Index knowledge graph generation method and device, electronic equipment and storage medium

Abstract

The application provides a method and device for generating an index knowledge graph, electronic equipment and a storage medium, wherein the method comprises: obtaining index relationship configuration information; analyzing the index relationship configuration information to obtain business relationship information corresponding to a plurality of pairs of indexes, wherein the business relationship information corresponding to each pair of indexes comprises a business relationship between two indexes in each pair of indexes and attribute information of the business relationship; and generating an index knowledge graph according to the business relationships and attribute information corresponding to the plurality of pairs of indexes. According to the application, the index knowledge graph can be generated based on the business relationship information between the plurality of pairs of indexes, the business relationships between the plurality of indexes can be analyzed based on the generated index knowledge graph, and the influence range of the indexes can also be located.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method, apparatus, electronic device, and storage medium for generating an indicator knowledge graph. Background Technology

[0002] For ease of management, some industries may use multiple indicators for analysis and evaluation. For example, due to the big data nature of banks, there are great challenges in analyzing the business relationships of complex and massive indicators.

[0003] In related technologies, the main approach is text-based registration management between management departments, which displays indicator information on a webpage in the form of a two-dimensional table for business personnel to query. However, this method is difficult to analyze the business relationships between multiple indicators. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for generating an indicator knowledge graph. The specific solution is as follows:

[0005] One aspect of this application provides a method for generating an indicator knowledge graph, comprising:

[0006] Obtain indicator relationship configuration information;

[0007] The indicator relationship configuration information is parsed to obtain the business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship.

[0008] Based on the business relationships and attribute information corresponding to multiple pairs of indicators, an indicator knowledge graph is generated.

[0009] According to another aspect of the embodiments of this application, an apparatus for generating an index knowledge graph is provided, comprising:

[0010] The first acquisition module is configured to acquire indicator relationship configuration information;

[0011] The second acquisition module is configured to parse the indicator relationship configuration information to obtain the business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship.

[0012] The first generation module is configured to generate an indicator knowledge graph based on the business relationships and attribute information corresponding to multiple pairs of indicators.

[0013] According to another aspect of the embodiments of this application, an electronic device is provided, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method as described in the embodiments of this application above.

[0014] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the methods of the embodiments of this application described above.

[0015] According to another aspect of the embodiments of this application, a computer program product is provided, comprising: a computer program that, when executed by a processor, implements the method described in the above embodiments of this application.

[0016] The technical solution provided by the embodiments of this application brings at least the following beneficial effects: by obtaining indicator relationship configuration information and parsing the indicator relationship configuration information to obtain business relationship information corresponding to multiple pairs of indicators, and then generating an indicator knowledge graph based on the business relationships and attribute information corresponding to multiple pairs of indicators. Therefore, an indicator knowledge graph can be generated based only on the business relationship information between multiple pairs of indicators. Based on the generated indicator knowledge graph, the analysis of business relationships between multiple indicators and the positioning of the scope of influence of indicators can be realized.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0019] Figure 1 This is a flowchart illustrating a method for generating an indicator knowledge graph according to an embodiment of this application.

[0020] Figure 2 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0021] Figure 3 This is a schematic diagram of an indicator registration interface provided in an embodiment of this application.

[0022] Figure 4 This is a schematic diagram of an index relationship configuration interface provided in an embodiment of this application.

[0023] Figure 5 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0024] Figure 6 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0025] Figure 7 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0026] Figure 8 This is a schematic diagram of upstream tracing analysis operation shown in one embodiment of this application.

[0027] Figure 9 This is a schematic diagram of the upstream tracing analysis results shown in one embodiment of this application. Figure 1 .

[0028] Figure 10 This is a schematic diagram of the upstream tracing analysis results shown in one embodiment of this application. Figure 2 .

[0029] Figure 11 This is a schematic diagram illustrating the downstream impact analysis results of an embodiment of this application.

[0030] Figure 12 This is a schematic diagram of the structure of an indicator knowledge graph generation device shown in one embodiment of this application.

[0031] Figure 13 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0033] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0034] In related technologies, the management of indicators is mainly based on text-based registration between management departments, displaying indicator information on a webpage in the form of a two-dimensional table for business personnel to query. However, this method makes it difficult to analyze the business relationships between multiple indicators.

[0035] Based on this, this application proposes a method, apparatus, electronic device, and storage medium for generating an indicator knowledge graph.

[0036] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0037] The following description, with reference to the accompanying drawings, describes a method, apparatus, electronic device, and storage medium for generating an indicator knowledge graph according to embodiments of this application. Figure 1 This is a flowchart illustrating a method for generating an indicator knowledge graph according to an embodiment of this application.

[0038] This application embodiment illustrates the example of the indicator knowledge graph generation method being configured in an indicator knowledge graph generation device. The indicator knowledge graph generation device can be applied to any electronic device so that the electronic device can perform the function of generating indicator knowledge graphs.

[0039] Among them, electronic devices can be any device with computing capabilities, such as personal computers, mobile terminals, servers, etc. Mobile terminals can be hardware devices with various operating systems, touch screens and / or displays, such as in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, etc.

[0040] like Figure 1 As shown, the method for generating this indicator knowledge graph may include the following steps 101-103.

[0041] In step 101, the indicator relationship configuration information is obtained.

[0042] In this application, a metric relationship configuration file can be obtained, which includes metric relationship configuration information. Alternatively, metric relationship configuration information can be obtained based on the configuration operations performed by business personnel on the metric relationship configuration interface. For example, business relationship information between two metrics can be configured on the configuration interface, thereby obtaining metric relationship configuration information for multiple pairs of metrics based on the configuration operations performed by business personnel on the business relationships between multiple pairs of metrics.

[0043] In step 102, the indicator relationship configuration information is parsed to obtain the business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship.

[0044] In this application, if the indicator relationship configuration information is stored in a configuration file, the configuration file can be parsed to obtain the business relationship information corresponding to multiple pairs of indicators. Alternatively, if the indicator relationship configuration information is obtained based on the configuration operations performed by business personnel on the indicator relationship configuration interface, the indicator relationship configuration information for each pair of indicators can be parsed to obtain the business relationship information corresponding to each pair of indicators.

[0045] The business relationship information for each pair of indicators may include the identifiers of the two indicators in each pair, the business relationship between the two indicators, and the attribute information of the business relationship.

[0046] For example, the business relationship between two indicators can be unrelated, non-deterministic, or deterministic. Unrelated means there is no mutual influence between the two indicators; non-deterministic means there is an influence between the two indicators, but it is not precise enough to be expressed by a function; deterministic means there is a clear functional relationship between the two indicators.

[0047] For example, the attribute information of business relationships can include relationship functions, correlation coefficients, and relationship impact types. The correlation coefficient can be a number between -1 and 1. A correlation coefficient of 0 indicates no correlation, a correlation coefficient greater than 0 indicates a positive correlation (the larger the coefficient, the stronger the correlation, with 1 indicating a perfect positive correlation), and a correlation coefficient less than 0 indicates a negative correlation (the smaller the coefficient, the stronger the negative correlation, with -1 indicating a perfect negative correlation). Relationship impact types can include upstream cause relationships, downstream result relationships, etc.

[0048] In step 103, an indicator knowledge graph is generated based on the business relationships and attribute information corresponding to multiple pairs of indicators.

[0049] In this application, indicators can be treated as entities, i.e., vertices, the business relationships between two indicators as edges, and the attribute information of the business relationships between two indicators as the attributes of the edges, thus generating an indicator knowledge graph. Therefore, an indicator knowledge graph is generated based on the business relationship information between multiple pairs of indicators. Based on the indicator knowledge graph, the business relevance, business impact, and business association relationships between indicators can be managed, enabling the analysis of business relationships between multiple indicators.

[0050] In this application, each vertex in the indicator knowledge graph corresponds to an indicator that can be linked to specific indicator information, such as indicator identifier, indicator number, business attribute, business department, etc. Each edge in the indicator knowledge graph represents a business relationship between two indicators, such as an unrelated, non-deterministic, or deterministic relationship. Each edge includes specific attribute information that can be used to describe the details of the relationship, such as the attribute information can include the relationship function, correlation coefficient, and relationship impact type, etc.

[0051] In practical applications, business operations may be divided into multiple levels, with each level having one or more indicators. In this application, the indicator relationship configuration information can be analyzed to obtain business relationship information corresponding to one or more pairs of indicators in adjacent levels, as well as business relationship information between one or more pairs of indicators in the same level. An indicator knowledge graph can be generated based on the business relationship information corresponding to multiple pairs of indicators. Thus, based on the knowledge graph, the business relationship between two or more indicators in different levels can be analyzed.

[0052] For example, taking banks as an example, the provincial-level new personal loan ratio, provincial-level personal business loans, and provincial-level micro and small enterprise loans are indicators at the same level in a certain province. The city-level new personal loan ratio, city-level personal business loans, and city-level micro and small enterprise loans of each city under the province belong to another level. Other city-level bank indicators that affect the city-level new personal loan ratio belong to another level. For example, the indicator relationship configuration information can include the business relationship information between the city-level new personal loan ratio of each city under the province and the provincial-level new personal loan ratio. It can also include the business relationship information between the city-level new loan ratio of each city and other indicators. Based on the business relationship information between multiple pairs of indicators in the indicator relationship configuration information, a bank indicator knowledge graph can be generated.

[0053] In this embodiment, by acquiring indicator relationship configuration information and parsing it, business relationship information corresponding to multiple pairs of indicators is obtained. Then, based on the business relationships and attribute information corresponding to the multiple pairs of indicators, an indicator knowledge graph is generated. Therefore, an indicator knowledge graph can be generated based solely on the business relationship information between multiple pairs of indicators. Based on the generated indicator knowledge graph, the business relationships between multiple indicators can be analyzed, and the scope of influence of the indicators can be located.

[0054] Figure 2 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0055] like Figure 2 As shown, the method for generating this indicator knowledge graph may include the following steps 201-207.

[0056] In step 201, upon receiving the indicator relationship configuration instruction, the indicator relationship configuration interface is displayed, which includes two indicator input boxes, a relationship type input box, and an attribute information input box.

[0057] In this application, business personnel can configure the business relationship between two metrics on the metric relationship configuration interface. During implementation, business personnel can trigger configuration controls on the interface, such as configuration buttons, to obtain metric relationship configuration instructions and display the metric relationship configuration interface accordingly.

[0058] The indicator relationship configuration interface may include, but is not limited to, two indicator input boxes, a relationship type input box, and an attribute information input box. The indicator input box can be used to input the indicator's identifier, such as the indicator's name or number; the relationship type input box can be used to input the business relationship between two indicators; and the attribute information input box can be used to input the attribute information of the business relationship between two indicators.

[0059] In step 202, based on the detected indicator input operations, two indicators to be configured are determined.

[0060] In this application, for the two indicator input boxes on the configuration interface, the identifier of the indicator to be configured can be directly entered into the indicator input box. Alternatively, a drop-down control can be set in the indicator input box. When the drop-down control in the indicator input box is triggered, an indicator list can be displayed. Business personnel can select the indicator to be configured from the indicator list. Based on the selection operation of the indicator in the indicator list, the indicator to be configured can be determined.

[0061] Furthermore, before configuring business relationships using the indicator relationship configuration interface, business personnel can also register indicators through the indicator registration interface. This allows them to obtain indicator configuration information and parse it to retrieve the indicator information for each indicator. This indicator information may include business attributes, data attributes, management attributes, indicator number, business department, indicator name, business department contact person, business rules, business department contact information, business definition, business timeliness requirements, update frequency, and the Chinese name of the physical subsystem. This allows business personnel to register the indicators they need to manage as required, improving the flexibility of indicator management.

[0062] To facilitate understanding, the following combination Figure 3 To explain, Figure 3 This is a schematic diagram of an indicator registration interface provided in an embodiment of this application. Figure 3 As shown, the indicator registration interface allows users to input the following: indicator number (e.g., 155882), indicator name (e.g., balance of new model products such as micro-loans), business attributes (e.g., loan balance of customers belonging to the "real estate industry"), data attributes (e.g., business management), management attributes, business department, business department contact person, business rules (e.g., needing to distinguish between preliminary figures and regulatory reports), business department contact information, business definition (e.g., total domestic and foreign currencies), business timeliness requirements (e.g., T+4), update frequency (e.g., monthly updates), and Chinese name of the physical subsystem (e.g., SMIS). Additionally, business personnel can input indicator information by triggering the "Edit" control on the indicator registration interface, and can also add new indicator information using the "Add" control on the indicator interface.

[0063] In addition, to further improve the accuracy of indicator information, auditors can review the submitted indicator information. Indicators that pass the review can be selected by business personnel from the above indicator list. For indicator information that does not pass the review, corresponding prompts can be generated, and auditors can also modify the indicator information.

[0064] In step 203, based on the detected relationship type input operation, the first target business relationship between the two metrics to be configured is determined.

[0065] In this application, business personnel can directly enter the first target business relationship information between two indicators to be configured in the relationship type input box. Based on the detected relationship type input operation, the first target business relationship between the two indicators to be configured can be determined.

[0066] Alternatively, a drop-down control can be provided in the relationship type input box. When the drop-down control in the relationship type input box is triggered, a list of relationships can be displayed. Business personnel can select the business relationship to be entered from the list. Based on the selection operation of the business relationship in the list, the first target business relationship between the two metrics to be configured can be determined.

[0067] In step 204, the target attribute information of the first target business relationship is determined based on the detected attribute information input operation.

[0068] In this application, business personnel can directly enter the attribute information of the business relationship between two indicators to be configured in the attribute information input box. Based on the detected attribute information input operation, the target attribute information of the first target business relationship can be determined.

[0069] Because the business relationships between two indicators are different, the types of attribute information for these business relationships, i.e., attribute types, may also differ. For example, if the business relationship between two indicators is deterministic, the attribute information for this relationship may include the relationship function, correlation coefficient, and relationship impact type. If the business relationship between two indicators is non-deterministic, the attribute information for this relationship may include the correlation coefficient and relationship impact type. If the business relationship between two indicators is uncorrelated, then the attribute information for this relationship may include the correlation coefficient.

[0070] Based on this, in order to improve the configuration efficiency of indicator relationships, the first target business relationship can be matched with multiple attribute types respectively, and the attribute type that matches the first target business relationship can be determined as the target attribute type. The attribute information input box corresponding to the target attribute type can be marked and displayed. The target attribute information of the first target business relationship can be determined based on the input operation of the attribute information input box corresponding to the detected target attribute type.

[0071] When matching the first target business relationship with multiple attribute types, the matching degree between the first target business relationship and each attribute type can be determined, and the target attribute type can be determined based on the matching degree. Alternatively, the attribute type matching the first target business relationship can be determined based on the pre-determined mapping relationship between each business relationship and attribute type.

[0072] In this application, the marker for the attribute information input box corresponding to the target attribute type can be displayed by changing the boundary line of the attribute information input box corresponding to the target attribute type from the default color to a specific color, such as red for the boundary line of the attribute information input box corresponding to the target attribute type, and gray for the boundary lines of other attribute information input boxes. Alternatively, the target character can be displayed at a preset position away from the attribute information input box corresponding to the target attribute type, such as displaying "*" on the left side of the input box to indicate to business personnel that the attribute information input box is a required field. Alternatively, other methods of marking and display can be used, and this application does not limit this.

[0073] For example, if the business relationship is deterministic, the corresponding attribute types include correlation coefficient and relationship impact type; if the business relationship is non-deterministic, the corresponding attribute types include correlation coefficient and relationship impact type; if the business relationship is unrelated, the corresponding attribute type includes correlation coefficient. If the business relationship between indicator A and indicator B is non-deterministic, then the attribute information boxes corresponding to the correlation coefficient and relationship impact type can be marked and displayed to indicate to business personnel what attribute information they need to input.

[0074] To further improve configuration efficiency, this application can also generate prompt information based on the target attribute type, wherein the prompt information can be used to prompt descriptive information about the target attribute type.

[0075] In this application, the prompt message can be displayed in the attribute information input box corresponding to the target attribute type, or at a preset position away from the attribute information input box corresponding to the target attribute type. Alternatively, a voice prompt control can be displayed at a preset position away from the attribute information input box corresponding to the target attribute type, such as displaying a speaker on the right side of the input box, which can play the prompt message when the business personnel trigger the speaker. Other methods can also be used to display the prompt message, and this application does not limit this approach.

[0076] For example, if the target attribute type includes a correlation coefficient, the prompt message could be that a correlation coefficient of 0 indicates no correlation, a correlation coefficient greater than 0 indicates a positive correlation, and a correlation coefficient less than 0 indicates a negative correlation. This prompt message can be displayed in the input box corresponding to the correlation coefficient.

[0077] Therefore, by generating prompts based on the target attribute type, business personnel can be prompted with descriptions of the target attribute type. This makes it easier for business personnel to understand the attribute information corresponding to the target attribute type, improving the efficiency of attribute information input and, consequently, the efficiency of indicator relationship configuration.

[0078] In step 205, if the indicator relationship configuration is completed, the indicator relationship configuration information corresponding to the two indicators to be configured is obtained.

[0079] In this application, there can be a submit button on the indicator relationship configuration interface. After the business personnel have configured the business relationship and the attribute information of the business relationship between the two indicators, they can click the submit button. Thus, when the indicator relationship configuration is detected as complete, the indicator relationship configuration information corresponding to the two indicators to be configured can be obtained.

[0080] The configuration information for the relationship between the two metrics to be configured may include the identifiers of the two metrics to be configured, the first target business relationship, and the attribute information of the first target business relationship.

[0081] Therefore, business personnel can configure the business relationships and attribute information of multiple pairs of indicators through the indicator relationship configuration interface, thereby obtaining the indicator relationship configuration information of multiple pairs of indicators.

[0082] To facilitate understanding, the following will be combined with... Figure 4 To provide an explanation, Figure 4 This is a schematic diagram of an index relationship configuration interface provided in an embodiment of this application. For example... Figure 4 As shown, on the indicator relationship configuration interface, you can enter the original indicator number and the target indicator number (corresponding to the two indicators to be configured mentioned above). For example, you can enter the original indicator number as 10001 (indicating that the indicator is the points redeemed in the current month) and the target indicator number as 10002 (indicating that the revenue to be recognized in the current month). You can also enter the relationship type (such as deterministic relationship), the relationship impact type (such as upstream cause relationship), the relationship function (such as the revenue to be recognized in the current month = points redeemed in the current month * 0.2% * 55% / 70%), and the relationship coefficient (such as 0.4).

[0083] In step 206, the indicator relationship configuration information is parsed to obtain the business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship.

[0084] In step 207, an indicator knowledge graph is generated based on the business relationships and attribute information corresponding to multiple pairs of indicators.

[0085] In this application, steps 206-207 can be implemented in any of the embodiments of this application, and therefore will not be described in detail here.

[0086] In this embodiment, when obtaining indicator relationship configuration information, an indicator relationship configuration interface can be displayed upon receiving an indicator relationship configuration instruction. Based on detected indicator input operations, two indicators to be configured are determined. Based on detected relationship type input operations, a first target business relationship between the two indicators to be configured is determined. Based on detected attribute information input operations, the target attribute information of the first target business relationship is determined. Upon detecting an indicator relationship configuration completion operation, the indicator relationship configuration information corresponding to the two indicators to be configured can be obtained. Therefore, business personnel can configure business relationships and attribute information between multiple pairs of indicators through the indicator relationship configuration interface, and can obtain indicator relationship configuration information for multiple pairs of indicators. Indicator relationship configuration is simple, convenient, and highly flexible.

[0087] Figure 5 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0088] like Figure 5 As shown, the method for generating this indicator knowledge graph may also include the following steps 501-504.

[0089] In step 501, a first indicator relationship query request is obtained, wherein the first indicator relationship query request includes a first indicator identifier and a second indicator identifier.

[0090] In this application, after generating the indicator knowledge graph, business personnel can enter the identifiers of two indicators to query on the query interface to find the business relationship between the two indicators. At this time, a first indicator relationship query request can be obtained. The first indicator relationship query request may include the first indicator identifier, the second indicator identifier, etc.

[0091] When business personnel enter the identifiers of two indicators to be queried on the query interface, they can either enter them directly or trigger a drop-down control to select indicators from the displayed indicator list. This application does not impose any restrictions on this.

[0092] In step 502, the first indicator identifier and the second indicator identifier are matched with the identifiers of each indicator in the indicator knowledge graph.

[0093] In this application, the first indicator identifier can be matched with the identifiers of each indicator in the indicator knowledge graph, and the second indicator identifier can be matched with the identifiers of each indicator in the indicator knowledge graph.

[0094] In step 503, if the first indicator identifier matches the first target indicator and the second indicator identifier matches the second target indicator, the business path from the first target indicator to the second target indicator in the indicator knowledge graph is determined.

[0095] If the first indicator identifier matches the first target indicator in the indicator knowledge graph and the second indicator identifier matches the second target indicator, the business path from the first target indicator to the second target indicator in the indicator knowledge graph is determined.

[0096] The business path from the first target indicator to the second target indicator can be the shortest business path, a business path with a sufficient number of nodes, or any of the business paths. This application does not limit the scope of the application.

[0097] In step 504, the first query result is generated based on the business path.

[0098] In this application, the first query result of the first indicator relationship query request can be generated according to the business path, and the first query result can be displayed on the query interface.

[0099] In this embodiment, a first indicator relationship query request can be made, and the first indicator identifier and the second indicator identifier in the first indicator relationship query request can be matched with the identifiers of each indicator in the indicator knowledge graph. If the first indicator identifier matches the first target indicator and the second indicator identifier matches the second target indicator, the business path from the first target indicator to the second target indicator in the indicator knowledge graph is determined, and a first query result is generated based on the business path. Thus, based on the indicator knowledge graph, it is possible to query the business relationship between two indicators.

[0100] Figure 6 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0101] like Figure 6 As shown, the method for generating this indicator knowledge graph may also include the following steps 601-603.

[0102] In step 601, a second indicator relationship query request is obtained, wherein the second indicator relationship query request includes a second target business relationship.

[0103] In this application, after generating the indicator knowledge graph, business personnel can directly input business relationships on the query interface or select from the provided list of business relationships to query all indicators belonging to the same business relationship, thereby obtaining a second indicator relationship query request. The second indicator relationship query request may include a second target business relationship.

[0104] In step 602, the second target business relationship is matched with the business relationships between pairs of indicators in the indicator knowledge graph.

[0105] In this application, the second target business relationship can be matched with the business relationships between pairs of indicators in the indicator knowledge graph, and the matching degree between the second target business relationship and the business relationships between pairs of indicators can be calculated.

[0106] In step 603, a second query result is generated based on the indicators that match the business relationships in the indicator knowledge graph with the second target business relationship.

[0107] In this application, indicators whose matching degree between business relationships in the indicator knowledge graph and the second target business relationship is greater than a preset threshold can be used as matching indicators to generate a second query result corresponding to the second indicator relationship query request, and the second query result can be displayed on the query interface.

[0108] For example, if the second target business relationship is unrelated, the business relationships that are unrelated in the indicator knowledge graph include indicators A1 and A2, indicators A2 and A4, and indicators A1 and A6.

[0109] In this embodiment, a second indicator relationship query request can also be made. The second target business relationship in the second indicator relationship query request is matched with the business relationships between pairs of indicators in the indicator knowledge graph. Based on the indicators in the indicator knowledge graph that match the business relationships with the second target business relationship, a second query result is generated. Thus, all indicators under a certain business relationship can be queried based on the indicator knowledge graph.

[0110] Figure 7 This is a flowchart illustrating a method for generating an indicator knowledge graph according to another embodiment of this application.

[0111] like Figure 7 As shown, the method for generating this indicator knowledge graph may also include the following steps 701-704.

[0112] In step 701, a third indicator relationship query request is obtained, wherein the third indicator relationship query request includes a third indicator identifier.

[0113] In this application, after generating the indicator knowledge graph, business personnel can enter the identifier of the indicator to be queried on the query interface, or trigger the indicator traceability analysis function control, etc., to query all indicators that have a business relationship with that indicator. At this time, a third indicator relationship query request can be obtained. The third indicator relationship query request may include the third indicator identifier.

[0114] When business personnel enter the identifier of the indicator they want to query on the query interface, they can either enter it directly or trigger a drop-down control to select the indicator from the displayed indicator list. This application does not impose any restrictions on this.

[0115] In step 702, the third indicator identifier is matched with the identifiers of each indicator in the indicator knowledge graph.

[0116] In this application, the matching degree between the third indicator identifier and the identifiers of each indicator in the indicator knowledge graph can be calculated.

[0117] In step 703, if the third indicator identifier matches the third target indicator, the fourth target indicator associated with the third target indicator in the indicator knowledge graph and the target business relationship information between the third target indicator and the fourth target indicator are determined.

[0118] In this application, if the matching degree between the third indicator identifier and the third target indicator is greater than a preset threshold, it can be considered that the third indicator identifier matches the third target indicator, and the fourth target indicator associated with the third target indicator in the indicator knowledge graph and the target business relationship information between the third target indicator and the fourth target indicator can be determined.

[0119] For example, the third indicator is labeled A1, and the indicators associated with A1 are A2, A3 and A6. Among them, the business relationship between A1 and A2 is unrelated, with a correlation coefficient of 0; the business relationship between A1 and A3 is uncertain, with a correlation coefficient of 0.5; and the business relationship between A1 and A2 is unrelated, with a correlation coefficient of 0.

[0120] In step 704, a third query result is generated based on the third target indicator, the fourth target indicator, and the target business relationship information.

[0121] In this application, a third query result can be generated based on the third target indicator, the fourth target indicator, and the target business relationship information, and the third query result can be displayed on the query interface.

[0122] Based on the above example, the third query result can be that the indicators associated with A1 are A2, A3 and A6. Among them, the business relationship between A1 and A2 is unrelated, with a correlation coefficient of 0; the business relationship between A1 and A3 is non-deterministic, with a correlation coefficient of 0.5; and the business relationship between A1 and A2 is unrelated, with a correlation coefficient of 0.

[0123] In this embodiment, a third indicator relationship query request can also be obtained, and the third indicator identifier in the query request can be matched with the identifiers of each indicator in the indicator knowledge graph. If the third indicator identifier matches the third target indicator, the fourth target indicator associated with the third target indicator and the target business relationship information between the third target indicator and the fourth target indicator in the indicator knowledge graph can be determined. Based on the target business relationship information of the third target indicator and the fourth target indicator, a third query result is generated. Thus, based on the indicator knowledge graph, it is possible to query the indicators associated with a certain indicator and the business relationship information between that indicator and the associated indicators.

[0124] To facilitate understanding of the scheme in this application, the following is combined with... Figures 8-11 Please provide an explanation.

[0125] Figure 8 The document displays a financial business asset monitoring report dated November 30, 2022. The report shows an anomaly in the provincial personal loan growth rate indicator for the D province branch. Using traditional indicator management methods, analyzing this anomaly would require not only knowledge of data processing rules but also extensive database comparisons. However, the proposed solution allows business personnel to right-click on the indicator value to trigger an analysis function list. From this list, they can select "Indicator Source Tracing Analysis" to identify the cause of the anomaly. After receiving the source tracing analysis request, the system can query the indicator knowledge graph based on the identifier of the provincial personal loan growth rate in the request to find related indicators.

[0126] The query results are as follows: Figure 9 As shown, leveraging the characteristics of knowledge graphs, metrics can be presented in the form of a network diagram, allowing business personnel to quickly pinpoint metric issues. According to... Figure 9 It can be seen that the abnormal increase in the proportion of new municipal-level personal loans at the D2 city branch caused the abnormal increase in the proportion of new provincial-level personal loans at the D province branch. In addition, the query results also include information on different dimensions of each indicator, such as institution dimension, date dimension, and currency dimension.

[0127] The proposed solution also supports further downward penetration analysis. This can be triggered by right-clicking on the indicator value of the percentage of new city-level personal loans in the D2 city branch. The interface will display a list of analysis functions, from which business personnel can select indicator source analysis to find the cause of the anomaly. After receiving the indicator source analysis request, the indicator knowledge graph can be queried based on the identifier of the percentage of new city-level personal loans in the D2 city branch in the indicator source analysis request to find the indicators associated with that indicator.

[0128] The final query results are as follows Figure 10As shown, the abnormal increase in the balance of municipal-level personal loan term deposits in the D2 city branch led to an abnormal increase in the proportion of municipal-level personal loans in the D2 city branch, which in turn led to an abnormal increase in the proportion of provincial-level personal loans in the D province branch.

[0129] Additionally, impact analysis of the indicator can be performed to examine what subsequent abnormal indicators this abnormal indicator has led to. Figure 8 From the analysis function list, you can select downstream impact analysis. From there, you can query the indicator knowledge graph based on the provincial personal loan increase ratio identifier in the downstream impact analysis request. The query results are as follows: Figure 11 As shown, according to Figure 11 It can be seen that the proportion of new provincial personal loans of the D Province branch will affect the proportion of new personal loans in South China, the agricultural production and operation loans of the D Province branch, the inclusive micro and small enterprise corporate loans of the D3 City branch of the D Province, and the asset quality of the xx City branch of the D Province, as well as the balance of non-performing loans at the beginning of the year.

[0130] Therefore, for the provincial branch's provincial personal loan growth rate, upstream source analysis and downstream impact analysis can be conducted to analyze the source of the problem. Figure 10 and Figure 11 The query results shown are combined and displayed.

[0131] With the above Figures 1-2 , Figures 5-7 Corresponding to the indicator knowledge graph generation method provided in the embodiments, this application also provides an indicator knowledge graph generation apparatus. Since the indicator knowledge graph generation apparatus provided in the embodiments of this application is similar to the one described above... Figures 1-2 , Figures 5-7 The method for generating an indicator knowledge graph provided in the embodiments corresponds to the method for generating an indicator knowledge graph. Therefore, the implementation method for generating an indicator knowledge graph is also applicable to the indicator knowledge graph generation apparatus provided in the embodiments of this application, and will not be described in detail in the embodiments of this application.

[0132] Figure 12 This is a schematic diagram of the structure of an indicator knowledge graph generation device shown in one embodiment of this application.

[0133] Reference Figure 12 The knowledge graph generation device 1200 may include:

[0134] The first acquisition module 1210 is configured to acquire indicator relationship configuration information;

[0135] The second acquisition module 1220 is configured to parse the indicator relationship configuration information to obtain the business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship.

[0136] The first generation module 1230 is configured to generate an indicator knowledge graph based on the business relationships and attribute information corresponding to multiple pairs of indicators.

[0137] In one possible implementation of this application embodiment, the first acquisition module 1210 is configured as follows:

[0138] Upon receiving the indicator relationship configuration instruction, the indicator relationship configuration interface is displayed, which includes two indicator input boxes, a relationship type input box, and an attribute information input box.

[0139] Based on the detected metric input operations, two metrics to be configured are identified.

[0140] Based on the detected relationship type input operation, determine the first target business relationship between the two metrics to be configured;

[0141] Based on the detected attribute information input operation, determine the target attribute information of the first target business relationship;

[0142] If the operation of configuring the indicator relationship is detected as complete, obtain the indicator relationship configuration information corresponding to the two indicators to be configured.

[0143] In one possible implementation of this application embodiment, the first acquisition module 1210 is configured as follows:

[0144] The first target business relationship is matched with multiple attribute types respectively;

[0145] The attribute type that matches the first target business relationship is identified as the target attribute type, and the corresponding attribute information input box is marked and displayed.

[0146] The target attribute information is determined based on the input operation of the attribute information input box corresponding to the detected target attribute type.

[0147] In one possible implementation of this application embodiment, the device may further include:

[0148] The second generation module is configured to generate prompt information based on the target attribute type, wherein the prompt information is used to provide descriptive information about the target attribute type.

[0149] In one possible implementation of this application embodiment, the device may further include:

[0150] The third acquisition module is configured to acquire a first indicator relationship query request, wherein the first indicator relationship query request includes a first indicator identifier and a second indicator identifier;

[0151] The first matching module is configured to match the first indicator identifier and the second indicator identifier with the identifiers of each indicator in the indicator knowledge graph, respectively.

[0152] The first determining module is configured to determine the business path from the first target indicator to the second target indicator in the indicator knowledge graph when the first indicator identifier matches the first target indicator and the second indicator identifier matches the second target indicator.

[0153] The third generation module is configured to generate the first query result based on the business path.

[0154] In one possible implementation of this application embodiment, the device may further include:

[0155] The fourth acquisition module is configured to acquire a second indicator relationship query request, wherein the second indicator relationship query request includes a second target business relationship;

[0156] The second matching module is configured to match the second target business relationship with the business relationships between pairs of indicators in the indicator knowledge graph;

[0157] The fourth generation module is configured to generate a second query result based on the indicators that match the business relationships in the indicator knowledge graph with the second target business relationships.

[0158] In one possible implementation of this application embodiment, the device may further include:

[0159] The fifth acquisition module is configured to acquire a third indicator relationship query request, wherein the third indicator relationship query request includes a third indicator identifier;

[0160] The third matching module is configured to match the third indicator identifier with the identifiers of each indicator in the indicator knowledge graph;

[0161] The second determination module is configured to determine, when the third indicator identifier matches the third target indicator, the fourth target indicator associated with the third target indicator in the indicator knowledge graph and the target business relationship information between the third target indicator and the fourth target indicator.

[0162] The fifth generation module is configured to generate the third query result based on the target business relationship information of the third target indicator and the fourth target indicator.

[0163] In this embodiment, by acquiring indicator relationship configuration information and parsing it, business relationship information corresponding to multiple pairs of indicators is obtained. Then, based on the business relationships and attribute information corresponding to the multiple pairs of indicators, an indicator knowledge graph is generated. Therefore, an indicator knowledge graph can be generated based solely on the business relationship information between multiple pairs of indicators. Based on the generated indicator knowledge graph, the business relationships between multiple indicators can be analyzed, and the scope of influence of the indicators can be located.

[0164] In an exemplary embodiment, an electronic device is also proposed.

[0165] The electronic devices include:

[0166] processor;

[0167] Memory used to store processor-executable instructions;

[0168] The processor is configured to execute instructions to implement the method for generating an indicator knowledge graph as proposed in any of the foregoing embodiments.

[0169] As an example, Figure 13 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this application, as follows: Figure 13 As shown, the aforementioned electronic device 1300 may further include:

[0170] The memory 1310 and the processor 1320 are connected by a bus 1330, which connects different components (including the memory 1310 and the processor 1320). The memory 1310 stores a computer program, and when the processor 1320 executes the program, it implements the method for generating an indicator knowledge graph as described in the embodiments of this application.

[0171] Bus 1330 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0172] Electronic device 1300 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 1300, including volatile and non-volatile media, removable and non-removable media.

[0173] Memory 1310 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1340 and / or cache memory 1350. Electronic device 1300 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 1360 may be used to read and write non-removable, non-volatile magnetic media (… Figure 13 Not shown; usually referred to as a "hard drive"). Although Figure 13 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 1330 via one or more data media interfaces. Memory 1310 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0174] A program / utility 1380 having a set (at least one) of program modules 1370 may be stored, for example, in memory 1310. Such program modules 1370 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 1370 typically perform the functions and / or methods described in the embodiments of this application.

[0175] Electronic device 1300 can also communicate with one or more external devices 1390 (e.g., keyboard, pointing device, display 1391, etc.), and with one or more devices that enable a user to interact with electronic device 1300, and / or with any device that enables electronic device 1300 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 1392. Furthermore, electronic device 1300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1393. As shown, network adapter 1393 communicates with other modules of electronic device 1300 via bus 1330. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0176] The processor 1320 performs various functional applications and data processing by running programs stored in the memory 1310.

[0177] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the method for generating the indicator knowledge graph in the embodiments of this application, and will not be repeated here.

[0178] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions that can be executed by a processor of an electronic device to perform the method proposed in any of the above embodiments. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0179] In an exemplary embodiment, a computer program product is also provided, including a computer program / instructions, characterized in that the computer program / instructions, when executed by a processor, implement the method proposed in any of the above embodiments.

[0180] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0181] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for generating an indicator knowledge graph, characterized in that, include: Upon receiving the indicator relationship configuration instruction, the indicator relationship configuration interface is displayed, which includes two indicator input boxes, a relationship type input box, and an attribute information input box. Based on the detected metric input operations, two metrics to be configured are identified. Based on the detected relationship type input operation, determine the first target business relationship between the two configurable metrics; The first target business relationship is matched with multiple attribute types respectively; The attribute type that matches the first target business relationship is determined as the target attribute type, and the attribute information input box corresponding to the target attribute type is marked and displayed; Based on the input operation of the attribute information input box corresponding to the detected target attribute type, the target attribute information of the first target business relationship is determined; Upon detecting that the indicator relationship configuration is complete, obtain the indicator relationship configuration information corresponding to the two indicators to be configured; The indicator relationship configuration information is parsed to obtain business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship. The business relationship between the two indicators includes unrelated, non-deterministic, and deterministic relationships. The attribute information of the business relationship includes relationship function, correlation coefficient, and relationship influence type. Based on the business relationships corresponding to the multiple pairs of indicators and the attribute information, an indicator knowledge graph is generated.

2. The method as described in claim 1, characterized in that, Also includes: Based on the target attribute type, a prompt message is generated, wherein the prompt message is used to provide descriptive information about the target attribute type.

3. The method as described in claim 1, characterized in that, Also includes: Obtain a first indicator relationship query request, wherein the first indicator relationship query request includes a first indicator identifier and a second indicator identifier; The first indicator identifier and the second indicator identifier are matched with the identifiers of each indicator in the indicator knowledge graph, respectively. If the first indicator identifier matches the first target indicator and the second indicator identifier matches the second target indicator, determine the business path from the first target indicator to the second target indicator in the indicator knowledge graph; Based on the business path, generate the first query result.

4. The method as described in claim 1, characterized in that, Also includes: Obtain a second indicator relationship query request, wherein the second indicator relationship query request includes a second target business relationship; Match the second target business relationship with the business relationships between pairs of indicators in the indicator knowledge graph; A second query result is generated based on the indicators in the indicator knowledge graph that match the business relationships with the second target business relationship.

5. The method as described in claim 1, characterized in that, Also includes: Obtain a third indicator relationship query request, wherein the third indicator relationship query request includes a third indicator identifier; Match the third indicator identifier with the identifiers of each indicator in the indicator knowledge graph; If the third indicator identifier matches the third target indicator, determine the fourth target indicator associated with the third target indicator in the indicator knowledge graph and the target business relationship information between the third target indicator and the fourth target indicator; Based on the target business relationship information of the third target indicator and the fourth target indicator, a third query result is generated.

6. A device for generating an indicator knowledge graph, characterized in that, include: The first acquisition module is configured to, upon receiving an indicator relationship configuration instruction, display an indicator relationship configuration interface, wherein the configuration interface includes two indicator input boxes, a relationship type input box, and an attribute information input box; determine two indicators to be configured based on detected indicator input operations; determine a first target business relationship between the two indicators to be configured based on detected relationship type input operations; match the first target business relationship with multiple attribute types; determine the attribute type that matches the first target business relationship as the target attribute type and mark and display the attribute information input box corresponding to the target attribute type; determine the target attribute information of the first target business relationship based on the detected input operations of the attribute information input box corresponding to the target attribute type; and, upon detecting an indicator relationship configuration completion operation, acquire the indicator relationship configuration information corresponding to the two indicators to be configured. The second acquisition module is configured to parse the indicator relationship configuration information to obtain business relationship information corresponding to multiple pairs of indicators. The business relationship information corresponding to each pair of indicators includes the business relationship between the two indicators in each pair and the attribute information of the business relationship. The business relationship between the two indicators includes unrelated, non-deterministic, and deterministic relationships. The attribute information of the business relationship includes relationship function, correlation coefficient, and relationship influence type. The first generation module is configured to generate an indicator knowledge graph based on the business relationships corresponding to the multiple pairs of indicators and the attribute information.

7. The apparatus as claimed in claim 6, characterized in that, Also includes: The second generation module is configured to generate prompt information based on the target attribute type, wherein the prompt information is used to provide descriptive information about the target attribute type.

8. The apparatus as claimed in claim 6, characterized in that, Also includes: The third acquisition module is configured to acquire a first indicator relationship query request, wherein the first indicator relationship query request includes a first indicator identifier and a second indicator identifier; The first matching module is configured to match the first indicator identifier and the second indicator identifier with the identifiers of each indicator in the indicator knowledge graph, respectively. The first determining module is configured to determine the business path from the first target indicator to the second target indicator in the indicator knowledge graph when the first indicator identifier matches the first target indicator and the second indicator identifier matches the second target indicator. The third generation module is configured to generate the first query result based on the business path.

9. The apparatus as claimed in claim 6, characterized in that, Also includes: The fourth acquisition module is configured to acquire a second indicator relationship query request, wherein the second indicator relationship query request includes a second target business relationship; The second matching module is configured to match the second target business relationship with the business relationships between pairs of indicators in the indicator knowledge graph; The fourth generation module is configured to generate a second query result based on the indicators that match the business relationships in the indicator knowledge graph with the second target business relationship.

10. The apparatus as claimed in claim 6, characterized in that, Also includes: The fifth acquisition module is configured to acquire a third indicator relationship query request, wherein the third indicator relationship query request includes a third indicator identifier; The third matching module is configured to match the third indicator identifier with the identifiers of each indicator in the indicator knowledge graph; The second determining module is configured to, when the third indicator identifier matches the third target indicator, determine the fourth target indicator associated with the third target indicator in the indicator knowledge graph and the target business relationship information between the third target indicator and the fourth target indicator. The fifth generation module is configured to generate a third query result based on the target business relationship information of the third target indicator and the fourth target indicator.

11. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images