Revenue analysis method, apparatus, device, and storage medium

Abstract

The application discloses an income analysis method and device, equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring first income data in a target period; determining income change data in the target period based on second income data and the first income data; the second income data is income data in a historical period; determining a target analysis path based on the income change data and a preset knowledge graph, and determining an income analysis result based on the target analysis path; the preset knowledge graph comprises business characteristics of each income business in the income data and income factors corresponding to each income business one by one; the target analysis path is an analysis path that meets a preset condition in at least one analysis path determined by the preset knowledge graph based on the income change data; the target analysis path comprises at least one income factor; and the income analysis result comprises the income factor in the target analysis path. Therefore, the operation data analysis efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a revenue analysis method, apparatus, device, and storage medium. Background Technology

[0002] As the market continues to expand, operators are offering increasingly diverse and abundant products to users. Consequently, the amount of data that operators acquire is also increasing.

[0003] Currently, with the acquisition of large amounts of operational data, manual analysis is required. Furthermore, the sheer volume and numerous data tags of operational data make it difficult to analyze. Summary of the Invention

[0004] This application provides a revenue analysis method, apparatus, device, and storage medium to improve the efficiency of operational data analysis. The technical solution of this application is as follows:

[0005] According to a first aspect of this application, a revenue analysis method is provided, the method comprising: acquiring first revenue data within a target period; determining revenue change data within the target period based on second revenue data and the first revenue data; the second revenue data being revenue data from historical periods; determining a target analysis path based on the revenue change data and a preset knowledge graph; and determining a revenue analysis result based on the target analysis path; the preset knowledge graph including business characteristics of each revenue business in the revenue data and revenue factors corresponding one-to-one with each revenue business; the target analysis path being an analysis path that meets preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data; the target analysis path including at least one revenue factor; and the revenue analysis result including the revenue factor in the target analysis path.

[0006] In one possible implementation, the above-mentioned "determining the target analysis path based on operational change data and a preset knowledge graph" includes: updating the preset knowledge graph based on operational change data to obtain an updated knowledge graph; and calculating the weight of each factor in the updated knowledge graph based on a preset entropy method to determine the target analysis path.

[0007] In one possible implementation, the above-mentioned "calculating the weight of each factor in the updated knowledge graph based on the preset entropy method to determine the target analysis path" includes: traversing the updated knowledge graph using a depth-first search algorithm to obtain multiple analysis paths, and calculating the weight of each analysis path in the multiple analysis paths based on the preset entropy method to determine the contribution value of the multiple analysis paths; the contribution value is positively correlated with the weight. Based on the contribution values ​​of the multiple analysis paths, a target analysis path is determined; the target analysis path is the analysis path whose contribution value is greater than a first preset threshold.

[0008] In one possible implementation, the above-mentioned "calculating the weight of each factor in the updated knowledge graph based on the preset entropy method to determine the target analysis path" includes: calculating the weight of each factor in the updated knowledge graph based on the preset entropy method, and traversing the updated knowledge graph based on the weight of each factor in the updated knowledge graph and the width traversal algorithm to determine the target analysis path, wherein the factors in the target analysis path are the factors with the largest weight ratio during the traversal of the updated knowledge graph.

[0009] In one possible implementation, the method further includes: acquiring multiple factors and basic attributes of each factor; the basic attributes are used to indicate the business information of the factors. Based on the multiple factors and the basic attributes of each factor, a preset knowledge graph is determined.

[0010] In one possible implementation, the method further includes: determining target anomaly factors based on income analysis results, and displaying the target anomaly factors.

[0011] In one possible implementation, the above-mentioned "displaying target anomaly factor" includes: displaying the target anomaly factor based on a preset color when the weight of the target anomaly factor is greater than a second preset threshold.

[0012] According to a second aspect of this application, a revenue analysis apparatus is provided, comprising: an acquisition unit for acquiring first revenue data within a target period; a determination unit for determining revenue change data within the target period based on second revenue data and the first revenue data; wherein the second revenue data is revenue data from a historical period; the determination unit for determining a target analysis path based on the revenue change data and a preset knowledge graph; wherein the preset knowledge graph includes business characteristics of each revenue business in the revenue data and revenue factors corresponding to each revenue business; the target analysis path is an analysis path that meets preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data; the target analysis path includes at least one revenue factor; and a determination unit for determining a revenue analysis result based on the target analysis path; wherein the revenue analysis result includes the revenue factor in the target analysis path.

[0013] In one possible implementation, the determining unit is specifically used for: updating a preset knowledge graph based on operational change data to obtain an updated knowledge graph; and calculating the weight of each factor in the updated knowledge graph based on a preset entropy method to determine the target analysis path.

[0014] In one possible implementation, the determining unit is further specifically configured to: traverse the updated knowledge graph using a depth-first search algorithm to obtain multiple analysis paths, and calculate the weight of each analysis path based on a preset entropy method to determine the contribution value of the multiple analysis paths; the contribution value is positively correlated with the weight. Based on the contribution values ​​of the multiple analysis paths, a target analysis path is determined; the target analysis path is the analysis path whose contribution value is greater than a first preset threshold.

[0015] In one possible implementation, the determining unit is further specifically used for: calculating the weight of each factor in the updated knowledge graph based on the preset entropy method, and traversing the updated knowledge graph based on the weight of each factor in the updated knowledge graph and the width traversal algorithm to determine the target analysis path, wherein the factors in the target analysis path are the factors with the largest weight proportion during the traversal of the updated knowledge graph.

[0016] In one possible implementation, the acquisition unit is further configured to acquire multiple factors and basic attributes of each factor; the basic attributes are used to indicate the business information of the factors. The determination unit is further configured to determine a preset knowledge graph based on the multiple factors and the basic attributes of each factor.

[0017] In one possible implementation, the revenue analysis device further includes a display unit. The determination unit is further configured to determine target anomaly factors based on the revenue analysis results. The display unit is configured to display the target anomaly factors.

[0018] In one possible implementation, the display unit is specifically used to: display the target anomaly factor based on a preset color when the weight of the target anomaly factor is greater than a second preset threshold.

[0019] According to a third aspect of this application, an electronic device is provided, comprising: a processor and a communication interface; the communication interface and the processor are coupled, the processor being used to run computer programs or instructions to implement the revenue analysis method as described in the first aspect.

[0020] According to a fourth aspect of this application, a computer-readable storage medium is provided, which stores instructions that, when executed by a computer, perform the revenue analysis method as described in the first aspect.

[0021] According to a fifth aspect of this application, a computer program product is provided, the computer program product including computer instructions, which, when executed on an electronic device, enable the electronic device to perform the revenue analysis method as described in the first aspect.

[0022] This application provides a revenue analysis method that offers the following advantages: Given initial operational data, it determines the change in revenue within a target period. Furthermore, based on the change in revenue within the target period and a pre-defined knowledge graph, it determines a target analysis path containing factors influencing the change in revenue within the target period, and then determines the revenue analysis results based on this target analysis path. Thus, with operational data available, revenue analysis results are obtained through the change in revenue and the knowledge graph, eliminating the need for manual analysis of large amounts of data and improving the efficiency of operational data analysis.

[0023] It should be noted that the technical effects of any of the implementation methods in aspects two through five can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.

[0024] 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

[0025] 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.

[0026] Figure 1 A schematic diagram of the structure of the revenue analysis system provided in the embodiments of this application;

[0027] Figure 2 One of the flowcharts for the revenue analysis method provided in the embodiments of this application;

[0028] Figure 3 A second flowchart illustrating the revenue analysis method provided in this application embodiment;

[0029] Figure 4 A factor-relationship logic diagram of the knowledge graph provided in the embodiments of this application;

[0030] Figure 5 This is a schematic diagram of the traversal results provided in the embodiments of this application;

[0031] Figure 6 A schematic diagram of a factor topology graph provided in an embodiment of this application;

[0032] Figure 7 A schematic diagram of the shortest path in a factor topology graph provided in an embodiment of this application;

[0033] Figure 8 One of the schematic diagrams showing the revenue analysis results provided in the embodiments of this application;

[0034] Figure 9A second schematic diagram showing the revenue analysis results provided in an embodiment of this application;

[0035] Figure 10 The third schematic diagram showing the revenue analysis results provided in the embodiments of this application;

[0036] Figure 11 Fourth illustration of the revenue analysis results provided in the embodiments of this application;

[0037] Figure 12 Fifth illustration of the revenue analysis results provided in the embodiments of this application;

[0038] Figure 13 Sixth schematic diagram showing the revenue analysis results provided in the embodiments of this application;

[0039] Figure 14 Seventh illustration of the revenue analysis results provided for the embodiments of this application;

[0040] Figure 15 The third flowchart of the revenue analysis method provided in the embodiments of this application;

[0041] Figure 16 This is a schematic diagram of the structure of an income analysis device provided in an embodiment of this application;

[0042] Figure 17 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0043] 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.

[0044] 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.

[0045] Before providing a detailed introduction to the transaction methods provided in this application, let's briefly introduce the application scenarios and implementation environment involved in this application.

[0046] Before briefly introducing the application scenarios involved in this application, let's introduce the terminology involved in this application.

[0047] Knowledge graph technology is a technique that describes the relationships between things using a graph model. Essentially, it's a semantic network that reveals the relationships between entities. Typically, a knowledge graph consists of multiple nodes. In this embodiment, the knowledge graph indicates the relationships between business processes.

[0048] Entropy is a measure of uncertainty. The greater the amount of information, the less uncertainty there is, and the lower the entropy. Entropy value is used to determine the degree of dispersion and importance of a feature.

[0049] This application provides a brief overview of its application scenarios.

[0050] As the market continues to expand, operators are offering increasingly diverse and abundant products to users. Consequently, the amount of data that operators acquire is also increasing.

[0051] Currently, with the acquisition of large amounts of operational data, manual analysis is required. Furthermore, the sheer volume and numerous data tags of operational data make it difficult to analyze.

[0052] Specifically, in the rapidly evolving information age, telecom operators' customers have new consumption demands regarding goods, content, and services. To meet these demands, operators have launched a wide variety of services. This has led to a surge in the amount of data operators acquire. Consequently, the difficulty of manually analyzing operational data has increased, making it challenging for humans to obtain accurate results from massive amounts of data.

[0053] In addition, due to staff shortages and a lack of analytical tools for grid workers, units below the prefecture level are unable to independently complete income analysis work and require assistance from the municipal company, resulting in a passive approach to their work.

[0054] To address the aforementioned issues, this application provides a revenue analysis method. The method includes: determining revenue change data within a target period based on second revenue data and first revenue data; the second revenue data is historical period revenue data; determining a target analysis path based on the revenue change data and a preset knowledge graph; and determining the revenue analysis result based on the target analysis path; the preset knowledge graph includes the business characteristics of each revenue business in the revenue data and the revenue factors corresponding to each revenue business; the target analysis path is an analysis path that meets preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data; the target analysis path includes at least one revenue factor; and the revenue analysis result includes the revenue factor in the target analysis path.

[0055] In this way, given the initial revenue data, the change in revenue within the target period is determined. Furthermore, based on the change in revenue within the target period and a pre-defined knowledge graph, a target analysis path containing factors influencing the change in revenue within the target period is determined, and the revenue analysis results are determined based on this target analysis path. Thus, with operational data, revenue analysis results are obtained through the change in revenue and the knowledge graph, eliminating the need for manual analysis of large amounts of data and improving the efficiency of operational data analysis.

[0056] Based on the above inventive concept, this application provides an income analysis system 100. For example... Figure 1 As shown, the revenue analysis system 100 includes an electronic device 101. The electronic device 101 stores a pre-defined knowledge graph.

[0057] In some embodiments, the revenue analysis system 100 includes an electronic device 101 and a server 102. The server 102 stores a preset knowledge graph in advance.

[0058] In some embodiments, the revenue data in this application is a type of operational data.

[0059] When electronic device 101 receives operational data input by the user, it transmits the operational data to server 102. Correspondingly, upon receiving the operational data from electronic device 101, server 102 analyzes the operational data based on a preset knowledge graph to obtain revenue analysis results. Further, server 102 sends the revenue analysis results back to electronic device 101.

[0060] Correspondingly, electronic device 101 receives the revenue analysis results sent by server 102 and displays the revenue analysis results to the user.

[0061] Electronic device 101 can be a mobile phone, tablet computer, desktop computer, laptop computer, etc. Server 102 can be a standalone server or a server cluster composed of multiple servers.

[0062] The preset knowledge graph in this embodiment is a pre-trained knowledge graph. Specifically, the process of building the preset knowledge graph is as follows: Figure 2 As shown, it includes S201-S205.

[0063] S201, Knowledge Modeling.

[0064] Specifically, the knowledge modeling process includes ontology modeling, topic modeling, knowledge representation, and the creation of dynamic graphs.

[0065] S202, Knowledge Establishment and Integration.

[0066] Specifically, knowledge creation and integration includes knowledge definition, knowledge completion, knowledge review, attribution and unification, expert experience, relationship building, and relationship review.

[0067] S203, Knowledge Storage.

[0068] Specifically, knowledge storage includes distributed storage, dynamic schemas, entity nesting, and composite types.

[0069] S204, Knowledge Computing.

[0070] Specifically, knowledge computing includes relation prediction, causal inference, knowledge reasoning, and potential speculation.

[0071] S205, Knowledge Empowerment.

[0072] Specifically, knowledge empowerment includes attribution diagnosis, correlation analysis, cascading effects, and potential impacts.

[0073] In some embodiments, multiple knowledge graphs are constructed in this application to analyze various operational data.

[0074] To facilitate a better understanding of the revenue analysis method in the embodiments of this application, the revenue analysis method in the embodiments of this application is described below.

[0075] In one design, it's good to improve the efficiency of operational data analysis. For example... Figure 3 As shown, the revenue analysis method provided in this application includes: S301-S304.

[0076] S301, Obtain the first revenue data within the target period.

[0077] As one possible approach, electronic devices retrieve first revenue data for a target period within a budgeted region from a pre-installed application.

[0078] In some embodiments, revenue data includes revenue data, number of users, and business type, etc.

[0079] For example, revenue data includes: total revenue, IPTV (Internet Protocol Television) revenue, mobile network revenue, broadband revenue, and service types. Mobile network revenue is further divided into 5G A package revenue, 5G B package revenue, 5G C package revenue, and 4G A package revenue. User numbers for each service are also included, such as the number of users on the 5G A package, 5G B package, and 4G A package. User parameters include new subscribers and existing subscribers.

[0080] In this embodiment of the application, the income data to be analyzed is referred to as the first income data, and the income data used as a reference is referred to as the second income data.

[0081] For example, the target period is the current month, but it can be the same day or half a year. This application does not specifically limit this.

[0082] For example, an electronic device retrieves revenue data for City A from March 1, 2023 to March 31, 2023. Another example is an electronic device retrieving revenue data for Community A in City A from March 1, 2023 to March 31, 2023.

[0083] S302. Based on the second revenue data and the first revenue data, determine the revenue change data within the target period.

[0084] The second revenue data is the revenue data for historical periods.

[0085] One possible approach is for an electronic device to acquire second revenue data and calculate the difference between the second revenue data and the first revenue data to determine the revenue change data within a target period.

[0086] In some embodiments, the electronic device, upon acquiring first revenue data and second revenue data, calculates the change data of total revenue, the change data of revenue for each business segment, and the change data of the number of employees for each business segment, one by one.

[0087] For example, taking the first revenue data as the revenue data for the current month and the second revenue data as the revenue data for the previous month as an example. Electronic device operation change data includes: changes in total revenue, changes in 5G A package revenue, changes in 5G B package revenue, changes in 5G C package revenue, changes in 4G A package revenue, changes in the number of users of 5G A packages, changes in the number of users of 5G B packages, changes in the number of users of 5G C packages, and changes in 4G C package revenue, etc.

[0088] S303. Based on income change data and a pre-set knowledge graph, determine the target analysis path.

[0089] The preset knowledge graph includes the business characteristics of each revenue business in the revenue data and the revenue factors that correspond one-to-one with each revenue business. The target analysis path is the analysis path that meets the preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data. The target analysis path includes at least one revenue factor.

[0090] The preset knowledge graph is used to indicate the relationship between multiple factors. The target analysis path includes at least one factor, and one factor corresponds to one business.

[0091] One possible approach is to import operational change data into a pre-defined knowledge graph and update the attributes of each factor. Furthermore, based on a pre-defined traversal algorithm and entropy analysis, the target analysis path is determined.

[0092] For a detailed implementation of this step, please refer to the subsequent steps; it will not be repeated here.

[0093] S304. Determine the revenue analysis results based on the target analysis path.

[0094] The income analysis results include the income factors in the target analysis path.

[0095] As one possible approach, electronic devices, given a defined target analysis path, determine the revenue analysis results based on the factors and factor attributes within that path.

[0096] For example, consider a decrease in total revenue. When an electronic device obtains the target analysis path: total revenue decrease - 5G Package A - secondary SIM cards for 5G Package A, and considering an 80% decrease in 5G Package A revenue and an increase in secondary SIM cards for 5G Package A, it determines that the decrease in total revenue is due to an excessive decrease in 5G Package A revenue; specifically, it's because too many secondary SIM cards were activated for 5G Package A.

[0097] For example, consider the increase in total revenue. When an electronic device obtains the target analysis path: Total Revenue Increase - 5G Package A - Number of 5G Package A Users, and considering a 50% decrease in 5G Package A users and an increase in the number of users subscribing to 5G Package A, it determines that the increase in total revenue is due to the increase in revenue from 5G Package A; specifically, it's due to the increase in the number of users subscribing to 5G Package A.

[0098] The revenue analysis method provided in this application offers the following advantages: Upon obtaining first revenue data, the method determines the change in revenue data within a target period. Furthermore, based on the change in revenue data within the target period and a preset knowledge graph, a target analysis path containing factors influencing revenue changes within the target period is determined, and the revenue analysis result is determined based on the target analysis path. Thus, with existing revenue data, revenue analysis results are obtained through the change in revenue and the knowledge graph, eliminating the need for manual analysis of large amounts of data and improving the efficiency of revenue data analysis.

[0099] In one design, to replace manual root cause analysis for reducing income, the optimal analysis path is determined. S303 provided in this application embodiment includes: S3031-S3032.

[0100] S3031. Update the preset knowledge graph based on operational change data to obtain the updated knowledge graph.

[0101] As one possible approach, electronic devices, given changes in operational data, update associated factors in a pre-defined knowledge graph based on changes in revenue data, thereby obtaining an updated knowledge graph.

[0102] In some embodiments, the electronic device acquires changes in total revenue, IPTV revenue, bandwidth revenue, mobile network revenue, 5G A package revenue, 5G B package revenue, 5G C package revenue, and 4G A package revenue, and updates the attributes of the total revenue factor, IPTV factor, bandwidth factor, mobile network factor, 5G A package factor, 5G B package factor, 5G C package factor, and 4G A package in a preset knowledge graph.

[0103] For example, electronic devices can add operational change data to relevant factors in a pre-defined knowledge graph.

[0104] It should be noted that in this embodiment, one factor is equivalent to one node. The updated knowledge graph includes the changes in revenue data within the target period.

[0105] S3032. Calculate the weight of each factor in the updated knowledge graph based on the preset entropy method to determine the target analysis path.

[0106] As one possible approach, upon acquiring an updated knowledge graph, the electronic device calculates the entropy value of each factor in the updated knowledge graph based on a pre-defined entropy method, and then calculates the contribution ratio of each factor. Furthermore, the target analysis path is determined based on the contribution ratio of each factor.

[0107] In some embodiments, the breadth-first traversal algorithm and the entropy method are used to calculate the factor with the highest contribution ratio at each layer, and then the target analysis path is calculated layer by layer.

[0108] In some embodiments, the updated knowledge graph is traversed using a depth-first search algorithm to obtain multiple analysis paths. The analysis path with the highest contribution ratio among the multiple analysis paths is calculated based on the entropy method. Furthermore, the analysis path with the highest contribution ratio is determined as the target analysis path.

[0109] Understandably, the entropy method is used to identify the factors with higher contributions from multiple factors, thereby determining the target analysis path. Based on the target analysis path, the income analysis results are determined. In this way, determining the target analysis path based on knowledge graphs replaces manual root cause analysis of income reduction and identifies the optimal analysis path.

[0110] In one design, to determine the correlation factors to changes in income, S3032 provided in this application embodiment includes: S401-S403.

[0111] S401. Based on the depth-first traversal algorithm, the updated knowledge graph is traversed to obtain multiple analysis paths.

[0112] In some embodiments, an initial factor is determined, and multiple analysis paths are obtained by traversing the updated knowledge graph based on the initial factor and a depth-first traversal algorithm.

[0113] For example, with the initial factor being total revenue, the electronic device uses the total revenue factor as the first node in a depth-first traversal and employs a depth-first traversal algorithm to calculate the analysis path traversed from the total revenue factor.

[0114] S402. Calculate the weight of each analysis path in the multiple analysis paths based on the preset entropy value method, so as to determine the contribution value of the multiple analysis paths.

[0115] The contribution value is positively correlated with the weight.

[0116] S403. Determine the target analysis path based on the contribution values ​​of multiple analysis paths.

[0117] The target analysis path is the analysis path whose contribution value is greater than the first preset threshold.

[0118] Understandably, a depth-first search algorithm is used to traverse the updated knowledge graph from the initial factor (e.g., total income) to identify the related factors that influence the initial factor, thereby obtaining the income analysis results.

[0119] In one design, to determine the correlation factors to changes in revenue, S3032 provided in the embodiments of this application may further include: S404-S405.

[0120] S404. Calculate the weight of each factor in the updated knowledge graph based on the preset entropy method.

[0121] S405. Based on the weight of each factor in the updated knowledge graph and the width traversal algorithm, traverse the updated knowledge graph to determine the target analysis path.

[0122] Among them, the factors in the target analysis path are those with the largest weight during the traversal and update of the knowledge graph.

[0123] To better understand the knowledge graphs and corresponding algorithms in the embodiments of this application, the algorithm principles involved in the embodiments of this application are explained below.

[0124] In this embodiment, the knowledge graph's knowledge definition factors and relationship storage are handled by Neo4j at the underlying level in a graph-like manner. This method allows for efficient implementation starting from a specific node. By analyzing the relationships between nodes, explicit and implicit relationships between two nodes are identified. Neo4j is composed of an attribute graph model formed through two most important elements—nodes and relationships—as shown below. Figure 4 As shown.

[0125] exist Figure 4 The diagram illustrates that the composition of an attribute graph includes record factors, relationships, and data. Specifically, the graph records nodes and relationships; nodes contain attributes, and relationships contain attributes and the connections between nodes.

[0126] In some embodiments, each graph model records nodes and relationships. Relationships and nodes can have their own attributes, and nodes can be assigned multiple labels (categories).

[0127] Secondly, factors are accessed using a graph traversal algorithm. Graph traversal algorithms are divided into depth-first and breadth-first searches. For example, ... Figure 5 As shown, Figure 5 Display the original data, the depth-first traversal result, and the breadth-first traversal result. The original data consists of five factors (numbered 1, 2, 3, 4, 5) and five edges (1-2, 1-3, 1-5, 2-4, 3-5). Now, we will start traversing the graph from factor 1 as the vertex (traversal means visiting each vertex once).

[0128] Furthermore, the traversal results are calculated based on the preset entropy value method.

[0129] Understandably, by combining depth-first traversal and / or breadth-first traversal algorithms, the importance of all nodes in the graph can be calculated sequentially using entropy analysis and explicitness analysis.

[0130] In some embodiments, calculating the contribution ratio using the preset entropy method may include the following steps:

[0131] S1. Obtain the data matrix.

[0132] For example, the data matrix is ​​as follows:

[0133] Where n represents the number of schemes and m represents the number of indicators. Both n and m are natural numbers greater than 1.

[0134] For example, X ij This represents the value of the j-th indicator in the i-th scheme.

[0135] S2, Data normalization processing.

[0136] For example, the normalization formula is as follows:

[0137]

[0138] Among them, X ij Let represent the value of the j-th index in the i-th scheme, where i≤n,j≤m.

[0139] S3. Calculate the proportion of the i-th option under the j-th indicator to that indicator.

[0140] Specifically, the proportion of the i-th option under the j-th indicator is calculated using the following formula (Formula 2).

[0141]

[0142] Where, p ij This indicates the proportion of the i-th option under the j-th indicator to that indicator.

[0143] S4. Calculate the entropy value of the j-th index.

[0144] The formula for calculating the entropy value of the index is shown in Formula 3 below.

[0145]

[0146] Where k > 0, e j ≥0, the constant k is related to the number of samples m.

[0147] For example, Thus, 0 ≤ e ≤ 1.

[0148] S5. Calculate the difference coefficient of the j-th indicator.

[0149] The formula for calculating the j-th indicator is shown in Formula 4 below.

[0150] g j =1-e j Formula 4

[0151] It needs to be explained that g j The larger the value, the more important it is. For the j-th indicator, the indicator value X... ij The greater the difference, the greater its impact on the evaluation of the scheme, and the smaller the entropy value.

[0152] S6. Calculate the weights and percentages of each node.

[0153] The formula for calculating the weights is shown in Formula 5 below.

[0154]

[0155] Among them, W j Let g represent the weight of the j-th scheme. j Let j represent the j-th indicator.

[0156] Next, the Floyd-Warshall dynamic programming algorithm is used to solve for the shortest path. The basic idea of ​​the Floyd algorithm is to create two matrices to store the data: a contiguous matrix D to store the path data, and another matrix P to store the intermediate point data, and finally find the shortest path between any two points.

[0157] For example, matrix D is:

[0158] Matrix P is:

[0159] Where 'a' represents the path value between vertices, and 'v' represents each vertex. If the number of vertices in the path planning is N, then matrix D and matrix P need to be updated N times. Initially, the search starts from the first point, and then matrix D is iteratively updated N times. The iteration formula is shown in Formula 6 below.

[0160]

[0161] Thus, in each iteration, the shortest path from vertex i,j to vertex k will be calculated.

[0162] For example, combining Figure 6 ,exist Figure 6Using a topological graph with 6 vertices as an example, this paper solves for the shortest path from point A1 to point A6 for a service robot in a Robot Operating System (ROS). Finally, as shown... Figure 7 As shown, for the robot to move from point A1 to point A6, its shortest path should be planned as A1-A2-A4-A6.

[0163] In one design, the revenue analysis method provided in this application embodiment further includes: S305-S306.

[0164] S305. Obtain multiple factors and the basic attributes of each factor.

[0165] Among them, the basic attributes are used to indicate the business information of the factors.

[0166] As one possible approach, electronic devices acquire multiple factors and the basic properties of each of the multiple factors.

[0167] For example, multiple factors include user-level factors, IPTV factors, bandwidth factors, and mobile network factors. User-level factors include type and description; IPTV factors include type and parameters; bandwidth factors include type and parameters; and mobile network factors include type and parameters. Additionally, basic attributes may include relationships between multiple factors.

[0168] S306. Based on the factors and the basic attributes of each factor, determine the preset knowledge graph.

[0169] As one possible approach, an electronic device, after acquiring multiple factors, the basic attributes of each factor, and the relationships between the multiple factors, generates a pre-defined knowledge graph based on these factors.

[0170] In some embodiments, factors, their basic attributes, and the relationships between factors are collected, and the factors, their basic attributes, and the relationships between factors are stored using a Resource Description Framework (RDF) triple storage format. Further, knowledge extraction and entity linking are performed on the factors, their basic attributes, and the relationships between factors to obtain a predefined knowledge graph.

[0171] In one design, the revenue analysis method provided in this application embodiment further includes: S307-S308.

[0172] S307. Identify target anomaly factors based on income analysis results.

[0173] S308, Display target abnormal factors.

[0174] In one design, the revenue analysis method provided in this application embodiment further includes: S309.

[0175] S309. When the weight of the target anomaly factor is greater than the second preset threshold, the target anomaly factor is displayed based on a preset color.

[0176] To better understand the revenue analysis method provided in the embodiments of this application, the display strategy of the revenue analysis method is explained below. For example... Figure 8 The image shows the display interface for the monthly scenario analysis results. After each calculation using a preset model algorithm, the root causes of the operational data are analyzed and paths are generated. Multiple paths may be generated for each user group, and these are displayed on the interface.

[0177] Specifically, in Figure 8 The diagram shows the anomalous factors in the lunar scene. Figure 8 The target billing period is shown as 202210, compared to the billing period of 202209. The analysis target is a comprehensive revenue reduction analysis, and the city / prefecture-level city is the entire province. Monthly factor dashboards include: mobile network, bandwidth, IPTV bandwidth, dual-line users, fixed-line users, and innovative users. Figure 8 The interface shown can also display attention factors and warning factors. Figure 8 The example shows the following abnormal factors: IPTV bandwidth: users whose convergence expired last month, IPTV bandwidth: IPTV Super Movie users in City A, and IPTV bandwidth: users whose compensation and debt settlement revenue decreased.

[0178] exist Figure 9 The target analysis path is shown in the diagram. The target analysis path is explained both graphically and in textual form.

[0179] The graphical section visually displays the income situation, while the text section explains the numerical values ​​in the images. Figure 9 The example shown is as follows: Mobile network: -331,000. Path 1-1: 100% (-1,439,700) (-1,108,700) (0.47% of users) due to whether 21-Yes-Included traffic fees decreased compared to last month. Bandwidth: 600,000. IPTV: -201,800.

[0180] In practical applications, a more detailed overview of revenue fluctuation analysis can be displayed. For example, this month's total revenue, the percentage increase or decrease year-on-year, the month-on-month change, the number of active users, and package fees, etc.

[0181] exist Figure 10 The image shows the interface for analyzing the path library.

[0182] By calculating and visualizing the relationships between factor groups, the original numbers represent the number of factors and factor groups set by the system, while the output for this month represents the number of factors and factor groups used in the model execution. Figure 10 The diagram shows the path library's current status: the raw data includes the number of factors, factor clusters, and paths. There are 144 factors and 44 factor clusters. The output data for this month includes the number of factors, factor clusters, and paths. There are 122 factors and 33 factor clusters. The raw data represents all factors involved in the statistical data. The output data for this month represents the number of factors involved in the month's operational data. Additionally, in... Figure 10 The system can also display the health of the path library. The health of the path library is used to characterize the percentage of factors and factor groups involved this month.

[0183] exist Figure 11 The diagram illustrates the relationships between factors, allowing users to better understand the factors involved.

[0184] exist Figure 11 The interface also allows you to select the data type: effective factors, invalid factors, this month's path, and my path. Additionally, there's a search button, and you can enter the factor name as the search path. Figure 11 The list shows the effective factors: 4G package, 4G secondary card, 5G unlimited, old package, daily rental card and other products.

[0185] In some embodiments, my path displays eight models solidified based on historical analysis experience, including analysis of mobile network traffic growth difference data, analysis of monthly revenue decline for mobile network users, analysis of revenue fluctuations for 5G service users, analysis of mobile network voice traffic cost fluctuations, analysis of voice revenue fluctuations, analysis of broadband traffic growth difference data, analysis of revenue fluctuations for broadband speed-up users, and analysis of fixed-line revenue fluctuations. Each model is displayed hierarchically in a mind map format, allowing for continued analysis at any node.

[0186] For example, in Figure 12 In the example, when the user selects "My Path," the following data analysis is displayed: Mobile network traffic increase difference analysis: Level: 7, Maximum decrease: -100.3%; Mobile user monthly revenue decrease analysis: Level: 5, Maximum decrease: -146.3%. In some embodiments, more content may be displayed, such as: 5G service user revenue fluctuation analysis, mobile network voice traffic fluctuation analysis, voice revenue fluctuation analysis, bandwidth rectification difference data analysis, and bandwidth speed-up user revenue analysis, etc.

[0187] For example, in Figure 13The path details are shown in the image. For example, a mobile network rectification difference data analysis is shown: there are 11.05 million mobile network users, the corresponding mobile network user increase difference is 565,000 (i.e., an increase of 565,000 users), and the corresponding mobile network user value increase revenue is 10.468 million (i.e., 10.468 million users have increased revenue).

[0188] In some embodiments, the path details can also display more information. For example, it can specifically display the difference in traffic growth, such as churned data, newly developed data, and returning data. Churn can specifically include existing churned data and newly developed churned data. Value-added revenue can specifically include specific data on 5G increases and data on changes in existing value.

[0189] In other scenarios, electronic devices can also display daily scene data. For example... Figure 14 As shown, a daily factor quadrant chart is presented. Based on the daily label, the daily value and the cumulative value for the month are displayed in quadrants, intuitively dividing abnormal daily factors into abnormal and non-abnormal daily factors.

[0190] Finally, to illustrate the process of implementing the revenue analysis method provided in this application, such as... Figure 15 The diagram shows the analysis flowchart. When performing intelligent revenue analysis on monthly or daily operational data: 1. It can highlight or hide factors, and after highlighting or hiding factors, determine the target analysis path. Further, it locates gap factors and then correlates them; 2. It can select the target path and automatically calculate the target path; 3. It performs month-on-month gap analysis and automatically calculates the entire path. Further, it locates gap factors and then correlates them; 4. It performs target gap analysis, automatically running the relevant paths for the target factors. Further, it locates gap factors and then correlates them; 5. It identifies early warning factors in the target analysis path and determines the scope and degree of influence of these early warning factors.

[0191] In addition, once the revenue analysis results are determined, drill-down analysis can be performed, which will then automatically generate PowerPoint presentations for users to view and display.

[0192] In the embodiments of this application, the gap analysis can be divided into automatic disassembly analysis and manual disassembly analysis.

[0193] The income analysis methods provided in this application involve: knowledge graphs, graph traversal, information entropy algorithm, prediction model, character analysis model, and dynamic programming algorithm.

[0194] The revenue analysis method provided in this application achieves the following technical effects: 1. Providing the optimal path: The optimal analysis path is determined through model calculation and scoring, replacing manual root cause analysis of revenue decline. 2. Root cause diagnosis: Utilizing the occurrence rate of factors and factor groups, as well as the performance characteristics of factors in different billing periods, the system automatically generates diagnostic reports and can set thresholds for factors of interest, intuitively displaying warnings and abnormal factors. 3. My path: Fixed analysis scenarios are set based on historical reasons for revenue decline and key revenue areas. The homepage of each analysis scenario displays the revenue decline rate and path hierarchy by billing period. 4. Analysis path map: Revenue fluctuations are displayed in a topological form according to different dimensions based on the analysis scenario. Paths with the largest declines and increases are distinguished and highlighted using color. 5. Continuing the path: Through the continuing the path function, multi-dimensional extended analysis is performed based on the existing analysis paths.

[0195] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, the revenue analysis device or electronic device includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0196] This application embodiment can, according to the above method, exemplarily divide a revenue analysis device or electronic device into functional modules. For example, the revenue analysis device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0197] For example, embodiments of this application also provide an income analysis device.

[0198] Figure 16 This is a block diagram of an income analysis device 50 according to an exemplary embodiment. (Refer to...) Figure 16 The revenue analysis device 50 includes an acquisition unit 501 and a determination unit 502.

[0199] Acquisition unit 501 is used to acquire the first revenue data within the target period.

[0200] The determining unit 502 is used to determine the revenue change data within the target period based on the second revenue data and the first revenue data; the second revenue data is the revenue data of the historical period.

[0201] The determining unit 502 is also used to determine the target analysis path based on revenue change data and a preset knowledge graph; the preset knowledge graph includes the business characteristics of each revenue business in the revenue data and the revenue factors that correspond one-to-one with each revenue business; the target analysis path is the analysis path that meets the preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data; the target analysis path includes at least one revenue factor.

[0202] The determination unit 502 is also used to determine the revenue analysis results based on the target analysis path; the revenue analysis results include the revenue factors in the target analysis path.

[0203] Optionally, unit 502 is specifically used for: updating a preset knowledge graph based on operational change data to obtain an updated knowledge graph; and calculating the weight of each factor in the updated knowledge graph based on a preset entropy method to determine the target analysis path.

[0204] Optionally, the determining unit 502 is further specifically used for: traversing the updated knowledge graph based on a depth-first search algorithm to obtain multiple analysis paths, and calculating the weight of each analysis path based on a preset entropy method to determine the contribution value of the multiple analysis paths; the contribution value is positively correlated with the weight. Based on the contribution values ​​of the multiple analysis paths, a target analysis path is determined. The target analysis path is the analysis path whose contribution value is greater than a first preset threshold.

[0205] Optionally, the determining unit 502 is also specifically used for: calculating the weight of each factor in the updated knowledge graph based on the preset entropy method, and traversing the updated knowledge graph based on the weight of each factor in the updated knowledge graph and the width traversal algorithm to determine the target analysis path, wherein the factors in the target analysis path are the factors with the largest weight proportion during the traversal of the updated knowledge graph.

[0206] Optionally, the acquisition unit 501 is further configured to acquire multiple factors and the basic attributes of each factor. The basic attributes are used to indicate the business information of the factors. The determination unit 502 is further configured to determine a preset knowledge graph based on the multiple factors and the basic attributes of each factor.

[0207] Optional, such as Figure 16 As shown, the revenue analysis device 50 also includes a display unit 503. The determination unit 502 is further configured to determine target anomaly factors based on the revenue analysis results. The display unit 503 is configured to display the target anomaly factors.

[0208] Optionally, the display unit 503 is specifically used to: display the target abnormal factor based on a preset color when the weight of the target abnormal factor is greater than a second preset threshold.

[0209] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 17 As shown, the electronic device 60 includes a processor 601, a memory 602, and a bus 603. The processor 601 and the memory 602 can be connected via the bus 603.

[0210] Processor 601 is the control center of the communication device. It can be a single processor or a collective term for multiple processing elements. For example, processor 601 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0211] As one embodiment, processor 601 may include one or more CPUs, for example Figure 17 CPU 0 and CPU 1 are shown in the diagram.

[0212] The memory 602 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0213] As one possible implementation, the memory 602 can exist independently of the processor 601. The memory 602 can be connected to the processor 601 via a bus 603 and is used to store instructions or program code. When the processor 601 calls and executes the instructions or program code stored in the memory 602, it can implement the sensor determination method provided in the embodiments of this application.

[0214] In another possible implementation, the memory 602 can also be integrated with the processor 601.

[0215] Bus 603 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 17 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0216] It should be pointed out that, Figure 17 The structure shown does not constitute a limitation on the electronic device 60. Except... Figure 17 In addition to the components shown, the electronic device 60 may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0217] Optionally, the electronic device 60 provided in this application embodiment may also include a communication interface 604.

[0218] Communication interface 604 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 604 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0219] In one design, the communication interface in the electronic device provided in this application embodiment can also be integrated into the processor.

[0220] In another hardware structure of the electronic device provided in this application embodiment, the electronic device may include a processor and a communication interface. The processor is coupled to the communication interface.

[0221] The functions of the processor can be found in the processor description above. In addition, the processor also has storage functions, which can be found in the memory function description above.

[0222] The communication interface is used to provide data to the processor. This communication interface can be an internal interface of the communication device or an external interface of the communication device.

[0223] It should be noted that the above-mentioned alternative hardware structure does not constitute a limitation on the electronic device. In addition to the above-mentioned alternative hardware component, the electronic device may include more or fewer components, or combine certain components, or have different component arrangements.

[0224] When the functions of the integrated modules described above are implemented in hardware, the present application provides a structural diagram of the middleware involved in the above embodiments, which can be referred to as the structural diagram of the execution machine described above.

[0225] When the functions of the integrated modules described above are implemented in hardware, the present application provides a schematic diagram of the electronic device involved in the above embodiments, which can be referred to in the description of electronic device 60, and will not be repeated here.

[0226] This application also provides a computer-readable storage medium storing instructions that, when executed by a computer, perform each step of the revenue analysis process shown in the above method embodiments.

[0227] This application also provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the revenue analysis method described in the above method embodiments.

[0228] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0229] Since the server, user equipment, computer-readable storage medium, and computer program product in the embodiments of this application can be applied to the above methods, the technical effects that can be obtained can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0230] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. An income analysis method, characterized in that, The method includes: Obtain the first revenue data within the target period; Based on the second revenue data and the first revenue data, the revenue change data within the target period is determined; the second revenue data is revenue data from a historical period. Based on the revenue change data and a preset knowledge graph, a target analysis path is determined, and a revenue analysis result is determined based on the target analysis path. The preset knowledge graph includes the business characteristics of each revenue business in the revenue data and the revenue factors that correspond one-to-one with each revenue business. The target analysis path is an analysis path that meets preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data. The target analysis path includes at least one revenue factor, and the revenue analysis result includes the revenue factor in the target analysis path. The step of determining the target analysis path based on the income change data and the preset knowledge graph includes: The preset knowledge graph is updated based on the income change data to obtain the updated knowledge graph; The weight of each factor in the updated knowledge graph is calculated based on the preset entropy method to determine the target analysis path.

2. The revenue analysis method according to claim 1, characterized in that, The step of calculating the weight of each factor in the updated knowledge graph based on the preset entropy method to determine the target analysis path includes: The updated knowledge graph is traversed using a depth-first search algorithm to obtain multiple analysis paths. The weight of each analysis path is calculated using a preset entropy method to determine the contribution value of the multiple analysis paths. The contribution value is positively correlated with the weight. Based on the contribution values ​​of the multiple analysis paths, the target analysis path is determined; the target analysis path is the analysis path whose contribution value is greater than a first preset threshold.

3. The revenue analysis method according to claim 1, characterized in that, The step of calculating the weight of each factor in the updated knowledge graph based on the preset entropy method to determine the target analysis path includes: The weight of each factor in the updated knowledge graph is calculated based on the preset entropy method, and the updated knowledge graph is traversed based on the weight of each factor in the updated knowledge graph and the width traversal algorithm to determine the target analysis path. The factor in the target analysis path is the factor with the largest weight ratio during the traversal of the updated knowledge graph.

4. The income analysis method according to any one of claims 1-2, characterized in that, The method further includes: Obtain multiple factors and the basic attributes of each factor; the basic attributes are used to indicate the business information of the factors. Based on the multiple factors and the basic attributes of each factor, a preset knowledge graph is determined.

5. The income analysis method according to any one of claims 1-2, characterized in that, The method further includes: Based on the revenue analysis results, target anomaly factors are identified and displayed.

6. The revenue analysis method according to claim 5, characterized in that, The display of the target anomaly factor includes: If the weight of the target anomaly factor is greater than a second preset threshold, the target anomaly factor is displayed based on a preset color.

7. An income analysis device, characterized in that, The apparatus for the income analysis method according to any one of claims 1-6 comprises: an acquisition unit and a determination unit; The acquisition unit is used to acquire the first revenue data within the target period; The determining unit is configured to determine revenue change data within the target period based on the second revenue data and the first revenue data; the second revenue data is revenue data from a historical period. The determining unit is further configured to determine a target analysis path based on the revenue change data and a preset knowledge graph; the preset knowledge graph includes the business characteristics of each revenue business in the revenue data and the revenue factors corresponding to each revenue business; the target analysis path is an analysis path that meets preset conditions among at least one analysis path determined by the preset knowledge graph based on the revenue change data; the target analysis path includes at least one revenue factor. The determining unit is further configured to determine the revenue analysis result based on the target analysis path; the revenue analysis result includes the revenue factors in the target analysis path.

8. An electronic device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being configured to run computer programs or instructions to implement the revenue analysis method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the revenue analysis method as described in any one of claims 1-6.

Images