Petroleum data structure design method and system based on business resource model

Abstract

The invention provides a data structure design method and system based on a business resource model, belongs to the field of petroleum data structure design, and is used for solving the problem of low petroleum data structure determination efficiency in related technologies. According to the method, the high-dimensional data space for expressing the petroleum data can be intelligently determined, then a petroleum data structure design scheme in which the high-dimensional data space is coupled with the actual data dimension and data expression of the petroleum data is determined, and a relatively reasonable petroleum data structure design scheme can be efficiently determined.

Description

Technical Field

[0001] The present application relates to the field of petroleum data structure design, and in particular to a data structure design method and system based on a business resource model. Background Art

[0002] Petroleum data structure design is a data management technology used in the petroleum industry. It involves how to effectively organize, store and manage large amounts of data related to petroleum exploration, mining, production, transportation and sales. In the petroleum industry, data structure design needs to take into account data from multiple aspects such as geology, geophysics, drilling, completion, production, economic evaluation, etc. to ensure the accuracy and consistency of the data while improving the efficiency of data processing and analysis. The design of the petroleum data structure needs to meet the needs of actual applications. In the existing design schemes, the relationship between different petroleum data is generally manually sorted out and refined, and then a reasonable petroleum data structure is determined. The method of manually sorting out and refining different petroleum data to determine the petroleum data structure is inefficient. Summary of the invention

[0003] The present application provides a petroleum data structure design method and system based on a business resource model, which is beneficial to improving the efficiency of petroleum data structure determination.

[0004] In a first aspect, the present application provides a method for designing a petroleum data structure based on a business resource model. The method comprises: Acquire a training data set of petroleum data, wherein the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data; Based on the business resource model, determining a petroleum data structure design scheme according to the training data set, the petroleum data structure design scheme comprising a high-dimensional vector expression of the petroleum data in a high-dimensional data space, the high-dimensional data space comprising space dimensions corresponding one-to-one to the data dimensions; The step of determining the petroleum data structure design scheme based on the business resource model and the training data set comprises: Based on the pre-acquired business resource model, determining a dimension unit value of each spatial dimension according to the training data set, wherein the dimension unit value is associated with an association relationship between a data dimension and a corresponding node in the business resource model; The dimension value of each dimensional expression corresponding to the spatial dimension is determined according to the training data, so that the correlation data between the training data conforms to the vector similarity of the corresponding high-dimensional vector expression.

[0005] By adopting the above technical scheme, only a business resource model and a training data set are needed to intelligently determine the petroleum data structure design scheme, and the petroleum data is determined by high-dimensional vector expression under the petroleum data structure design scheme. The vector similarity of the high-dimensional vector expression of petroleum data that is close in business logic and actual conditions is also high, thereby making the petroleum data structure design scheme more reasonable.

[0006] Furthermore, the business resource model includes nodes and dependencies and correlations between nodes; The determining of the dimension unit value of each spatial dimension according to the training data set based on the pre-acquired business resource model includes: Based on the training data set, determining a node corresponding to each data dimension in the business resource model as a dimension node; Determine the dimension correlation data between the corresponding dimension data according to the correlation relationship between every two dimension nodes in the business resource model; The dimension unit value of each spatial dimension is determined according to the dimension correlation data, so that the vector similarity between the dimension unit vectors conforms to the dimension correlation between the data dimensions.

[0007] Further, the step of determining the dimensional correlation data between the corresponding dimensional data according to the correlation relationship between each two dimensional nodes in the business resource model includes: for each two dimensional nodes, Determine a first dimension association component according to a direct relationship between two dimension nodes, wherein the first dimension association component is associated with whether there is a direct association relationship between the two dimension nodes; Determine a second dimension association component according to the same belonging relationship of the two dimension nodes, the second dimension association component is associated with whether the two dimension nodes depend on the same node, and if so, the second dimension association component is negatively correlated with the dependency level between the node on which the two dimension nodes depend and the two dimension nodes; Determine the third dimension correlation component according to the indirect relationship between the two dimension nodes, the third dimension correlation component is related to whether there is a direct correlation relationship between the nodes that the two dimension nodes depend on, if so, the third dimension correlation component is positively correlated to the number of direct correlation relationships between the nodes that the two dimension nodes depend on, and negatively correlated to the dependency level between the nodes that the two dimension nodes depend on and the two dimension nodes; The dimension association data is determined according to the first dimension association component, the second dimension association component and the third dimension association component.

[0008] Further, determining the second dimension associated component according to the same belonging relationship of two dimension nodes includes: for every two dimension nodes, If two dimension nodes depend on the same node, the lowest node on which the two dimension nodes depend is determined as the lowest dependent node; Determine the dependency levels between the two dimension nodes and the lowest dependent node respectively; The second dimension component is calculated according to the dependency level between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels.

[0009] Further, determining the third dimension association component according to the indirect relationship between the two dimension nodes includes: for every two dimension nodes, Let A and B represent two dimension nodes respectively. Suppose there are n sets of direct associations between the nodes that dimension nodes A and B depend on. Suppose the dependency level between the node to which A belongs and A in the i-th set of direct associations is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

[0010] In a second aspect, the present application provides a petroleum data structure design system based on a business resource model. The system includes a data acquisition module and a solution determination module; The data acquisition module is used to acquire a training data set of petroleum data, wherein the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data; The scheme determination module is used to determine a petroleum data structure design scheme based on the business resource model and the training data set, wherein the petroleum data structure design scheme includes a high-dimensional vector expression of the petroleum data in a high-dimensional data space, wherein the high-dimensional data space includes space dimensions corresponding to the data dimensions one by one; The solution determination module is further configured to: Based on the pre-acquired business resource model, determining a dimension unit value of each spatial dimension according to the training data set, wherein the dimension unit value is associated with an association relationship between a data dimension and a corresponding node in the business resource model; The dimension value of each dimensional expression corresponding to the spatial dimension is determined according to the training data, so that the correlation data between the training data conforms to the vector similarity of the corresponding high-dimensional vector expression.

[0011] Furthermore, the solution determination module is further configured to: The determining of the dimension unit value of each spatial dimension according to the training data set based on the pre-acquired business resource model includes: Based on the training data set, determining a node corresponding to each data dimension in the business resource model as a dimension node; Determine the dimension correlation data between the corresponding dimension data according to the correlation relationship between every two dimension nodes in the business resource model; The dimension unit value of each spatial dimension is determined according to the dimension correlation data, so that the vector similarity between the dimension unit vectors conforms to the dimension correlation between the data dimensions.

[0012] Furthermore, the solution determination module is further configured to: for every two dimensional nodes, Determine a first dimension association component according to a direct relationship between two dimension nodes, wherein the first dimension association component is associated with whether there is a direct association relationship between the two dimension nodes; Determine a second dimension association component according to the same belonging relationship of the two dimension nodes, the second dimension association component is associated with whether the two dimension nodes depend on the same node, and if so, the second dimension association component is negatively correlated with the dependency level between the node on which the two dimension nodes depend and the two dimension nodes; Determine the third dimension correlation component according to the indirect relationship between the two dimension nodes, the third dimension correlation component is related to whether there is a direct correlation relationship between the nodes that the two dimension nodes depend on, if so, the third dimension correlation component is positively correlated to the number of direct correlation relationships between the nodes that the two dimension nodes depend on, and negatively correlated to the dependency level between the nodes that the two dimension nodes depend on and the two dimension nodes; The dimension association data is determined according to the first dimension association component, the second dimension association component and the third dimension association component.

[0013] Furthermore, the solution determination module is further configured to: for every two dimensional nodes, If two dimension nodes depend on the same node, the lowest node on which the two dimension nodes depend is determined as the lowest dependent node; Determine the dependency levels between the two dimension nodes and the lowest dependent node respectively; The second dimension component is calculated according to the dependency level between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels.

[0014] Furthermore, the solution determination module is further configured to: for every two dimensional nodes, Let A and B represent two dimension nodes respectively. Suppose there are n groups of direct associations between the nodes that dimension nodes A and B depend on. Suppose the dependency level between the node to which A belongs and A in the i-th group of direct associations is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

[0015] In summary, this application at least has the following beneficial effects: A petroleum data structure design scheme and system based on a business resource model are provided, which is conducive to designing a more efficient and reasonable petroleum data structure.

[0016] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A flow chart of a data structure design method based on a business resource model in an embodiment of the present application is shown; Figure 2 A block diagram of a data structure design system based on a business resource model in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0020] The present application provides a petroleum data structure design solution and system based on a business resource model, which is conducive to more efficient design of a more reasonable petroleum data structure.

[0021] In a first aspect, the present application provides a petroleum data structure design method based on a business resource model. The method can be executed by a server.

[0022] Figure 1 A flow chart of a data structure design method based on a business resource model in an embodiment of the present application is shown.

[0023] Reference Figure 1 , the method specifically comprises the following steps: S110: Obtain a training data set of petroleum data.

[0024] The training data in the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data.

[0025] Specifically, the training data set refers to a set of training data used to train the final petroleum data structure design scheme of this method, which can be extracted from historical data of past business, and the specific extraction range can be selected manually. According to the specification, historical data is generally determined by data dimension and data expression of each data dimension. If the selected historical data is not in a standard format, or the specifications followed are inconsistent, the non-standard historical data can be eliminated or the historical data can be pre-processed so that all historical data finally follow the same specification, and finally the training data available under the only specification is determined to form a training data set. Data dimensions include object dimensions, business dimensions, work dimensions, professional dimensions, process dimensions, etc. Dimension expressions include specific work objects such as pipelines, well objects, oil and gas pipes, development units, etc., specific business dimensions include production operations, program research, production management, etc., and specific professions include drilling, testing, etc.

[0026] The correlation data between training data can also be intelligently determined based on historical data of past businesses. Specifically, it can be determined based on the frequency of use of the training data in the same data processing model, the frequency of use in the same business report, etc. The higher the frequency of common use, the greater the correlation data between the training data.

[0027] S120: Based on the business resource model, determine the petroleum data structure design solution according to the training data set.

[0028] The business resource model includes nodes and dependencies and correlations between nodes. The business resource model is pre-acquired, which specifically includes multiple node relationship graphs, each of which reflects the dependencies between nodes, and there may be direct associations between nodes in the same node relationship graph and between different node relationship graphs. It should be understood that the nodes in the business resource model correspond to the actual data dimensions. The general business resource model contains all possible macro and micro data dimensions, so it can also reflect the correlation between all data dimensions appearing in the training data set.

[0029] In the method of this step, the petroleum data structure design scheme includes a high-dimensional vector expression of the petroleum data in a high-dimensional data space, and the high-dimensional data space includes space dimensions that correspond one-to-one to the data dimensions; Specifically, the method of this step includes: based on the pre-acquired business resource model, determining the dimensional unit value of each spatial dimension according to the training data set, and the dimensional unit value is associated with the association relationship between the data dimension and the corresponding node in the business resource model; determining the dimensional value of the spatial dimension corresponding to each dimensional expression according to the training data, so that the correlation data between the training data conforms to the vector similarity expressed by the corresponding high-dimensional vector.

[0030] Regarding the determination of the dimension unit value, in the method of this step, the dimension unit value of each spatial dimension is determined based on the pre-acquired business resource model and the training data set, specifically including: based on the training data set, determining the node corresponding to each data dimension in the business resource model as a dimension node; determining the dimension association data between the corresponding dimension data according to the association relationship between each two dimension nodes in the business resource model; determining the dimension unit value of each spatial dimension according to the dimension association data, so that the vector similarity between the dimensional unit vectors conforms to the dimensional association between the data dimensions.

[0031] Regarding the determination of dimensional association data between two dimensional nodes, it specifically includes: determining a first dimensional association component according to the direct relationship between the two dimensional nodes, the first dimensional association component is related to whether there is a direct association relationship between the two dimensional nodes; determining a second dimensional association component according to the same relationship between the two dimensional nodes, the second dimensional association component is related to whether the two dimensional nodes depend on the same node, if so, the second dimensional association component is negatively correlated with the dependency level between the nodes that the two dimensional nodes depend on and the two dimensional nodes; determining a third dimensional association component according to the indirect relationship between the two dimensional nodes, the third dimensional association component is related to whether there is a direct association relationship between the nodes that the two dimensional nodes depend on, if so, the third dimensional association component is positively correlated with the number of direct associations between the nodes that the two dimensional nodes depend on, and negatively correlated with the dependency level between the nodes that the two dimensional nodes depend on and the two dimensional nodes; determining the dimensional association data according to the first dimensional association component, the second dimensional association component and the third dimensional association component.

[0032] In a specific example, the first dimension component takes the value of 0 or 1, that is, if there is a direct association relationship between two dimension nodes, the first dimension component takes the value of 1, otherwise the first dimension component takes the value of 0.

[0033] The method for determining the second dimension associated component specifically includes: if two dimension nodes depend on the same node, then determine the lowest node on which the two dimension nodes depend as the lowest dependent node; respectively determine the dependency levels between the two dimension nodes and the lowest dependent node; calculate the second dimension component according to the dependency levels between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels. In this example, let the second dimension component be , the absolute value of the difference between the two dependency levels is E, and the arithmetic mean is F, then .

[0034] The method for determining the third dimension association component specifically includes: representing two dimension nodes with A and B respectively, assuming that there are n groups of direct association relationships between the nodes that the dimension nodes A and B depend on, assuming that the dependency level between the node to which A belongs and A in the i-th group of direct association relationships is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

[0035] Let the first dimension component be , the dimension associated data is W, then In this way, the calculation of the dimension association data between every two dimensional data can be realized.

[0036] When training the dimension unit value specifically according to the dimension association data, a dimension representative vector can be determined in the high-dimensional data space relative to each dimension data. The dimension representative vector takes a positive real number (assuming an unknown quantity) in the spatial dimension corresponding to the dimension data, and takes a value of 0 in other spatial dimensions. The unknown quantity of the spatial dimension value is trained based on the dimension representative vector and the dimension association data, so that the relationship between the vector similarities between the representative vectors of different dimensions basically fits the corresponding dimension association data. The training method specifically points to the goal of minimizing the sum of squared differences between the vector similarities of the dimension representative vector and the corresponding dimension association data, and determines the modulus of each dimension representative vector at this time as the dimension unit value of the corresponding dimension data.

[0037] After the dimension unit value is determined, the dimension values ​​represented by all dimensional expressions are multiples of the dimension unit value. At this time, the training data can be used to train the dimension values ​​of the spatial dimensions corresponding to each dimensional expression. Similarly, the training method specifically points to the goal of minimizing the sum of squares of the difference between the correlation data between the training data and the vector similarity expressed by the corresponding high-dimensional vector, and determines the specific value of the spatial dimension corresponding to the dimensional expression, and then determines the dimension value, that is, the specific value is how many times the dimension unit value.

[0038] Regarding the calculation of vector similarity in the aforementioned content, the vector similarity can be calculated by referring to the existing method to obtain a unique numerical result. For example, the vector similarity of two vectors is generally equal to the modulus of the first vector multiplied by the modulus of the second vector multiplied by the cosine of the angle between the two vectors.

[0039] Based on the above, the final oil data structure design scheme can be determined. The oil data structure design scheme includes all data dimensions existing in the training data set and all data expressions existing in each data dimension, and the oil data structure design scheme also includes each data dimension and each data expression corresponding to the high-dimensional vector expression in the high-dimensional data space, that is, the oil data determined according to the oil data structure design scheme is characterized as a high-dimensional vector expression with specific dimensional meanings. The oil data structure meets the needs of actual data applications and can reasonably and clearly express the relationship between different oil data. The design of the oil data structure does not require the process of manually combing and refining data association logic, thereby realizing the intelligent and efficient determination of the oil data structure.

[0040] By utilizing the training data set and business resource model of petroleum data, we can intelligently determine a high-dimensional data space for expressing petroleum data, and then determine the petroleum data structure design scheme that couples the high-dimensional data space with the actual data dimensions and data expression of the petroleum data, which is conducive to efficiently determining a more reasonable petroleum data structure design scheme.

[0041] Of course, when the petroleum data structure is actually used, nodes can be added or deleted manually in the business resource model, or the relevance data of a set of petroleum data determined intelligently can be adjusted manually through feedback. These operations can achieve the process of training the petroleum structure data design plan, so that the petroleum data structure design plan can keep up with the actual business needs at any time and become more reasonable and reliable.

[0042] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0043] In a second aspect, the present application provides a petroleum data structure design system based on a business resource model. The system can be specifically configured as a server.

[0044] Figure 2 A block diagram of a data structure design system based on a business resource model in an embodiment of the present application is shown.

[0045] Reference Figure 2 , the system specifically includes a data acquisition module 210 and a solution determination module 220; The data acquisition module 210 is used to acquire a training data set of petroleum data, wherein the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data; The solution determination module 220 is used to determine the petroleum data structure design solution based on the business resource model and the training data set, wherein the petroleum data structure design solution includes a high-dimensional vector expression of the petroleum data in a high-dimensional data space, wherein the high-dimensional data space includes space dimensions corresponding to the data dimensions one by one; The solution determination module 220 is further configured to: Based on the pre-acquired business resource model, determining a dimension unit value of each spatial dimension according to the training data set, wherein the dimension unit value is associated with an association relationship between a data dimension and a corresponding node in the business resource model; The dimension value of each dimensional expression corresponding to the spatial dimension is determined according to the training data, so that the correlation data between the training data conforms to the vector similarity of the corresponding high-dimensional vector expression.

[0046] Furthermore, the solution determination module 220 is further configured to: The determining of the dimension unit value of each spatial dimension according to the training data set based on the pre-acquired business resource model includes: Based on the training data set, determining a node corresponding to each data dimension in the business resource model as a dimension node; Determine the dimension association data between corresponding dimension data according to the association relationship between every two dimension nodes in the business resource model; The dimension unit value of each spatial dimension is determined according to the dimension correlation data, so that the vector similarity between the dimension unit vectors conforms to the dimension correlation between the data dimensions.

[0047] Furthermore, the solution determination module 220 is further configured to: for every two dimensional nodes, Determine a first dimension association component according to a direct relationship between two dimension nodes, wherein the first dimension association component is associated with whether there is a direct association relationship between the two dimension nodes; Determine a second dimension association component according to the same belonging relationship of the two dimension nodes, the second dimension association component is associated with whether the two dimension nodes depend on the same node, and if so, the second dimension association component is negatively correlated with the dependency level between the node on which the two dimension nodes depend and the two dimension nodes; Determine the third dimension correlation component according to the indirect relationship between the two dimension nodes, the third dimension correlation component is related to whether there is a direct correlation relationship between the nodes that the two dimension nodes depend on, if so, the third dimension correlation component is positively correlated to the number of direct correlation relationships between the nodes that the two dimension nodes depend on, and negatively correlated to the dependency level between the nodes that the two dimension nodes depend on and the two dimension nodes; The dimension association data is determined according to the first dimension association component, the second dimension association component and the third dimension association component.

[0048] Furthermore, the solution determination module 220 is further configured to: for every two dimensional nodes, If two dimension nodes depend on the same node, the lowest node on which the two dimension nodes depend is determined as the lowest dependent node; Determine the dependency levels between the two dimension nodes and the lowest dependent node respectively; The second dimension component is calculated according to the dependency level between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels.

[0049] Furthermore, the solution determination module 220 is further configured to: for every two dimensional nodes, Let A and B represent two dimension nodes respectively. Suppose there are n sets of direct associations between the nodes that dimension nodes A and B depend on. Suppose the dependency level between the node to which A belongs and A in the i-th set of direct associations is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

[0050] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0051] In summary, this application at least has the following beneficial effects: A petroleum data structure design scheme and system based on a business resource model are provided, which is conducive to designing a more efficient and reasonable petroleum data structure.

[0052] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A petroleum data structure design method based on a business resource model, characterized in that: include: Acquire a training data set of petroleum data, wherein the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data; Based on the business resource model, determining a petroleum data structure design scheme according to the training data set, the petroleum data structure design scheme comprising a high-dimensional vector expression of the petroleum data in a high-dimensional data space, the high-dimensional data space comprising space dimensions corresponding one-to-one to the data dimensions; The step of determining the petroleum data structure design scheme based on the business resource model and the training data set comprises: Based on the pre-acquired business resource model, determining a dimension unit value of each spatial dimension according to the training data set, wherein the dimension unit value is associated with an association relationship between a data dimension and a corresponding node in the business resource model; The dimension value of each dimensional expression corresponding to the spatial dimension is determined according to the training data, so that the correlation data between the training data conforms to the vector similarity of the corresponding high-dimensional vector expression.

2. The petroleum data structure design method based on the business resource model according to claim 1 is characterized in that: The business resource model includes nodes and dependencies and correlations between nodes; The determining of the dimension unit value of each spatial dimension according to the training data set based on the pre-acquired business resource model includes: Based on the training data set, determining a node corresponding to each data dimension in the business resource model as a dimension node; Determine the dimension association data between corresponding dimension data according to the association relationship between every two dimension nodes in the business resource model; The dimension unit value of each spatial dimension is determined according to the dimension association data, so that the vector similarity between the dimension unit vectors conforms to the dimension association between the data dimensions.

3. The petroleum data structure design method based on the business resource model according to claim 2 is characterized in that: The step of determining the dimensional correlation data between corresponding dimensional data according to the correlation relationship between each two dimensional nodes in the business resource model includes: for each two dimensional nodes, Determine a first dimension association component according to a direct relationship between two dimension nodes, wherein the first dimension association component is associated with whether there is a direct association relationship between the two dimension nodes; Determine a second dimension association component according to the same belonging relationship of the two dimension nodes, the second dimension association component is associated with whether the two dimension nodes depend on the same node, and if so, the second dimension association component is negatively correlated with the dependency level between the node on which the two dimension nodes depend and the two dimension nodes; Determine the third dimension correlation component according to the indirect relationship between the two dimension nodes, the third dimension correlation component is related to whether there is a direct correlation relationship between the nodes that the two dimension nodes depend on, if so, the third dimension correlation component is positively correlated to the number of direct correlation relationships between the nodes that the two dimension nodes depend on, and negatively correlated to the dependency level between the nodes that the two dimension nodes depend on and the two dimension nodes; The dimension association data is determined according to the first dimension association component, the second dimension association component and the third dimension association component.

4. The petroleum data structure design method based on the business resource model according to claim 3 is characterized in that: The determining of the second dimension associated component according to the same belonging relationship of two dimension nodes comprises: for each two dimension nodes, If two dimension nodes depend on the same node, the lowest node on which the two dimension nodes depend is determined as the lowest dependent node; Determine the dependency levels between the two dimension nodes and the lowest dependent node respectively; The second dimension component is calculated according to the dependency level between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels.

5. The petroleum data structure design method based on business resource model according to claim 3 is characterized in that: The determining of the third dimension association component according to the indirect relationship between two dimension nodes comprises: for each two dimension nodes, Let A and B represent two dimension nodes respectively. Suppose there are n sets of direct associations between the nodes that dimension nodes A and B depend on. Suppose the dependency level between the node to which A belongs and A in the i-th set of direct associations is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

6. A petroleum data structure design system based on a business resource model, characterized in that: It includes a data acquisition module (210) and a solution determination module (220); The data acquisition module (210) is used to acquire a training data set of petroleum data, wherein the training data set includes multiple data dimensions and data expressions of each data dimension, and the training data set also includes correlation data between the training data; The scheme determination module (220) is used to determine a petroleum data structure design scheme based on the business resource model and the training data set, wherein the petroleum data structure design scheme includes a high-dimensional vector expression of the petroleum data in a high-dimensional data space, wherein the high-dimensional data space includes space dimensions corresponding to the data dimensions one by one; The solution determination module (220) is further configured to: Based on the pre-acquired business resource model, determining a dimension unit value of each spatial dimension according to the training data set, wherein the dimension unit value is associated with an association relationship between a data dimension and a corresponding node in the business resource model; The dimension value of each dimensional expression corresponding to the spatial dimension is determined according to the training data, so that the correlation data between the training data conforms to the vector similarity of the corresponding high-dimensional vector expression.

7. The petroleum data structure design system based on business resource model according to claim 6 is characterized in that: The solution determination module (220) is further configured to: The determining of the dimension unit value of each spatial dimension according to the training data set based on the pre-acquired business resource model includes: Based on the training data set, determining a node corresponding to each data dimension in the business resource model as a dimension node; Determine the dimension association data between corresponding dimension data according to the association relationship between every two dimension nodes in the business resource model; The dimension unit value of each spatial dimension is determined according to the dimension association data, so that the vector similarity between the dimension unit vectors conforms to the dimension association between the data dimensions.

8. The petroleum data structure design system based on business resource model according to claim 7 is characterized in that: The solution determination module (220) is further configured to: for every two dimensional nodes, Determine a first dimension association component according to a direct relationship between two dimension nodes, wherein the first dimension association component is associated with whether there is a direct association relationship between the two dimension nodes; Determine a second dimension association component according to the same belonging relationship of the two dimension nodes, the second dimension association component is associated with whether the two dimension nodes depend on the same node, and if so, the second dimension association component is negatively correlated with the dependency level between the node on which the two dimension nodes depend and the two dimension nodes; Determine the third dimension correlation component according to the indirect relationship between the two dimension nodes, the third dimension correlation component is related to whether there is a direct correlation relationship between the nodes that the two dimension nodes depend on, if so, the third dimension correlation component is positively correlated to the number of direct correlation relationships between the nodes that the two dimension nodes depend on, and negatively correlated to the dependency level between the nodes that the two dimension nodes depend on and the two dimension nodes; The dimension association data is determined according to the first dimension association component, the second dimension association component and the third dimension association component.

9. The petroleum data structure design system based on business resource model according to claim 8, characterized in that: The solution determination module (220) is further configured to: for every two dimensional nodes, If two dimension nodes depend on the same node, the lowest node on which the two dimension nodes depend is determined as the lowest dependent node; Determine the dependency levels between the two dimension nodes and the lowest dependent node respectively; The second dimension component is calculated according to the dependency level between the two dimension nodes and the lowest dependent node, and the second dimension component is negatively correlated to the absolute value and arithmetic mean of the difference between the two dependency levels.

10. The petroleum data structure design system based on business resource model according to claim 9, characterized in that: The solution determination module (220) is further configured to: for every two dimensional nodes, Let A and B represent two dimension nodes respectively. Suppose there are n sets of direct associations between the nodes that dimension nodes A and B depend on. Suppose the dependency level between the node to which A belongs and A in the i-th set of direct associations is , the dependency level between the nodes that B is subordinate to and B is , then the third dimension component is ,but .

Images