CN114089415B

CN114089415B - Knowledge graph generation method and device based on seismic data processing

Info

Publication number: CN114089415B
Application number: CN202010771382.3A
Authority: CN
Inventors: 首皓; 曹宏; 崔栋; 曾同生
Original assignee: Petrochina Co Ltd
Current assignee: Petrochina Co Ltd
Priority date: 2020-08-04
Filing date: 2020-08-04
Publication date: 2023-11-28
Anticipated expiration: 2040-08-04
Also published as: CN114089415A

Abstract

The invention provides a knowledge graph generation method and device based on seismic data processing, wherein the method comprises the following steps: acquiring a first characteristic attribute of the seismic data of the target work area; acquiring sub-feature attributes corresponding to the first feature attributes according to the first feature attributes; and generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data. According to the method and the device, the targeted seismic data processing knowledge graph can be obtained in the seismic data processing process. Further obtaining deep processing associated information of the seismic data of the same type; and the information related to the annual treatment can be classified and stored through the knowledge graph so as to inquire when the information is treated again.

Description

Knowledge graph generation method and device based on seismic data processing

Technical Field

The invention relates to the technical field of petroleum exploration, in particular to the technical field of seismic data processing, and specifically relates to a knowledge graph generation method and device based on seismic data processing.

Background

In the prior art, different types of data have corresponding targeted processing measures in the seismic data processing, but because the types of the seismic data are greatly different, characteristic analysis is required to be carried out on the seismic data before each processing, and the targeted processing measures are formulated according to the data characteristics. When the same data is processed for the second time, if the change occurs to the processing personnel, the data analysis needs to be carried out again; re-performing the data analysis even if the processed data features are similar to the data features of the neighboring locations; the same data has larger difference because the processor understands that the analysis results of the data obtained differently are also different, and the processing results are different; the above problems are caused by the lack of a seismic data processing-related information query approach.

In addition, the main methods adopted by the current processing personnel in order to obtain the related information of the processed seismic data as soon as possible are consulting the report of the next processing or the acquisition report, however, the content of the data is single, which generally reflects that the personal understanding of the processing personnel in the processing process and the fact are inevitably deviated to a certain extent, and meanwhile, the written report is inevitably limited by the processing level of the processing personnel, and the written report is inevitably erroneous or misunderstood, so that the value of the report itself can be influenced to a certain extent, and therefore, a query method for obtaining the information related to the seismic data processing through the seismic data characteristics is urgently needed.

Disclosure of Invention

Aiming at the problems in the prior art, the invention provides a knowledge graph generation method, a device, electronic equipment and a storage medium based on seismic data processing, which can acquire a targeted seismic data processing knowledge graph in the seismic data processing process. Further obtaining deep processing associated information of the seismic data of the same type; and the information related to the annual treatment can be classified and stored through the knowledge graph so as to inquire when the information is treated again.

In order to achieve the above purpose, the present invention adopts the following technical scheme:

In a first aspect, a knowledge graph generation method based on seismic data processing is provided, including:

acquiring a first characteristic attribute of the seismic data of the target work area;

acquiring sub-feature attributes corresponding to the first feature attributes according to the first feature attributes;

and generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data.

Further, the first characteristic attribute includes: at least one of acquisition parameters, acquisition instrumentation, surface conditions, and subsurface formations;

the sub-feature attributes of the acquisition parameters include: at least one of acquisition unit, spatial position, offset range, azimuth range, recording time, coverage times, detector combination mode, excitation energy, observation system setting mode, excitation depth and detector burial depth;

the sub-feature attributes of the acquisition instrument include: at least one of a source type and a detector type;

the sub-feature attributes of the surface condition include: at least one of surface lithology, surface elevation value, surface elevation change range;

the sub-feature attributes of the subsurface formation include: at least one of a formation type, a fracture type, and a reservoir type.

Further, the acquiring the first characteristic attribute of the seismic data of the target work area includes:

constructing a seismic data characteristic analysis model according to a feedforward machine learning algorithm;

inputting the seismic data to the seismic data feature analysis model to acquire the type of interference waves and/or the positions of the interference waves in the seismic data;

the first characteristic attribute is extracted from text data, the type of interference wave and/or the position of the interference wave in the pre-acquired seismic data.

Further, the step of obtaining the text data includes the steps of:

extracting first text data from the seismic data acquisition report;

extracting second text data from the analysis report of the seismic data; the text data includes at least one of the first text data and the second text data.

Further, the extracting the first characteristic attribute from text data, a type of interference wave and/or a position of the interference wave in the pre-acquired seismic data includes:

dividing the text data into word groups;

screening the phrase to generate keywords of the seismic data;

and matching the keywords according to preset conditions to determine the first characteristic attribute.

Further, the obtaining the sub-feature attribute corresponding to the first feature attribute according to the first feature attribute includes:

and matching the sub-feature attributes according to the keywords and the first feature attributes to determine the sub-feature attributes.

Further, the generating a knowledge graph according to the first feature attribute, the sub-feature attribute and the seismic data includes:

matching the first characteristic attribute to determine an interrelated label of the first characteristic attribute;

matching the sub-feature attributes to determine interrelated labels of the sub-feature attributes;

simultaneously matching the first characteristic attribute and the sub-characteristic attribute to determine a common correlation tag;

matching the interrelated labels of the sub-feature attributes to determine common interrelated labels of the same sub-feature attributes;

and carrying out the same merging operation on the interrelated label of the first characteristic attribute, the interrelated label of the sub-characteristic attribute, the common interrelated label and the common interrelated label of the same sub-characteristic attribute so as to generate the knowledge graph.

In a second aspect, there is provided a knowledge-graph generating apparatus based on seismic data processing, including:

the first attribute acquisition unit is used for acquiring a first characteristic attribute of the seismic data of the target work area;

the sub-attribute acquisition unit is used for acquiring sub-feature attributes corresponding to the first feature attributes according to the first feature attributes;

and the map generation unit is used for generating a knowledge map according to the first characteristic attribute, the sub-characteristic attribute and the seismic data.

Further, the first attribute obtaining unit includes:

the model building module is used for building a seismic data characteristic analysis model according to a feedforward machine learning algorithm;

the interference wave acquisition module is used for inputting the seismic data into the seismic data characteristic analysis model so as to acquire the type of interference waves and/or the positions of the interference waves in the seismic data;

and the first attribute extraction module is used for extracting the first characteristic attribute from text data, the type of interference waves and/or the position of the interference waves in the pre-acquired seismic data.

Further, the knowledge graph generating device based on the seismic data processing further comprises: a text acquisition unit, configured to acquire the text data, the text acquisition unit including:

the first text extraction module is used for extracting first text data from the acquisition report of the seismic data;

the second text extraction module is used for extracting second text data from the analysis report of the seismic data; the text data includes at least one of the first text data and the second text data.

Further, the first attribute extraction module includes:

the character segmentation module is used for segmenting the character data into word groups;

the keyword screening module is used for screening the phrase to generate keywords of the seismic data;

and the first attribute determining module is used for matching the keywords according to preset conditions so as to determine the first characteristic attribute.

Further, the sub-attribute obtaining unit is specifically configured to match the sub-feature attribute according to the keyword and the first feature attribute, so as to determine the sub-feature attribute.

Further, the map generation unit includes:

the first attribute matching module is used for matching the first characteristic attribute to determine the interrelated label of the first characteristic attribute;

the sub-attribute matching module is used for matching the sub-feature attributes to determine the interrelated labels of the sub-feature attributes;

the simultaneous matching module is used for simultaneously matching the first characteristic attribute and the sub-characteristic attribute to determine common correlation labels;

the mutual tag matching module is used for matching the mutual associated tags of the sub-feature attributes so as to determine the common mutual associated tags of the same sub-feature attributes;

And the map generation module is used for carrying out the same merging operation on the interrelated label of the first characteristic attribute, the interrelated label of the sub-characteristic attribute, the common interrelated label and the common interrelated label of the same sub-characteristic attribute so as to generate the knowledge map.

In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the knowledge graph generation method based on seismic data processing described above when the program is executed by the processor.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the steps of the knowledge-graph generation method based on seismic data processing described above.

The embodiment of the invention provides a knowledge graph generation method, a device, electronic equipment and a storage medium based on seismic data processing, wherein the method comprises the following steps: firstly, acquiring a first characteristic attribute of seismic data of a target work area; then, sub-feature attributes corresponding to the first feature attributes are obtained according to the first feature attributes; and finally, generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data. According to the method and the device, the targeted seismic data processing knowledge graph can be obtained in the seismic data processing process.

The foregoing and other objects, features and advantages of the application will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:

FIG. 1 is a schematic flow chart of a knowledge graph generation method based on seismic data processing according to an embodiment of the application;

fig. 2 shows a specific step of step S100 in fig. 1;

FIG. 3 is a flow chart of a method for obtaining text data according to an embodiment of the application;

fig. 4 is a schematic flow chart of step S103 in the embodiment of the present application;

fig. 5 shows a specific step of step S200 in fig. 1;

fig. 6 shows a specific step of step S300 in fig. 1;

FIG. 7 is a second flow chart of a knowledge graph generation method based on seismic data processing in an embodiment of the application;

FIG. 8 is a flow chart of a method for multi-domain processing of seismic data based on machine learning in accordance with an embodiment of the application;

fig. 9 is a schematic structural diagram of a knowledge-graph generating apparatus based on seismic data processing according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a first attribute acquiring unit in the embodiment of the present application;

FIG. 11 is a schematic diagram II of a knowledge-graph generating apparatus based on seismic data processing according to an embodiment of the present application;

FIG. 12 is a schematic diagram showing the structure of a Chinese character acquiring unit according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a first attribute extraction module according to an embodiment of the present application;

fig. 14 is a schematic structural view of a map generating unit in the embodiment of the present application;

fig. 15 is a block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

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

It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present application and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

The following problems exist in view of the prior art: when the same seismic data are processed for the second time, if the processing personnel change, the data analysis is needed to be carried out again; re-performing the data analysis even if the processed data features are similar to the data features of the neighboring locations; the same seismic data has a large difference in processing results because the processing personnel understand that the data analysis results obtained differently are also different. The embodiment of the application provides a knowledge graph generation method based on seismic data processing, which can obtain the processing information of the same type of seismic data through the seismic data processing knowledge graph; deep processing associated information of the same type of seismic data can be obtained through the seismic data processing knowledge graph; the information related to the past year processing can be classified and stored through the seismic data processing knowledge graph so as to inquire when the information is processed again.

As shown in fig. 1, the knowledge graph generation method based on the seismic data processing may include the following:

step S100: a first characteristic attribute of the seismic data of the target work area is obtained.

The first characteristic attribute in step S100 specifically includes: one or more of acquisition parameters, acquisition instrumentation, surface conditions, subsurface formations.

Step S200: and obtaining the sub-feature attribute corresponding to the first feature attribute according to the first feature attribute.

The sub-feature attributes in step S200 specifically include:

sub-feature attributes of acquisition parameters: one or more of acquisition units, space positions, offset ranges, azimuth ranges, recording time, coverage times, a detector combination mode, excitation energy, an observation system setting mode, excitation depth and detector burial depth;

sub-feature attributes of the acquisition instrument: one or more of a source type and a detector type;

sub-feature attributes of surface conditions: one or more of surface lithology, surface elevation value and surface elevation change range;

sub-feature properties of subsurface formations: one or more of a formation type, a fracture type, and a reservoir type.

Step S300: and generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data.

It can be understood that the knowledge graph is a modern theory that combines the theory and method of subjects such as application mathematics, graphics, information visualization technology, information science and the like with the methods of metering introduction analysis, co-occurrence analysis and the like, and utilizes the visualized graph to visually display the core structure, development history, leading edge field and overall knowledge architecture of subjects to achieve the goal of multi-subject fusion. The complex knowledge field is displayed through data mining, information processing, knowledge metering and graphic drawing, the dynamic development rule of the knowledge field is revealed, and a practical and valuable reference is provided for discipline research. The knowledge graph can find the most desirable information, provide the most comprehensive abstract and enable the search to have more depth and breadth, and the seismic data can be searched more pertinently through the knowledge graph generated in the step S300.

The invention can obtain the processing information of the seismic data of the same type through the technical scheme; deep processing associated information of the same type of seismic data can be obtained through the seismic data processing knowledge graph; the information related to the past year processing can be classified and stored through the seismic data processing knowledge graph so as to inquire when the information is processed again.

In an alternative embodiment, the first characteristic attribute includes: at least one of acquisition parameters, acquisition instrumentation, surface conditions, and subsurface formations;

In an alternative embodiment, referring to fig. 2, step S100 further includes:

step S101: constructing a seismic data characteristic analysis model according to a feedforward machine learning algorithm;

it can be appreciated that the seismic data profiling model is a feed-forward machine learning model; it will be appreciated that the goal of the feed forward machine learning model is to approximate a certain function. For example, for a classifier, y=f×x (x) maps an input x to one class y. The feed forward network defines a mapping y=f (x; θ) and learns the value of the parameter θ so that it can get the best function approximation. Within the feedforward neural network, parameters propagate unidirectionally from an input layer to an output layer, and in general, the feedforward deep learning network comprises a convolution layer, a pooling layer and a full-connection layer.

Step S102: inputting the seismic data to the seismic data feature analysis model to acquire the type of interference waves and/or the positions of the interference waves in the seismic data;

the seismic data feature analysis model is configured to obtain corresponding feature analysis results from the input seismic data; the corresponding feature analysis results include: one or more of the type of the interference wave and the location information of the interference wave.

Step S103: the first characteristic attribute is extracted from text data, the type of interference wave and/or the position of the interference wave in the pre-acquired seismic data.

In an alternative embodiment, referring to fig. 3, the acquiring the text data includes the steps of:

step S701: extracting first text data from the seismic data acquisition report;

step S702: extracting second text data from the analysis report of the seismic data; the text data includes at least one of the first text data and the second text data.

Specifically, text content extracted from the acquisition report; the text content summarized when the seismic data is analyzed by a processor; data feature literal description content obtained by a machine-learned seismic data feature analysis model; and extracting a first characteristic attribute from the text content and the data characteristic text description content.

In an alternative embodiment, referring to fig. 4, step S103 further includes:

step S1031: dividing the text data into word groups;

step S1032: screening the phrase to generate keywords of the seismic data;

step S1033: and matching the keywords according to preset conditions to determine the first characteristic attribute.

In step S1031 to step S1033, specifically, the seismic data related text information is divided into phrases; screening the split phrases, and reserving the phrases related to the seismic data as keywords of the seismic data; matching the seismic data keywords according to a preset first characteristic classification, and taking the matched classification result as a first characteristic attribute of the seismic data; in addition, the unmatched results are retained as new seismic data first characteristic attributes.

In an alternative embodiment, referring to fig. 5, step S200 further includes:

step S201: and matching the sub-feature attributes according to the keywords and the first feature attributes to determine the sub-feature attributes.

Specifically, matching the seismic data keywords with sub-feature attributes under the corresponding classification of the first feature attributes; further using the matched result as the seismic data sub-feature attribute; in addition, the unmatched result is used as a new sub-feature attribute.

In an alternative embodiment, referring to fig. 6, step S300 further includes:

step S301: and matching the first characteristic attribute to determine the interrelated label of the first characteristic attribute.

Specifically, the same first characteristic attribute pre-associated labels are obtained by matching the first characteristic attributes of the seismic data.

Step S302: and matching the sub-feature attributes to determine the interrelated labels of the sub-feature attributes.

Specifically, the same sub-feature attribute pre-correlated labels are obtained by matching sub-feature attributes of the seismic data.

Step S303: and simultaneously matching the first characteristic attribute and the sub-characteristic attribute to determine a common correlation label.

Specifically, the first characteristic attribute and the sub-characteristic attribute of the seismic data are matched simultaneously to obtain the first characteristic attribute and the sub-characteristic attribute and simultaneously correlate the labels in advance.

Step S304: matching the correlated labels of the sub-feature attributes to determine the common correlated labels of the same sub-feature attributes.

Specifically, the sub-feature attributes are pre-associated with the tags to match the first feature attributes and the sub-feature attributes which obtain the same sub-feature attributes, and the tags are pre-associated with each other.

Step S305: and carrying out the same merging operation on the interrelated label of the first characteristic attribute, the interrelated label of the sub-characteristic attribute, the common interrelated label and the common interrelated label of the same sub-characteristic attribute so as to generate the knowledge graph.

Specifically, the same tags in step S301 to step S304 are combined; and presenting the obtained label, association times and text content corresponding to the label as a knowledge graph to a user.

In an alternative embodiment, referring to fig. 7, the knowledge-graph generating method based on the seismic data processing further includes:

step S400: correlating the seismic data.

Specifically, obtaining the seismic data processing information corresponding to the first characteristic attribute and the sub-characteristic attribute of the existing seismic data processing text keyword includes: one or more items of data analysis results, processing units, processing software, processing flows and parameters, and information related to a machine learning seismic data processing model; establishing association of the same first characteristic attributes, and recording association times as first characteristic attribute pre-associating tags; the seismic data processing text corresponding to the first characteristic attribute is used as text content corresponding to the first characteristic attribute pre-associated label; establishing association of the same sub-feature attributes and recording association times as sub-feature attribute pre-association labels; the seismic data processing text corresponding to the sub-feature attribute is used as text content corresponding to the sub-feature attribute pre-associated label; establishing association between the first characteristic attribute and the sub-characteristic attribute which are the same at the same time, and recording association times as the first characteristic attribute and the sub-characteristic attribute and associating labels with each other in advance; and taking the seismic data processing text corresponding to the first characteristic attribute and the sub-characteristic attribute simultaneously as text contents corresponding to the first characteristic attribute and the sub-characteristic attribute simultaneously and mutually associating tags in advance.

To further explain the present embodiment, the present invention provides a specific application example of the knowledge-graph generation method based on seismic data processing, which specifically includes the following, see fig. 8.

In this specific application example, the seismic block to be processed is subjected to multiple acquisitions and multiple treatments of different treatment units, and after each seismic data acquisition and treatment, the treatment result is archived in the form of a text report, so that before the current seismic block to be processed is processed, the knowledge graph is used to obtain the relevant experience of the past acquisition and treatment process, and the following steps are adopted:

s1: extracting text content related to acquisition parameters, acquisition instruments, ground surface conditions and underground structures from text content in a text report of the past time.

Specifically, firstly, electronic documents, such as acquisition reports and acquisition design reports, related to the work area of the seismic data processed at this time are obtained through checking; then, text content is extracted from the electronic document, where the extracted text content includes: the text content extracted from the acquisition report, the text content summarized by a processor when analyzing the seismic data, and the data characteristic text description content obtained by a machine-learned seismic data characteristic analysis model.

The text content extracted from the electronic document comprises the following steps: the seismic data processing related electronic document is a text report related to the acquisition report and the processing report, if the title or the catalog is the acquisition report and the processing report, the related text content can be extracted as the extracted text content, and in addition, more data characteristic text description content is extracted through a machine learning seismic data characteristic analysis model.

Among the dominant types of interference waves in seismic data processing are: strong energy interference, linear interference, multiple interference, scattered interference, random interference.

The method comprises the following steps of: extracting the seismic data and manually calibrating the type of the interference wave of the seismic data, taking the seismic data and the manual calibration result as samples to carry out deep learning model training, wherein the trained model is a seismic data feature correlation analysis model, when the correlation feature keyword analysis result is obtained, sliding a time window on the seismic data, wherein the transverse and longitudinal widths of the time window are 1/3 of the transverse and longitudinal widths, and inputting the data in the time window into the seismic data feature correlation analysis model to obtain the correlation feature keyword analysis result.

And finally, extracting the first characteristic attribute of the seismic data after the text content is extracted from the electronic document and is divided into phrases. Specifically, the method comprises the following steps: the segmentation of phrases is performed by means of common seismic data acquisition and processing keywords taken from entries in a related professional dictionary, for example: the Chinese petroleum exploration and development encyclopedia takes 'seismic acquisition' and 'seismic processing' as entries. The segmented phrase is further screened, the phrase related to the seismic data is reserved as a keyword of the seismic data, for example, the keyword is input into a search engine or petroleum encyclopedia, and the segmented phrase which is not completely matched is omitted.

And matching the seismic data keywords according to a preset first feature classification, taking the matched classification result as a first feature attribute of the seismic data, and reserving the unmatched result as a new first feature attribute of the seismic data, wherein the preset first feature classification comprises one or more of acquisition parameters, acquisition instruments, surface conditions and underground structures. For example, when the keyword "orthogonal observation system" is classified, the search engine or the petroleum encyclopedia searches for a result that neither the "orthogonal observation system" + "acquisition parameter" nor the "orthogonal observation system" + "ground surface condition" has a perfect match, the orthogonal observation system is newly added as the first feature classification, and when the keyword "non-vertical offset distance" is classified, the "non-vertical offset distance" + "orthogonal observation system" has a matching content, the "non-vertical offset distance" belongs to the "orthogonal observation system" classification, the classification result is irrelevant to the input sequence, even if the result is the "orthogonal observation system" belongs to the "non-vertical offset distance" classification, the processor can understand the meaning, and the search content matching means that the search engine returns the result and simultaneously contains both contents.

S2: and (3) further extracting keywords of specific related features from the text contents related to the acquisition parameters, the acquisition instrument, the surface conditions and the underground structures extracted in the step (S1).

The sub-feature attribute corresponding to the first feature attribute of the seismic data refers to: sub-feature attributes of acquisition parameters: one or more of acquisition units, spatial positions, offset ranges, azimuth ranges, recording time, coverage times, detector combination modes, excitation energy, observation system setting modes, excitation depth and detector burial depth.

sub-feature properties of subsurface formations: one or more of a construction type, a fracture type, and a reservoir type;

specifically, the method comprises the following steps: and matching the seismic data keywords with the sub-feature attributes under the corresponding classification of the first feature attributes, and then further taking the matched result as the seismic data sub-feature attributes, and taking the seismic data sub-feature attributes as new sub-feature attributes if the keywords are not matched. For example, the keyword "gravel area" belongs to the first type of feature "surface condition", and is further subdivided, the keyword "gravel area" is searched by a search engine or petroleum encyclopedia according to "gravel area" + "surface lithology", "gravel area" + "surface elevation", and the search content is classified when the search content is completely matched, that is, the search content contains the two contents at the same time, and the gravel area belongs to the surface lithology sub-feature attribute. As another example, the keyword "beach" belongs to a first class of feature "surface conditions", but does not match an existing defined second feature condition, then the keyword "beach" becomes a new class of sub-feature attributes.

S3: and (2) extracting keywords of specific related features according to the step (S2), and establishing association with keywords related to seismic data processing so as to form a knowledge graph.

Firstly, establishing pre-correlation with the processing information of the seismic data, and specifically adopting the following steps: the method as in the first step obtains existing seismic data processing text, such as a seismic processing report. Obtaining keywords of the existing seismic data processing text; wherein the keywords are taken from entries in the relevant professional dictionary, for example: the term in the encyclopedia of China petroleum exploration and development takes 'seismic processing' as the content.

The first characteristic attribute and the sub-characteristic attribute of the existing seismic data processing text keyword are obtained as in the first step method, for example, the classification of the keyword 'residual static correction', the search engine or the petroleum encyclopedia is searched for 'residual static correction' + 'acquisition parameters' or 'residual static correction' + 'ground surface condition', and the keyword 'residual static correction' is classified as the first special diagnosis attribute of the 'ground surface condition' according to the result. Then, the second type of characteristic attribute of the keyword "residual static correction" under the "surface condition" first type of characteristic diagnosis attribute is classified, for example, the keyword "residual static correction" belongs to the "surface condition" of the first type of characteristic, and is further subdivided, the keyword "residual static correction" is searched through a search engine or a petroleum encyclopedia according to "residual static correction" + "surface lithology", "residual static correction" + "surface elevation", and the search content is completely matched, that is, the search content contains both contents, and the keyword "residual static correction" belongs to the "surface lithology" and the "surface elevation" two sub-characteristic attributes.

Obtaining seismic data processing classification information corresponding to a first characteristic attribute and a sub-characteristic attribute of an existing seismic data processing text keyword, wherein the seismic data processing classification information comprises: the data analysis result, the processing unit, the processing software, the processing flow and the parameters, and the machine learning seismic data processing model related information. For example: the method comprises the steps of searching a first characteristic attribute 'surface condition' and a sub-characteristic attribute 'surface elevation' of a keyword 'residual static correction' in a search engine or petroleum encyclopedia for 'surface condition' + 'processing software' or 'surface condition' + 'processing flow and parameter', classifying the first characteristic attribute 'surface condition' of the keyword 'residual static correction' as 'data analysis result' seismic data processing classification information according to a result, and classifying the sub-characteristic attribute 'surface elevation' of the keyword 'residual static correction' as 'processing flow and parameter' seismic data processing classification information according to the result.

Establishing association between keywords and processing information, firstly establishing association with the same first characteristic attribute and recording association times as a first characteristic attribute pre-association label; then, the seismic data processing text corresponding to the first characteristic attribute is used as text content corresponding to the first characteristic attribute pre-associated label; then, the same sub-feature attributes are associated and the association times are recorded as sub-feature attribute pre-association labels; then, the seismic data processing text corresponding to the sub-feature attribute is used as text content corresponding to the sub-feature attribute pre-associated label; then, establishing association between the first characteristic attribute and the sub-characteristic attribute which are the same at the same time, and recording association times as the first characteristic attribute and the sub-characteristic attribute and associating labels with each other in advance; and finally, the seismic data processing text corresponding to the first characteristic attribute and the sub-characteristic attribute is used as text content corresponding to the label which is simultaneously and mutually associated with the first characteristic attribute and the sub-characteristic attribute.

For example: the first characteristic attribute of the keyword 'residual static correction' is 'surface condition', the sub-characteristic attribute is 'ground surface elevation', and the seismic processing information classification is 'processing flow and parameter'. The first characteristic attribute of the keyword 'multiple attenuation' is 'surface condition', the sub-characteristic attribute is 'surface lithology', and the seismic processing information classification is 'processing flow and parameter'. The first characteristic attribute of the keyword 'velocity analysis' is 'surface condition', the sub-characteristic attribute is 'surface lithology', and the seismic processing information classification is 'processing flow and parameter'.

And the first characteristic attribute establishes association and records association times as a first characteristic attribute pre-associated label, wherein the first characteristic attribute is the key words of residual static correction, multiple attenuation and speed analysis corresponding to the ground surface condition, and the association times are recorded as 3.

And (3) establishing association of the same sub-feature attributes, recording association times as sub-feature attributes, and associating tags with each other in advance, wherein the association is established between the keyword multiple attenuation and speed analysis corresponding to the same sub-feature attribute 'surface lithology', and recording association times as 2.

And (3) taking the seismic data processing words corresponding to the sub-feature attributes as word contents corresponding to the sub-feature attributes and pre-associating tags with each other, wherein the key words "multiple attenuation", "speed analysis" corresponding to the sub-feature attributes "surface lithology" are used for associating the word contents of "multiple attenuation", "speed analysis" in the processing report with "surface lithology". And (3) the keyword 'residual static correction' corresponding to the sub-feature attribute 'ground surface elevation', and the text content of the 'residual static correction' in the processing report is associated with the 'ground surface elevation'.

And establishing association between the first characteristic attribute and the sub-characteristic attribute which are the same at the same time, recording association times as the first characteristic attribute and the sub-characteristic attribute, and simultaneously associating labels with each other in advance, wherein the key words of the first characteristic attribute of 'earth surface condition' and the sub-characteristic attribute of 'earth surface lithology' are 'multiple attenuation' and 'velocity analysis', and the association between the 'multiple attenuation' and the 'velocity analysis' is established, and recording association times as 2.

The seismic data processing text corresponding to the first characteristic attribute and the sub-characteristic attribute is used as text content corresponding to the first characteristic attribute and the sub-characteristic attribute and is associated with each other in advance, so that keywords of 'multiple attenuation' and 'velocity analysis' of 'surface lithology' of the first characteristic attribute and 'surface condition' of the sub-characteristic attribute are simultaneously associated, the 'multiple attenuation' and 'velocity analysis' are established, and text content of 'multiple attenuation' and 'velocity analysis' in the processing report is associated with 'surface condition' of the first characteristic attribute and 'surface lithology' of the sub-characteristic attribute.

And then obtaining seismic data processing information which is associated with each other in advance by the characteristic attribute to form a knowledge graph, and adopting the following steps: firstly, matching sub-feature attributes of seismic data to obtain the same sub-feature attribute pre-associated labels; then, the same first characteristic attribute pre-correlation labels are obtained through the first characteristic attribute matching of the seismic data; then, simultaneously matching the first characteristic attribute and the sub-characteristic attribute of the seismic data to obtain a first characteristic attribute and a sub-characteristic attribute which are simultaneously associated with the labels in advance; then, the sub-feature attributes are pre-associated with labels to obtain first feature attributes and sub-feature attributes of the same sub-feature attributes, and the labels are pre-associated with each other; then merging the same tags; and finally, the obtained label, association times and text content corresponding to the label are presented to a user as a knowledge graph.

For example, the first characteristic attribute of the keyword "residual static correction" is "surface condition", the sub-characteristic attribute is "ground elevation", and the seismic processing information classification is "processing flow and parameter". The first characteristic attribute of the keyword 'multiple attenuation' is 'surface condition', the sub-characteristic attribute is 'surface lithology', and the seismic processing information classification is 'processing flow and parameter'. The first characteristic attribute of the keyword 'velocity analysis' is 'surface condition', the sub-characteristic attribute is 'surface lithology', and the seismic processing information classification is 'processing flow and parameter'.

The same sub-feature attribute pre-associated labels are obtained through the matching of the sub-feature attributes of the seismic data, and then the associated labels of 'multiple attenuation' and 'speed analysis' are obtained when the sub-feature attribute keywords 'surface lithology' are searched. The "residual static correction" associated label is obtained when the sub-feature attribute keyword "surface elevation" is retrieved.

And (3) obtaining the same first characteristic attribute pre-associated labels by matching the first characteristic attributes of the seismic data, and obtaining residual static correction, multiple attenuation and speed analysis associated labels when the first characteristic attribute keywords are searched for.

The first characteristic attribute and the sub-characteristic attribute of the seismic data are matched simultaneously to obtain the first characteristic attribute and the sub-characteristic attribute and the labels are associated with each other in advance, and then the associated labels of multiple attenuation and speed analysis are obtained when the first characteristic attribute keyword 'surface condition' and the sub-characteristic attribute keyword 'surface lithology' are searched.

The sub-feature attribute is matched with each other to obtain a first feature attribute and a sub-feature attribute of the same sub-feature attribute, and the sub-feature attribute is simultaneously correlated with each other in advance, so that the sub-feature attribute keyword 'surface lithology' is searched to obtain a 'multiple attenuation' and 'speed analysis' correlation label.

Merging the same tags, if there is a completely consistent classification and tag; and presenting the obtained label, association times and text content corresponding to the label as a knowledge graph to a user, wherein the content presented to the user is as follows: the block surface condition related content 3 items, the surface lithology related content 2 items and the ground surface elevation related content 1 items are processed by multiple attenuation and speed analysis aiming at the surface lithology and the detailed content of related processing reports is presented, and the processing method aiming at the ground surface elevation is residual static correction and the content of related processing reports is imaged.

According to the knowledge graph generation method based on the seismic data processing, the accuracy and the comprehensiveness of the seismic data processing associated information query are improved by establishing the seismic data processing knowledge graph. Comprising the following steps: firstly, obtaining a first characteristic attribute of seismic data; then obtaining the seismic data sub-feature attribute from the first feature attribute; and finally, obtaining seismic data processing information which is associated with each other in advance according to the characteristic attribute to form a knowledge graph. The application can obtain the existing targeted seismic data processing knowledge graph from the seismic data in the seismic data processing process.

Based on the same inventive concept, the embodiment of the application also provides a knowledge graph generating device based on seismic data processing, which can be used for realizing the method described in the embodiment, as described in the following embodiment. Since the principle of the knowledge-graph generating device based on the seismic data processing to solve the problem is similar to that of the method, the implementation of the knowledge-graph generating device based on the seismic data processing can be referred to the implementation of the method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

As shown in fig. 9, the knowledge graph generating apparatus based on the seismic data processing specifically includes:

a first attribute acquiring unit 10 for acquiring a first characteristic attribute of the seismic data of the target work area;

a sub-attribute obtaining unit 20, configured to obtain a sub-feature attribute corresponding to the first feature attribute according to the first feature attribute;

and a map generating unit 30, configured to generate a knowledge map according to the first feature attribute, the sub-feature attribute, and the seismic data.

Further, referring to fig. 10, the first attribute acquiring unit 10 includes:

the model construction module 101 is used for constructing a seismic data characteristic analysis model according to a feedforward machine learning algorithm;

the interference wave acquisition module 102 is configured to input the seismic data to the seismic data feature analysis model to acquire a type of an interference wave and/or a position of the interference wave in the seismic data;

A first attribute extraction module 103, configured to extract the first feature attribute from text data, a type of interference wave and/or a position of the interference wave in the pre-acquired seismic data.

Further, referring to fig. 11, the knowledge-graph generating apparatus based on the seismic data processing further includes: a text obtaining unit 40 for obtaining the text data, referring to fig. 12, the text obtaining unit 40 includes:

a first text extraction module 401, configured to extract first text data from the seismic data acquisition report;

a second text extraction module 402 for extracting second text data from the analysis report of the seismic data; the text data includes at least one of the first text data and the second text data.

Further, referring to fig. 13, the first attribute extraction module 103 includes:

a word segmentation module 1031, configured to segment the word data into word groups;

a keyword screening module 1032, configured to screen the phrase to generate a keyword of the seismic data;

and a first attribute determining module 1033, configured to match the keywords according to a preset condition, so as to determine the first feature attribute.

Further, the sub-attribute obtaining unit 20 is specifically configured to match the sub-feature attribute according to the keyword and the first feature attribute, so as to determine the sub-feature attribute.

Further, referring to fig. 14, the map generation unit 30 includes:

a first attribute matching module 301, configured to match the first feature attribute to determine an interrelated label of the first feature attribute;

a sub-attribute matching module 302, configured to match the sub-feature attributes to determine interrelated labels of the sub-feature attributes;

a simultaneous matching module 303, configured to simultaneously match the first feature attribute and the sub-feature attribute to determine a common correlation tag;

a mutual tag matching module 304, configured to match the mutual associated tags of the sub-feature attributes to determine common mutual associated tags of the same sub-feature attributes;

the map generating module 305 is configured to perform the same merging operation on the correlated label of the first feature attribute, the correlated label of the sub-feature attribute, the common correlated label, and the common correlated label of the same sub-feature attribute, so as to generate the knowledge map.

The knowledge graph generation device based on seismic data processing firstly acquires first characteristic attributes of seismic data of a target work area; then, sub-feature attributes corresponding to the first feature attributes are obtained according to the first feature attributes; and finally, generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data. According to the method and the device, the targeted seismic data processing knowledge graph can be obtained in the seismic data processing process.

The apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

In a typical example the electronic device comprises in particular a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the steps of the above described knowledge graph generation method based on seismic data processing when said program is executed.

Referring now to fig. 15, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application is shown.

As shown in fig. 15, the electronic apparatus 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data required for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on drive 610 as needed, so that a computer program read therefrom is mounted as needed as storage section 608.

In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the knowledge-graph generation method described above based on seismic data processing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611.

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

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.

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

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

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

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

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. The knowledge graph generation method based on seismic data processing is characterized by comprising the following steps of:

generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data;

correlating the seismic data;

correlating the seismic data includes: obtaining the seismic data processing information corresponding to the first characteristic attribute and the sub-characteristic attribute of the existing seismic data processing text keywords comprises the following steps: one or more items of data analysis results, processing units, processing software, processing flows and parameters, and information related to a machine learning seismic data processing model; establishing association of the same first characteristic attributes, and recording association times as first characteristic attribute pre-associating tags; the seismic data processing text corresponding to the first characteristic attribute is used as text content corresponding to the first characteristic attribute pre-associated label; establishing association of the same sub-feature attributes and recording association times as sub-feature attribute pre-association labels; the seismic data processing text corresponding to the sub-feature attribute is used as text content corresponding to the sub-feature attribute pre-associated label; establishing association between the first characteristic attribute and the sub-characteristic attribute which are the same at the same time, and recording association times as the first characteristic attribute and the sub-characteristic attribute and associating labels with each other in advance; the seismic data processing text corresponding to the first characteristic attribute and the sub-characteristic attribute simultaneously serves as text content corresponding to the tag which is correlated with the first characteristic attribute and the sub-characteristic attribute simultaneously in advance;

The first characteristic attribute includes: at least one of acquisition parameters, acquisition instrumentation, surface conditions, and subsurface formations;

the sub-feature attributes of the subsurface formation include: at least one of a formation type, a fracture type, a reservoir type;

the acquiring the first characteristic attribute of the seismic data of the target work area comprises:

extracting the first characteristic attribute from character data, the type of interference waves and/or the position of the interference waves in the pre-acquired seismic data;

The generating a knowledge graph according to the first characteristic attribute, the sub-characteristic attribute and the seismic data includes:

2. The knowledge-graph generation method based on seismic data processing according to claim 1, wherein acquiring the text data comprises the steps of:

extracting first text data from the seismic data acquisition report;

3. The knowledge-graph generation method based on seismic data processing according to claim 1, wherein the extracting the first feature attribute from text data, a type of interference wave, and/or a position of the interference wave in the pre-acquired seismic data includes:

dividing the text data into word groups;

screening the phrase to generate keywords of the seismic data;

4. The knowledge-graph generation method based on seismic data processing according to claim 3, wherein the obtaining sub-feature attributes corresponding to the first feature attributes includes:

5. A knowledge graph generation device based on seismic data processing, comprising:

The map generation unit is used for generating a knowledge map according to the first characteristic attribute, the sub-characteristic attribute and the seismic data;

the data association module is used for associating the seismic data with each other;

the data association module is specifically configured to obtain seismic data processing information corresponding to a first feature attribute and a sub-feature attribute of an existing seismic data processing text keyword, where the seismic data processing information includes: one or more items of data analysis results, processing units, processing software, processing flows and parameters, and information related to a machine learning seismic data processing model; establishing association of the same first characteristic attributes, and recording association times as first characteristic attribute pre-associating tags; the seismic data processing text corresponding to the first characteristic attribute is used as text content corresponding to the first characteristic attribute pre-associated label; establishing association of the same sub-feature attributes and recording association times as sub-feature attribute pre-association labels; the seismic data processing text corresponding to the sub-feature attribute is used as text content corresponding to the sub-feature attribute pre-associated label; establishing association between the first characteristic attribute and the sub-characteristic attribute which are the same at the same time, and recording association times as the first characteristic attribute and the sub-characteristic attribute and associating labels with each other in advance; the seismic data processing text corresponding to the first characteristic attribute and the sub-characteristic attribute simultaneously serves as text content corresponding to the tag which is correlated with the first characteristic attribute and the sub-characteristic attribute simultaneously in advance;

the first attribute acquisition unit includes:

the first attribute extraction module is used for extracting the first characteristic attribute from character data, the type of interference waves and/or the position of the interference waves in the pre-acquired seismic data;

The map generation unit includes:

6. The knowledge-graph generation apparatus based on seismic data processing as recited in claim 5, further comprising: a text acquisition unit, configured to acquire the text data, the text acquisition unit including:

7. The knowledge-graph generation apparatus based on seismic data processing of claim 5, wherein the first attribute extraction module comprises:

8. The knowledge-graph generation apparatus based on seismic data processing according to claim 7, wherein the sub-attribute obtaining unit is specifically configured to match the sub-feature attribute according to the keyword and the first feature attribute to determine the sub-feature attribute.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the knowledge-graph generation method based on seismic data processing of any one of claims 1 to 4 when the program is executed by the processor.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the knowledge-graph generation method based on seismic data processing according to any one of claims 1 to 4.