the third subset returned by the second node is received, determining a fifth fitness of each body in the third subset to which each body belongs, so as to complete inversion of the second geological data set through the second node based on the fifth fitness.

3. A data processing method, wherein the method is applied to a second node of a second electronic device, comprising:

receiving a first fitness of each individual in a first geological data set which the first node of first electronic equipment belongs to and the first geological data set; wherein the geological dataset comprises at least one individual measurement parameter;

optimizing the first geological data set according to the first fitness of each individual to obtain a first subset of the first geological data set;

transmitting the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first node belongs; and

in the process of waiting for the first node to return to the third fitness, performing optimization processing on a second geological data set to obtain a third subset of the second geological data set;

Receiving a third fitness of each individual in the first subset to which the first node returns;

and carrying out optimization processing on the first geological data set again according to the third fitness until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

4. A method according to claim 3, wherein said re-optimizing the first geological data set according to the third fitness until the number of optimizations satisfies a first convergence condition, and completing inversion of the first geological data set, comprises:

carrying out optimization processing on the first geological data set again according to the third fitness to obtain a second subset of the first geological data set;

continuing to optimize the first geological data set according to the individual fitness of the subset of the first geological data set obtained by the k-1 th iteration, and obtaining a fourth subset and corresponding candidate individuals; wherein k is the total number of optimization processing times;

selecting a target individual meeting a first condition from a plurality of different candidate individuals, taking a measurement parameter corresponding to the target individual as a target inversion parameter of the first geological data set, and completing inversion of the first geological data set.

5. The method of claim 4, wherein optimizing the first geological dataset according to the first fitness of each individual results in a first subset of the first geological dataset, comprising:

determining the distance between each individual and other individuals according to the measurement parameters of the individuals in the first geological data set to obtain a first distance;

and dividing the first geological data set according to each first distance to obtain a first subset of the first geological data set.

6. The method of claim 5, wherein determining the distance between each individual and the other individuals based on the measured parameters of the individuals in the first set of geological data, resulting in a first distance, comprises:

sorting the first fitness of each individual in the first geological data set to obtain a sorted first geological data set;

and determining the distance between each individual and other individuals according to the measurement parameters of the individuals in the sequenced first geological data set to obtain a first distance.

7. The method of claim 5, wherein dividing the first geological data set according to each of the first distances results in a first subset of the first geological data set, comprising:

Searching for an individual with a first distance from the (i+1) th individual to the last individual in the sorted first geological data set, wherein the first distance from the (i) th individual meets a first condition; establishing connection between the ith individual and the corresponding individual meeting the first condition; until connection establishment of each individual in the first geological data set after the sorting and the corresponding individual meeting the condition is sequentially traversed; wherein i is greater than 0 and less than or equal to the total number of individuals of the first geological data set; the first fitness of the (i+1) th individual is greater than the first fitness of the (i) th individual; the first condition is that the distance is nearest or less than a first threshold;

disconnecting the connection with the connected individual if the first distance between the ith individual and the connected individual is greater than a second threshold;

and until the judgment of whether the first distance between each individual in the first geological data set after the sorting and the connected individual is larger than a second threshold value is traversed, taking the connected individuals as a first subset.

8. The method of claim 4, wherein the re-optimizing the first geological dataset according to the fitness of the individuals of the subset of the first geological dataset obtained in the k-1 th iteration to obtain a fourth subset and corresponding candidate individuals comprises:

According to the individual fitness of the subset of the first geological data set obtained by the k-1 th iteration, carrying out optimization processing on the first geological data set again to obtain a fourth subset and a corresponding excellent individual; wherein k is the total number of optimization processing times;

and determining the candidate individuals of the subset of the first geological data set obtained by the k-1 th iteration and the individuals with the fitness meeting the second condition in the excellent individuals of the fourth subset as the candidate individuals of the fourth subset.

9. A data processing apparatus, comprising:

a determining module for determining a first fitness of each individual in a first geological data set to which each individual belongs; wherein the first set of geological data includes at least one individual measurement parameter;

the sending module is used for sending the first geological data set to a second node so that the second node can optimize the first geological data set to obtain a first subset of the first geological data set;

the determining module is further used for determining a second fitness of each individual in a second geological data set to which the second node belongs in the process of waiting for the second node to return to the first subset; wherein the second geological data set is a next geological data set to the first geological data set;

The determining module is further configured to determine a third fitness of each individual in the received first subset;

the sending module is further configured to send the third fitness to the second node, so that the second node performs optimization processing on the first geological data set again until the optimization processing times meet a first convergence condition, and inversion of the first geological data set is completed.

10. A data processing apparatus, comprising:

the receiving module is used for receiving the first fitness of each body in the first geological data set and the first geological data set which are transmitted by the first node; wherein the geological dataset comprises at least one individual measurement parameter;

the processing module is used for carrying out optimization processing on the first geological data sets according to the first fitness of each individual to obtain a first subset of the first geological data sets;

a sending module, configured to send the first subset to the first node, so that the first node determines a third fitness of each individual in the first subset to which the first node belongs;

the processing module is further configured to perform optimization processing on a second geological data set in a process of waiting for the first node to return to the third fitness, so as to obtain a third subset of the second geological data set;

The receiving module is further configured to receive a third fitness of each individual in the first subset to which the first node returns;

and the processing module is further used for carrying out optimization processing on the first geological data set again according to the third adaptability until the optimization processing times meet a first convergence condition, and completing inversion of the first geological data set.

11. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, wherein the processor implements the method of any one of claims 1 to 8 when the program is executed.

12. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any one of claims 1 to 8.