Operation analysis method and device, equipment and storage medium

Abstract

The invention discloses an operation analysis method and device, equipment and a storage medium, and relates to the technical field of data analysis, and the method comprises the steps: obtaining first business data of a plurality of business indexes in a current time period; performing attribution analysis on the first business data of any business index, so as to generate a business operation strategy according to an attribution analysis result; and collecting second service data for executing a service index corresponding to the service operation strategy, so as to determine a verification result of the service operation strategy according to the second service data. The business data of the business indexes are monitored in real time, the collected data are deeply mined and analyzed to extract useful information and identify potential rules and trends, the corresponding operation strategy is recommended according to the analysis result, the operation strategy is verified, and scientific decision-making assistance can be carried out on the business.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to an operation analysis method, device, equipment and storage medium. Background Art

[0002] The current business strategy operation process mainly relies on the monitoring, analysis and strategy optimization of business data, but this process is highly dependent on human intervention, resulting in low efficiency and difficulty in responding to business changes in a timely manner. Specifically, the monitoring and analysis of business data are usually done manually based on experience and rules, which is not only time-consuming and labor-intensive, but also prone to human errors due to difficulty in fully tapping the potential value of data. In terms of strategy optimization, humans may not be able to fully consider all relevant factors, nor can they discover and respond to market changes in a timely manner, resulting in delayed or inaccurate strategy adjustments. This decision-making method based on experience and rules often fails to provide effective decision support in the face of a complex and changing business environment, thus affecting the long-term development and competitiveness of the business. Summary of the invention

[0003] Based on this, it is necessary to provide an operation analysis method, device, equipment and storage medium for the above-mentioned technical problems to solve at least one of the above-mentioned technical problems.

[0004] The present invention provides an operation analysis method, comprising:

[0005] Obtaining the first business data of several business indicators in the current time period;

[0006] Performing attribution analysis on the first business data of any of the business indicators to generate a business operation strategy according to the attribution analysis result;

[0007] Second business data of business indicators corresponding to the execution of the business operation strategy are collected to determine a verification result of the business operation strategy based on the second business data.

[0008] Optionally, according to an operation analysis method provided by the present invention, the performing attribution analysis on the first business data of any of the business indicators includes:

[0009] For any of the business indicators;

[0010] Obtaining third business data of the business indicator in a historical time period;

[0011] Determine the indicator type corresponding to the business indicator;

[0012] According to the indicator type, attribution analysis is performed on the first business data and the third business data of the business indicator to obtain the attribution analysis result.

[0013] Optionally, according to an operation analysis method provided by the present invention, performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes:

[0014] If the indicator type is a single indicator, then based on the first business data and the second business data of the business indicator, the influence weights of the preset multiple diagnostic dimensions are calculated;

[0015] The attribution analysis result is determined based on the diagnostic dimension with the greatest impact weight.

[0016] Optionally, according to an operation analysis method provided by the present invention, performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes:

[0017] If the indicator type is a composite indicator, determining each target indicator associated with the business indicator;

[0018] Based on the first business data and the second business data of the business indicator, respectively calculate the influence weight of each of the target indicators;

[0019] The attribution analysis result is determined based on the target indicator with the largest impact weight.

[0020] Optionally, according to an operation analysis method provided by the present invention, generating a business operation strategy according to the attribution analysis result includes:

[0021] Based on the attribution analysis result, query in a preset strategy knowledge base to obtain the business operation strategy;

[0022] The strategy knowledge base is generated based on the following steps:

[0023] For the business operation strategy corresponding to any business indicator: according to the attribution analysis result, the optimization strategy and its corresponding verification result are classified and stored in the strategy knowledge base.

[0024] Optionally, according to an operation analysis method provided by the present invention, determining the verification result of the business operation strategy according to the second business data includes:

[0025] Determine fourth business data of a business indicator corresponding to the business operation strategy that is not implemented;

[0026] The second business data and the fourth business data are compared and verified to obtain a verification result of the business operation strategy.

[0027] Optionally, according to an operation analysis method provided by the present invention, after obtaining the third business data of the business indicator in the historical time period, the method further includes:

[0028] Comparing the first business data and the third business data of the business indicator to obtain a fluctuation value;

[0029] If the fluctuation value is greater than a preset threshold, an alarm message is issued.

[0030] The present invention also provides an operation analysis device, comprising:

[0031] An acquisition module, used to acquire first business data of a plurality of business indicators;

[0032] An analysis module, configured to perform attribution analysis on the first business data of any of the business indicators, so as to generate a business operation strategy according to the attribution analysis result;

[0033] The verification module is used to collect second business data of business indicators corresponding to the execution of the business operation strategy, so as to determine the verification result of the business operation strategy according to the second business data.

[0034] The present invention also provides a computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned operation analysis method when executing the computer-readable instructions.

[0035] The present invention also provides one or more readable storage media storing computer-readable instructions, and the computer-readable instructions implement the above-mentioned operation analysis method when executed by a processor.

[0036] The above-mentioned operation analysis method, device, equipment and storage medium include: obtaining the first business data of several business indicators in the current time period; performing attribution analysis on the first business data of any of the business indicators to generate a business operation strategy based on the attribution analysis results; collecting the second business data of the business indicators corresponding to the execution of the business operation strategy to determine the verification result of the business operation strategy based on the second business data. The present invention monitors the business data of business indicators in real time, conducts in-depth mining and analysis on the collected data to extract useful information and identify potential rules and trends, recommends corresponding operation strategies based on the analysis results, and verifies the operation strategies, which can assist in scientific decision-making for the business. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0038] Figure 1 is a flow chart of an operation analysis method in one embodiment of the present invention;

[0039] Figure 2 is a structural schematic diagram of an operation analysis device in one embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms of "a", "said" and "the" used in one or more embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present invention refers to and includes any or all possible combinations of one or more associated listed items.

[0043] It should be noted that the application scenarios of the embodiments of the present invention are not specifically limited and can be applied to scenarios such as cargo transportation, e-commerce industry, financial industry, and medical industry.

[0044] For e-commerce industry scenarios:

[0045] Product inventory management: By real-time monitoring of sales data, inventory levels, and logistics and delivery information of various products on the e-commerce platform, using diagnostic attribution to analyze the causes of sales fluctuations, and conducting AB experiments to determine the effects of different replenishment strategies, the early warning center promptly alerts to out-of-stock risks, and the strategy center generates optimized inventory allocation and replenishment plans to achieve a balance between reducing inventory costs and maximizing sales.

[0046] Customer service optimization: Analyze customer consultation data, complaint data, and after-sales feedback data, intelligently monitor customer service response time and satisfaction indicators, compare the effects of different customer service scripts and service processes through AB experiments, diagnose and analyze the service quality of customer service personnel, and adjust strategies based on the results to improve customer service experience, promote customer loyalty and increase repurchase rate.

[0047] For the financial industry:

[0048] Risk management: Real-time monitoring of financial transaction data, including stock trading, credit business, etc., using diagnostic attribution to analyze abnormal transaction patterns and potential risk factors, AB experiments to evaluate the effectiveness of different risk control models and strategies, the early warning center to promptly discover and alert financial risk events, and the strategy center to dynamically adjust risk thresholds, credit assessment standards, etc. based on analysis results to ensure the asset security and business stability of financial institutions.

[0049] Financial product innovation and optimization: Combine internal customer demand survey data with external financial market innovation trends, competitor product features and other data to conduct AB experiments and diagnostic analysis on the functions, income structure, and fees of financial products, such as testing the rate of return settings of different wealth management products and the adjustment of the coverage of insurance products. Based on the feedback, optimize the design of financial products to improve product competitiveness and market adaptability.

[0050] For medical industry scenarios:

[0051] Hospital operation management: Real-time monitoring of hospital outpatient volume, hospitalization rate, medical resource utilization and other data; diagnosis and attribution analysis of inefficient operational links; AB experiments to compare the effects of different appointment registration strategies and ward allocation plans; early warning center to remind of medical resource shortages; strategy center to formulate optimized hospital operation strategies, such as reasonable arrangement of medical staff shifts, optimization of medical equipment procurement plans, etc., to improve the overall hospital operation efficiency and service quality.

[0052] Medical supply chain management: monitor the procurement, inventory, distribution and other data of medical supplies such as drugs and medical devices, analyze issues such as cost control and timeliness of supply in the supply chain, conduct AB experiments on the effects of different supplier cooperation models and inventory management strategies, and ensure the supply security of medical supplies through the early warning center. The strategy center optimizes the medical supply chain process to ensure that hospitals reduce procurement costs and inventory backlogs while meeting clinical needs.

[0053] In one embodiment, specifically, Figure 1 As shown, Figure 1 : is a flow chart of an operation analysis method in an embodiment of the present invention. The embodiment of the present invention provides an operation analysis method, comprising the following steps:

[0054] Step S11, obtaining first business data of a number of business indicators in the current time period;

[0055] It should be noted that the embodiment of the present invention is specifically described by taking the transportation scenario as an example. Business indicators include order data, transportation data, transaction data, financial data, etc. The data of various business indicators are collected and monitored in real time. For example, the frequency of data update can be set to once every 5 minutes to ensure the real-time nature of the data.

[0056] Step S12, performing attribution analysis on the first business data of any of the business indicators to generate a business operation strategy according to the attribution analysis result;

[0057] Specifically, for any of the business indicators, the following steps are performed: obtaining the third business data of the business indicator in the historical time period, the historical time period refers to the time before the current time period; in addition, determining the indicator type corresponding to the business indicator, wherein the indicator type includes a single indicator and a composite indicator, and the review indicator refers to the indicator data obtained by calculating other indicator data. Further, according to the indicator type of the business indicator, the first business data and the third business data of the business indicator are subjected to attribution analysis to obtain the attribution analysis result. The specific analysis process is specifically described in the following embodiments and will not be repeated here.

[0058] Furthermore, based on the attribution analysis results, a query is performed in a preset policy knowledge base to obtain the business operation strategy; wherein the policy knowledge base is generated based on the following steps: for the business operation strategy corresponding to any business indicator: according to the attribution analysis results, the optimization strategy and its corresponding attribution analysis results, verification results and other information are classified and stored in the policy knowledge base, so that the business operation strategy associated with it can be retrieved based on the analyzed attribution analysis results.

[0059] In addition, the first business data and the third business data of the business indicator are compared to obtain a fluctuation value. For example, the sales amount in the historical time period is 72,000, and the sales amount in the current time period is 44,800. The fluctuation value is that the sales amount has dropped by 27,200. Optionally, the daily or weekly fluctuations corresponding to the data on different dates can be calculated based on the first business data and the third business data as the fluctuation value. Furthermore, if the fluctuation value is greater than a preset threshold, an alarm message is issued for timely review by the management personnel. The preset threshold can be set according to the actual situation and is not specifically limited here.

[0060] Step S13: collect second business data of business indicators corresponding to the business operation strategy, and determine the verification result of the business operation strategy according to the second business data.

[0061] Specifically, the second business data of the business indicators corresponding to the business operation strategy executed within the preset time is collected, and the fourth business data of the business indicators corresponding to the business operation strategy not executed is collected; and then the second business data and the fourth business data are compared and verified to obtain the verification result of the business operation strategy, and the verification result is used to evaluate the effect of the business operation strategy. For example, a portion of orders can be randomly selected to apply the business operation strategy for pricing, and then the indicators such as the completion quantity of the orders to which the business operation strategy has been applied and the orders to which the strategy has not been applied are compared, so as to evaluate the effect of the business operation strategy.

[0062] In addition, if the verification result of the business operation strategy is positive, for example, the number of orders completed and the sales amount increase, it proves that the business operation strategy is beneficial, and then the business operation strategy and the corresponding attribution analysis results are associated and stored in the strategy knowledge base. If the verification result of the business operation strategy is not positive, for example, the number of orders completed, the sales amount and other data continue to decline, it proves that the business operation strategy is useless, and then the business operation strategy is deleted to re-analyze and obtain a new business operation strategy to ensure the effectiveness of the strategy.

[0063] The embodiment of the present invention, through the above scheme, includes: obtaining the first business data of several business indicators in the current time period; performing attribution analysis on the first business data of any of the business indicators to generate a business operation strategy based on the attribution analysis result; collecting the second business data of the business indicators corresponding to the execution of the business operation strategy to determine the verification result of the business operation strategy based on the second business data. The embodiment of the present invention monitors the business data of business indicators in real time, conducts in-depth mining and analysis on the collected data to extract useful information and identify potential rules and trends, recommends corresponding operation strategies based on the analysis results, and verifies the operation strategies, which can assist in scientific decision-making for the business.

[0064] In one embodiment of the present invention, performing attribution analysis on the first business data of any of the business indicators includes:

[0065] For any of the business indicators; obtain the third business data of the business indicator in the historical time period; determine the indicator type corresponding to the business indicator; and according to the indicator type, perform attribution analysis on the first business data and the third business data of the business indicator to obtain the attribution analysis result.

[0066] Specifically, the third business data of the business indicator in the historical time period is obtained. If the indicator type is a single indicator, the first business data of the current time period and the third business data of the historical time period are split according to the preset diagnostic dimension, and then based on the first business data of the current time period and the third business data of the historical time period and the data after the dimension splitting, the impact weights corresponding to each dimension are analyzed according to different diagnostic dimensions, and the diagnostic dimension with the largest impact weight is used as the attribution analysis result. The specific analysis process is specifically described in the following embodiments and will not be repeated here. In addition, if the indicator type is a composite indicator (the review indicator refers to the indicator data obtained by calculating other indicator data), then determine the various target indicators associated with the business indicator, and the business indicator is the indicator data obtained by calculating and processing according to each target indicator; then determine the business data of each target indicator in the current time period and the historical time period, and calculate the impact weight of each target indicator based on the first business data and the second business data of the business indicator and the business data of each target indicator in the current time period and the historical time period; further, take the target indicator with the largest impact weight as the attribution analysis result.

[0067] In addition, during the attribution analysis process, in order to further understand the specific factors that affect the business data, the operational strategies, marketing activities, etc. related to the diagnostic dimensions or target indicators are queried to determine whether the operational strategies, marketing activities, etc. related to the diagnostic dimensions or target indicators will affect the attribution results of the business indicators. In addition, the weather, road conditions, strategies and other factors related to the diagnostic dimensions or target indicators are queried to determine whether the relevant factors will affect the attribution results of the business indicators, so as to understand the specific dimensions and specific factors that affect the business data.

[0068] Through the above-mentioned scheme, the embodiment of the present invention realizes attribution analysis on the first business data and the third business data of the business indicator according to the indicator type of the business indicator with different analysis schemes to improve the accuracy of the attribution analysis results, so that the specific dimensions and specific factors affecting the business data can be understood according to the attribution analysis results.

[0069] In one embodiment of the present invention, performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes:

[0070] If the indicator type is a single indicator, the influence weights of the preset multiple diagnostic dimensions are calculated based on the first business data and the second business data of the business indicator; and the attribution analysis result is determined based on the diagnostic dimension with the largest influence weight.

[0071] It should be noted that the diagnostic dimensions include multiple dimensions such as city, business line, user group, mileage segment, payment attribute, order category, user channel, and cargo type. Specifically, if the indicator type is a single indicator, the first business data of the business indicator is divided according to the multiple diagnostic dimensions to obtain the first divided data corresponding to each diagnostic dimension; and the second business data of the business indicator is divided according to the multiple diagnostic dimensions to obtain the second divided data corresponding to each diagnostic dimension. For example, the business data is the total order volume; it is divided according to the city dimension to obtain the order volume corresponding to each city.

[0072] Further, for any diagnostic dimension, the following steps are performed: In one embodiment, based on the third business data of the business indicator in the historical time period and the second division data corresponding to the diagnostic dimension, the proportion of the data of the diagnostic dimension in the total data of all diagnostic dimensions is calculated, that is, the proportion of the second division data of the dimension in the historical time period to the total third business data. Further, according to the proportion, the dimension weight corresponding to the diagnostic dimension is calculated, and the calculation formula is as follows: the dimension weight corresponding to the diagnostic dimension = the proportion corresponding to the diagnostic dimension / (1-the proportion corresponding to the diagnostic dimension). Further, based on the first division data and the second division data corresponding to the diagnostic dimension, the change rate of the diagnostic dimension is calculated, and based on the first business data of the business indicator and the third business data, the overall change rate is calculated. Then, based on the overall change rate, the change rate corresponding to the diagnostic dimension and the dimension weight, the impact weight of the diagnostic dimension is calculated. The calculation formula of the impact weight is as follows: the impact weight of the diagnostic dimension = (the change rate corresponding to the diagnostic dimension-the overall change rate) × the dimension weight corresponding to the diagnostic dimension.

[0073] In another embodiment, based on the first divided data and the second divided data corresponding to the diagnostic dimension, the change amount corresponding to the diagnostic dimension is calculated; in addition, based on the change amount corresponding to the diagnostic dimension and the third business data of the business indicator in the historical time period, the impact weight of the diagnostic dimension is calculated.

[0074] For example, for business indicators (such as sales), the data in this period (current time period) and the benchmark date (historical time period) are as follows: Diagnostic dimension A sales in this period: 1200; Diagnostic dimension A sales on the benchmark date: 1000; Business indicator sales as a whole on the benchmark date: 5000; At this time, the change in diagnostic dimension A = 1200-1000 = 200; The impact weight of diagnostic dimension A: 200 / 5000 = 0.04 or 4%

[0075] In another embodiment, the impact weight of the diagnostic dimension can be calculated using a fluctuation contribution algorithm based on the first business data of the business indicator in the current time period, the third business data in the historical time period, the first partition data, and the second partition data.

[0076] For example, for business indicators (such as completion rate), the data for this period (current time period) and the benchmark date (historical time period) are as follows:

[0077] The number of completed orders for dimension A in this period: 80;

[0078] The total number of orders for dimension A in this period: 100;

[0079] Number of completed orders for Dimension A on the benchmark date: 70;

[0080] Total number of orders for Dimension A on the benchmark date: 90;

[0081] Overall (data from all diagnostic dimensions) number of completed orders in this period: 140;

[0082] Overall total number of orders in this period: 220;

[0083] The total number of completed orders on the benchmark day: 120;

[0084] The total number of orders on the benchmark day: 200;

[0085] The volatility contribution of dimension A is calculated as follows:

[0086] The current period rate value of dimension A = 80 / 100 = 0.8;

[0087] The benchmarking rate of dimension A = 70 / 90≈0.778;

[0088] The overall current period rate value = 140 / 220 ≈ 0.636;

[0089] Overall benchmarking value = 120 / 200 = 0.6;

[0090] The absolute value of the denominator dimension A of the current period rate value = 100;

[0091] The overall absolute value of the denominator of the current period rate value = 220;

[0092] The absolute value of the denominator dimension A of the benchmarking rate value = 90;

[0093] The overall absolute value of the denominator of the benchmarking rate value = 200;

[0094] The impact weight of the diagnostic dimension = (this period rate value of dimension m - overall benchmark rate value) (absolute value of dimension m in the denominator of current period rate value / overall absolute value of the denominator of current period rate value) - (benchmark rate value of dimension m - overall benchmark rate value) (absolute value of dimension m in the denominator of benchmark rate value / overall absolute value of the denominator of benchmark rate value) = 0.0118 or 1.18%.

[0095] Furthermore, based on the influence weights of multiple diagnostic dimensions, the diagnostic dimension with the greatest influence weight is determined, and based on the diagnostic dimension with the greatest influence weight, the attribution analysis result is determined. In other embodiments, after determining the diagnostic dimension with the greatest influence weight among multiple diagnostic dimensions such as cities, business lines, user groups, mileage segments, payment attributes, order categories, user channels, and types of goods, in order to further understand the specific factors affecting the business data, query the operating strategies, marketing activities, etc. related to the diagnostic dimensions to determine whether the operating strategies, marketing activities, and other factors related to the diagnostic dimensions will affect the attribution results of the business indicators. In addition, query the weather, road conditions, strategies, and other factors related to the diagnostic dimensions to determine whether the relevant factors will affect the attribution results of the business indicators, so that the specific dimensions and specific factors affecting the business data can be understood.

[0096] Through the above scheme, the embodiment of the present invention realizes that when the indicator type of the business indicator is a single indicator, the indicator data is split into different dimensions, so that the collected data is deeply mined and analyzed according to different dimensions to extract useful information and identify potential rules and trends, so as to analyze the impact weights brought by different dimensions and obtain accurate attribution analysis results.

[0097] In one embodiment of the present invention, performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes:

[0098] If the indicator type is a composite indicator, determine the target indicators associated with the business indicator; based on the first business data and the second business data of the business indicator, respectively calculate the impact weight of each target indicator; based on the target indicator with the largest impact weight, determine the attribution analysis result.

[0099] Specifically, if the indicator type is a composite indicator, then determine the various target indicators associated with the business indicator; that is, the upstream parent indicator of the composite indicator (for example, sales amount = exposure number * conversion rate * customer unit price, where exposure number, conversion rate, and customer unit price are the various target indicators associated with the sales amount). Further, determine the business data of all target indicators in the current time period and the historical time period, and replace the business data of each target indicator in the current time period with the business data in the calculation formula corresponding to the business indicator in turn, so as to calculate the impact weight of each target indicator. For example, a certain analytical business indicator M is obtained by three interrelated factors A, B, and C, and the current indicator and comparison indicator are:

[0100] The first business data M1 of the business indicator of the current time period: M1 = A1*B1*C1;

[0101] The third business data M0 of the business indicator of the historical time period: M0 = A0*B0*C0;

[0102] A1, B1, and C1 represent the business data of each target indicator in the current time period; A0, B0, and C0 represent the business data of each target indicator in the historical time period. The business data of each target indicator in the current time period is substituted for the business data in the calculation formula corresponding to the business indicator, as follows:

[0103] M0=A0*B0*C0……Formula (1);

[0104] The first time A1 is used as a substitute: A1*B0*C0...Formula (2);

[0105] The second time, use B1 to replace: A1*B1*C0...Formula (3);

[0106] The third time, use C1 to replace: A1*B1*C1...Formula (4);

[0107] Formula (2) - Formula (1) is the impact of changes in target indicator A on business indicator M.

[0108] Formula (3) - Formula (2) is the impact of changes in target indicator B on business indicator M.

[0109] Formula (4) - Formula (3) is the impact of changes in target indicator C on business indicator M.

[0110] Furthermore, the target indicator with the largest influence weight is determined among the influence weights of each target indicator, and then the target indicator with the largest influence weight is used as the attribution analysis result. In other embodiments, after determining the target indicator with the largest influence weight, in order to further understand the specific factors affecting the business data, the operating strategies, marketing activities, etc. related to the target indicator are queried to determine whether the operating strategies, marketing activities, and other factors related to the target indicator will affect the attribution results of the business indicator. In addition, the weather, road conditions, strategies, and other factors related to the target indicator are also queried to determine whether the relevant factors will affect the attribution results of the business indicator, so that the specific dimensions and specific factors affecting the business data can be understood.

[0111] Through the above scheme, the embodiment of the present invention realizes that when the indicator type of the business indicator is a composite indicator, the target indicator associated with the current business indicator is determined, so as to deeply mine and analyze the data collected for each target indicator to extract useful information and identify potential rules and trends, so as to analyze the influence weights of different target indicators and obtain accurate attribution analysis results.

[0112] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0113] In one embodiment, an operation analysis device is provided, and the operation analysis device corresponds one-to-one to the operation analysis method in the above embodiment. Figure 2 As shown, Figure 2 : is a schematic diagram of a structure of an operation analysis device in one embodiment of the present invention, the operation analysis device comprises:

[0114] An acquisition module 21 is used to acquire first business data of a plurality of business indicators;

[0115] An analysis module 22, configured to perform attribution analysis on the first business data of any of the business indicators, so as to generate a business operation strategy according to the attribution analysis result;

[0116] The verification module 23 is used to collect second business data of business indicators corresponding to the execution of the business operation strategy, so as to determine the verification result of the business operation strategy according to the second business data.

[0117] The analysis module 22 is also used for:

[0118] For any of the business indicators;

[0119] Obtaining third business data of the business indicator in a historical time period;

[0120] Determine the indicator type corresponding to the business indicator;

[0121] According to the indicator type, attribution analysis is performed on the first business data and the third business data of the business indicator to obtain the attribution analysis result.

[0122] The analysis module 22 is also used for:

[0123] If the indicator type is a single indicator, then based on the first business data and the second business data of the business indicator, the influence weights of the preset multiple diagnostic dimensions are calculated;

[0124] The attribution analysis result is determined based on the diagnostic dimension with the greatest impact weight.

[0125] The analysis module 22 is also used for:

[0126] If the indicator type is a composite indicator, determining each target indicator associated with the business indicator;

[0127] Based on the first business data and the second business data of the business indicator, respectively calculate the influence weight of each of the target indicators;

[0128] The attribution analysis result is determined based on the target indicator with the largest impact weight.

[0129] The analysis module 22 is also used for:

[0130] Based on the attribution analysis result, query in a preset strategy knowledge base to obtain the business operation strategy;

[0131] The strategy knowledge base is generated based on the following steps:

[0132] For the business operation strategy corresponding to any business indicator: according to the attribution analysis result, the optimization strategy and its corresponding verification result are classified and stored in the strategy knowledge base.

[0133] The verification module 23 is also used for:

[0134] Determine fourth business data of a business indicator corresponding to the business operation strategy that is not implemented;

[0135] The second business data and the fourth business data are compared and verified to obtain a verification result of the business operation strategy.

[0136] The operational analysis device also includes:

[0137] Comparing the first business data and the third business data of the business indicator to obtain a fluctuation value;

[0138] If the fluctuation value is greater than a preset threshold, an alarm message is issued.

[0139] For the specific definition of the operation analysis device, please refer to the definition of the operation analysis method above, which will not be repeated here. Each module in the above-mentioned operation analysis device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0140] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, Figure 3 : is a schematic diagram of a computer device in one embodiment of the present invention. The computer device includes a processor, a memory, a network interface and a database connected by a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating device, a computer-readable instruction and a database. The internal memory provides an environment for the operation of the operating device and the computer-readable instructions in the readable storage medium. The database of the computer device is used to store data involved in the operation analysis method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instruction is executed by the processor, an operation analysis method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0141] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, an operation analysis method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0142] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and when the processor executes the computer-readable instructions, the steps of the above-mentioned operation analysis method are implemented.

[0143] In one embodiment, a readable storage medium is provided, the readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by the processor to implement the above-mentioned operation analysis method steps. A person of ordinary skill in the art can understand that the implementation of all or part of the process in the above-mentioned embodiment method can be completed by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the process of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0144] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0145] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An operation analysis method, characterized in that: include: Obtaining the first business data of several business indicators in the current time period; Performing attribution analysis on the first business data of any of the business indicators to generate a business operation strategy according to the attribution analysis result; Second business data of business indicators corresponding to the execution of the business operation strategy are collected to determine a verification result of the business operation strategy based on the second business data.

2. The operation analysis method according to claim 1, characterized in that: The performing attribution analysis on the first business data of any of the business indicators includes: For any of the business indicators; Obtaining third business data of the business indicator in a historical time period; Determine the indicator type corresponding to the business indicator; According to the indicator type, attribution analysis is performed on the first business data and the third business data of the business indicator to obtain the attribution analysis result.

3. The operation analysis method according to claim 2, characterized in that: The performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes: If the indicator type is a single indicator, then based on the first business data and the second business data of the business indicator, the influence weights of the preset multiple diagnostic dimensions are calculated; The attribution analysis result is determined based on the diagnostic dimension with the greatest impact weight.

4. The operation analysis method according to claim 2, characterized in that: The performing attribution analysis on the first business data and the third business data of the business indicator according to the indicator type to obtain the attribution analysis result includes: If the indicator type is a composite indicator, determining each target indicator associated with the business indicator; Based on the first business data and the second business data of the business indicator, respectively calculate the influence weight of each of the target indicators; The attribution analysis result is determined based on the target indicator with the largest impact weight.

5. The operation analysis method according to claim 1, characterized in that: The business operation strategy is generated according to the attribution analysis results, including: Based on the attribution analysis result, query in a preset strategy knowledge base to obtain the business operation strategy; The strategy knowledge base is generated based on the following steps: For the business operation strategy corresponding to any business indicator: according to the attribution analysis result, the optimization strategy and its corresponding verification result are classified and stored in the strategy knowledge base.

6. The operation analysis method according to claim 1, characterized in that: Determining the verification result of the business operation strategy according to the second business data includes: Determine fourth business data of a business indicator corresponding to the business operation strategy that is not implemented; The second business data and the fourth business data are compared and verified to obtain a verification result of the business operation strategy.

7. The operation analysis method according to claim 2, characterized in that: After obtaining the third business data of the business indicator in the historical time period, the method further includes: Comparing the first business data and the third business data of the business indicator to obtain a fluctuation value; If the fluctuation value is greater than a preset threshold, an alarm message is issued.

8. An operation analysis device, characterized in that: include: An acquisition module, used to acquire first business data of a plurality of business indicators; An analysis module, configured to perform attribution analysis on the first business data of any of the business indicators, so as to generate a business operation strategy according to the attribution analysis result; The verification module is used to collect second business data of business indicators corresponding to the execution of the business operation strategy, so as to determine the verification result of the business operation strategy according to the second business data.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the operation analysis method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium having computer readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the operation analysis method according to any one of claims 1 to 7 is implemented.

Images