Method, device and equipment for data processing, medium and program product

Abstract

The invention relates to the technical field of data processing, and discloses a method, device and equipment for data processing, a medium and a program product, the method comprises the following steps: in response to an analysis element determined by a user, obtaining analysis data corresponding to the analysis element and an associated factor corresponding to the analysis element; on the basis of the analysis data, contribution weights of the correlation factors to the target indexes are generated, an initial analysis result is obtained, and on the basis of a data correlation model, a mapping relation between the analysis elements and the target indexes is established; in response to the adjustment of the contribution weight, generating an updated analysis result based on the adjusted contribution weight and the analysis data; or in response to adjustment of the analysis elements by the user, second analysis data corresponding to the adjusted analysis elements are obtained, a target analysis result is generated based on the second analysis data and the contribution weight, and the analysis elements and the adjusted analysis elements have the same associated factors. Analysis element adjustment is supported, and the method can adapt to actual service scene change.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to methods, devices, equipment, media and program products for data processing. Background Art

[0002] In today's digital age, enterprises and organizations have accumulated massive amounts of data. Data attribution analysis in related technologies often relies on complex statistical models and analyzes factor contributions through static causal structures.

[0003] However, this approach has certain limitations in practical applications. Actual business scenarios may undergo various changes, such as adjustments to market strategies or emergencies. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, device, medium and program product for data processing to solve the problem of limitations of data attribution analysis models in related technologies.

[0005] In a first aspect, the present invention provides a method for data processing, comprising: in response to an analysis element determined by a user, obtaining analysis data corresponding to the analysis element and an association factor corresponding to the analysis element; based on the analysis data, generating a contribution weight of the association factor to a target indicator, and obtaining an initial analysis result, wherein, based on a data association model, a mapping relationship between the analysis element and the target indicator is established; in response to an adjustment of the contribution weight, generating an updated analysis result based on the adjusted contribution weight and the analysis data; or, in response to an adjustment of the analysis element by the user, obtaining second analysis data corresponding to the adjusted analysis element, and generating a target analysis result based on the second analysis data and the contribution weight, wherein the analysis element and the adjusted analysis element have the same association factor.

[0006] In an optional embodiment, the contribution weight of the correlation factor to the target indicator is generated based on the analysis data, including: based on other correlation factors in the correlation factors, generating multiple sets including the other correlation factors, wherein the correlation factors include target correlation factors and the other correlation factors; based on the target set in the set, generating the contribution weight difference before and after adding the target correlation factor to the target set; based on each of the sets, obtaining the contribution weight difference corresponding to the set, and taking a weighted average of the multiple contribution weight differences to obtain the contribution weight of the target correlation factor to the target indicator.

[0007] In an optional embodiment, generating the contribution weight of the correlation factors to the target indicator based on the analysis data also includes: if the number of the correlation factors exceeds a preset number threshold, randomly generating multiple correlation factor sets; constructing a first correlation factor set, and calculating the correlation factor marginal contribution of the first correlation factor set, wherein the first correlation factor set is obtained based on the first correlation factor in the initial correlation factor set, and the initial correlation factor set is one of the multiple correlation factor sets; based on the order of the correlation factors represented by the initial correlation factor set, adding second correlation factors to the first correlation factor set one by one, and calculating the difference in correlation factor marginal contribution before and after adding the second correlation factor; and obtaining the contribution weight of the target correlation factor to the target indicator based on the correlation factor marginal contribution of the target correlation factor and the average of the correlation factor marginal contribution difference.

[0008] In an optional embodiment, in response to the adjustment of the contribution weight, an updated analysis result is generated based on the adjusted contribution weight and the analysis data, including: in response to the user's adjustment of the contribution weight, the updated analysis result is generated based on the adjusted contribution weight and the analysis data; and the updated analysis result is presented to the user.

[0009] In an optional embodiment, in response to the analysis elements determined by the user, obtaining the association factors corresponding to the analysis elements includes: converting the analysis elements into quantifiable features; integrating the analysis data based on the quantifiable features to establish an association relationship between the analysis elements and multiple factors; and determining the association relationship that meets the user scenario requirements as the association factor.

[0010] In an optional embodiment, the aforementioned method for data processing further includes: performing visual presentation based on the initial analysis result, the updated analysis result, or the target analysis result.

[0011] In a second aspect, the present invention provides a device for data processing, comprising: a first acquisition module for acquiring, in response to an analysis element determined by a user, analysis data corresponding to the analysis element and an associated factor corresponding to the analysis element; a second acquisition module for generating, based on the analysis data, a contribution weight of the associated factor to a target indicator, to obtain an initial analysis result, wherein a mapping relationship between the analysis element and the target indicator is established based on a data association model; a first generation module for generating, in response to an adjustment of the contribution weight, an updated analysis result based on the adjusted contribution weight and the analysis data; a second generation module for acquiring, in response to the user's adjustment of the analysis element, second analysis data corresponding to the adjusted analysis element, and generating a target analysis result based on the second analysis data and the contribution weight, wherein the analysis element and the adjusted analysis element have the same associated factor.

[0012] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for data processing of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for data processing of the above-mentioned first aspect or any corresponding embodiment thereof.

[0014] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the method for data processing according to the first aspect or any corresponding embodiment thereof.

[0015] It supports the adjustment of analysis factors and contribution weights, can adapt to changes in actual business scenarios, and can quickly verify different business assumptions; it responds to user adjustments in real time to improve interaction efficiency; at the same time, through intelligent attribution calculation, it can automatically and accurately analyze the impact of different related factors on target indicators, reduce errors, and improve the accuracy of attribution analysis; in addition, the reuse of contribution weights can reduce redundant processing; and by identifying high contribution weights in the analysis results and guiding resource allocation, it can improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the related art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 The flowchart shows the method for data processing according to an embodiment of the present invention;

[0018] Figure 2 The structural diagram shows the device for data processing according to an embodiment of the present invention;

[0019] Figure 3 The hardware structural diagram of the computer device according to an embodiment of the invention. Specific embodiments

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0021] In the causal attribution analysis method in the related art, the factor contribution degree analysis mainly relies on the static causal structure. However, this method has certain limitations in practical applications. The actual business scenario may undergo various changes, such as the adjustment of market strategies or emergencies.

[0022] According to an embodiment of the present invention, a method embodiment for data processing is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0023] In this embodiment, a method for data processing is provided, which can be used in terminals such as mobile phones, tablet computers, desktop computers, or servers, etc. Figure 1 The flowchart shows the method for data processing according to an embodiment of the present invention, as Figure 1 shown, the process includes the following steps:

[0024] Step S101, in response to the analysis elements determined by the user, obtain the analysis data corresponding to the analysis elements and the associated factors corresponding to the analysis elements.

[0025] In this step, the analysis elements are the core analysis dimensions defined by the user, such as time range, geographical area, or user group, etc. Based on the analysis elements, a Dynamic Structured Query Language (SQL) can be constructed to extract analysis data and associated factors from the database.

[0026] The analysis data can be various types of relevant data collected in advance. The analysis data includes business data, market data, or user data, etc. The analysis data can be cleaned, sorted, and classified to ensure the accuracy and usability of the data.

[0027] Specifically, the user sets the time range to be analyzed, clicks the query button, obtains all orders within the current time range through database query, and pulls the associated factors related to the orders, such as the driving duration, order receiving duration, or driver service score, etc. The data can be integrated and rendered for display on the page, and chart interaction is supported.

[0028] Step S102: Based on the analysis data, generate the contribution weight of the associated factors to the target indicator to obtain the initial analysis result. Among them, based on the data association model, establish the mapping relationship between the analysis elements and the target indicator.

[0029] In this step, based on the Cooperative Game Theory (Shapley), the total revenue generated by the collaboration of multiple associated factors can be configured. The core idea of the Cooperative Game Theory is to calculate the mean of the marginal contributions of a certain factor in all possible combinations.

[0030] The method of Causal Forest can also be used to construct multiple causal trees, estimate the Conditional Average Treatment Effect (CATE) of each associated factor, and the contribution weight is the mean of the importance of the associated factors in all trees.

[0031] The analysis elements can be mapped to the influencing factors of the target indicator through the data association model. Through multi-source data fusion technology, the scattered influencing factors can be integrated into a structured data set, including: structured data integration and external data extension. Among them, structured data integration includes directly associating fields such as timestamps, geographical coordinates, or user identifiers contained in the order data with the analysis elements; or associating driver behavior data with order data through driver identifiers. External data extension includes matching weather data with the order time or order location to analyze the impact of abnormal weather on supply and demand, etc.

[0032] Screen the influencing factors to obtain the associated factors, including screening the influencing factors based on the time dimension or the space dimension to obtain the associated factors.

[0033] Specifically, down - drilling analysis can be performed in the time dimension to compare the order fulfillment rate or response time in different time periods and identify associated factors, such as driver departure density. Or down - drilling analysis can be carried out in the spatial dimension. High - demand areas can be divided through geofencing, and the heat map of driver distribution can be associated with order density data. A high - demand area is an area where the passenger order demand is higher than a preset order quantity threshold.

[0034] The influence degree of each influencing factor on the target index can also be calculated through random forest, and fields with an influence degree lower than the preset influence threshold can be excluded to obtain associated factors.

[0035] The contribution weights of the generated associated factors to the target index are obtained to get the initial analysis result, which can be: driver service score: 30%, driving duration: 25%, city: 20%. The initial analysis result includes detailed data such as tables and charts, which can facilitate users to view the current order flow in real - time and efficiently, optimize the order - assignment strategy, and improve the user experience. The data source and processing link of the associated factors can be traced through the metadata management tool to ensure the interpretability of the analysis result.

[0036] Step S103, in response to the adjustment of the contribution weight, an updated analysis result is generated based on the adjusted contribution weight and analysis data.

[0037] In this step, by providing visualization controls, users can be allowed to manually adjust the contribution weight. For example, the driver service score is increased from 30% to 40%. For the analysis data, the predicted value of the target index is recalculated through the adjusted contribution weight to generate an updated analysis result. And a comparison chart of the original result and the predicted result, such as a line chart or a bar chart, is presented to the user.

[0038] Step S104, in response to the user's adjustment of the analysis elements, the second analysis data corresponding to the adjusted analysis elements is obtained, and the target analysis result is generated based on the second analysis data and the contribution weight, where the analysis elements and the adjusted analysis elements have the same associated factors.

[0039] In this step, when the user adjusts the analysis elements, only the newly added data can be queried. Based on the second analysis data representing the newly added data, the calculation logic of the original associated factors is reused. For example, when the user adjusts the time range from November to December, only the order data for December can be queried. The original contribution weight is retained to generate the order analysis result for December.

[0040] The data processing method provided in this embodiment supports users to adjust analysis factors and contribution weights, can adapt to changes in actual business scenarios, and can quickly verify different business hypotheses; it responds to user adjustments in real time, which can improve interaction efficiency; at the same time, through intelligent attribution calculation, it can automatically and accurately analyze the impact of different correlation factors on target indicators, reduce errors, and improve the accuracy of attribution analysis; in addition, the reuse of contribution weights can reduce redundant processing; and by identifying high contribution weights in the analysis results, it can guide resource allocation and improve resource utilization.

[0041] In some optional embodiments, based on the analysis data, the contribution weights of the correlation factors to the target indicators are generated, including: based on other correlation factors in the correlation factors, generating multiple sets including other correlation factors, wherein the correlation factors include target correlation factors and other correlation factors; based on the target set in the set, generating the contribution weight difference before and after adding the target correlation factor to the target set; based on each set, obtaining the contribution weight difference corresponding to the set, and taking the weighted average of the multiple contribution weight differences to obtain the contribution weight of the target correlation factor to the target indicator.

[0042] In this embodiment, all subset combinations of the entire set of correlation factors can be traversed. Assume that there are three correlation factors, and the entire set of correlation factors N = {x1, x2, x3}. Traverse all subset combinations, for each factor x i , traverse all the i Subset of

[0043] In the case of calculating the contribution weight of the target correlation factor x1, it is necessary to traverse the following subsets {x2}, {x3}, {x2, x3}. For the subset For each target set in the target index, the first contribution weight of the target set to the target index is generated; after adding the target correlation factor x1 to the target set, the second set is obtained, and the second contribution weight of the second set to the target index is generated. Based on the difference between the first contribution weight and the second contribution weight, the target correlation factor contribution weight is calculated. The contribution weight of the target-related factors of each set in the weighted average is obtained to obtain the contribution weight of the target-related factor x1 to the target indicator.

[0044] The contribution weight difference can be calculated by the following formula in, To characterize the subset The first contribution weight, It is used to represent that after the target correlation factor x1 is added to the target set, a second set is obtained, and a second contribution weight of the second set to the target indicator is generated.

[0045] In this way, by calculating the difference in weights before and after adding the target factor, the interference of other associated factors can be stripped, and the net contribution of the target factor to the indicator can be directly measured; based on the weighted average mechanism of multi-set combination, it can flexibly adapt to the changes in causal relationships in different business scenarios. For example: when the platform adjusts the subsidy rules, the new strategy may change the association strength between "subsidy amount" and "completed order volume", and the multi-set dynamic weights can quickly capture such changes; at the same time, the transparent calculation process of the contribution weight difference provides a traceable basis for business decisions; in addition, when the completed order volume drops sharply, the factor with the largest decrease in contribution weight can be quickly identified. For example, the weight of "weather" drops by 30%, and relevant data anomalies or external events are preferentially investigated.

[0046] In the case where the number of associated factors is too large, it is not feasible to calculate the contribution weights of all subsets in full. The contribution weights can be approximately estimated by randomly arranging the associated factors.

[0047] In some alternative embodiments, generating the contribution weights of associated factors to the target indicator based on the analysis data further includes: if the number of associated factors exceeds a preset number threshold, randomly generating multiple sets of associated factors; constructing a first set of associated factors and calculating the marginal contribution of the associated factors in the first set of associated factors. Among them, based on the first associated factor in the initial set of associated factors, the first set of associated factors is obtained, and the initial set of associated factors is one of the multiple sets of associated factors; based on the order of the associated factors represented by the initial set of associated factors, the second associated factor is sequentially added to the first set of associated factors, and the difference in the marginal contribution of the associated factors before and after adding the second associated factor is calculated; based on the mean value of the marginal contribution of the target associated factor and the difference in the marginal contribution of the associated factors, the contribution weight of the target associated factor to the target indicator is obtained.

[0048] In this embodiment, M sets of associated factors can be randomly generated, and M can take values as an exponent of the number of associated factors N. Each set of associated factors is used to represent a possibility of the order of adding associated factors. For example, the set of associated factors may be x2→x3→x1. The second associated factor is the other associated factors in the initial set of associated factors except the first associated factor.

[0049] Specifically, for each set of associated factors π, the associated factors are sequentially added one by one, and the marginal contribution of each associated factor x i when added is calculated. For example, for the set of associated factors x2→x3→x1, the contribution of x2 added alone needs to be calculated: the contribution of x3 added to the existing subset {x2}: v({x2,x3})-v({x2}); the contribution of x1 added to the existing subset {x2,x3}: v(N)-v({x2,x3}). For each associated factor x i , in all subsets containing xi In the set of associated factors, calculate x i When joining, the marginal contribution is generated, and the mean is taken as x i The contribution weight to the target indicator.

[0050] The M sets of correlation factors may be subjected to distributed computing, and the M sets of correlation factors may be distributed to different nodes of the cluster, with each node processing a subset of the set.

[0051] In this way, by generating a random set of correlated factors and using distributed parallel computing, we address the high complexity of calculating contribution weights for high-dimensional factors. The marginal contribution of a single correlated factor is determined by its average influence across all sets, and the resulting contribution weight reflects its true contribution to the target indicator.

[0052] In some optional embodiments, in response to the adjustment of the contribution weight, an updated analysis result is generated based on the adjusted contribution weight and the analysis data, including: in response to the user's adjustment of the contribution weight, an updated analysis result is generated based on the adjusted contribution weight and the analysis data; and the updated analysis result is presented to the user.

[0053] In this embodiment, the contribution weight adjusted by the user is obtained, for example, the weight of the "weather factor" is increased from 0.2 to 0.3; and an updated analysis result is generated based on the new weight and analysis data. The user can adjust the weight through a visual interface, and the adjusted weight can be written to a distributed cache, which supports millisecond-level reading and writing. The current analysis data can be loaded from the pre-calculated analysis data cache to avoid repeated queries of the initial analysis data. The analysis data can be split into partitions, such as geographic grids or time windows, and the results under the new weights can be calculated in parallel using a distributed framework.

[0054] This allows users to quickly verify hypotheses and meet high-frequency interaction needs. Users can adjust weights multiple times to observe changes in the supply and demand gap in real time and assist in strategy formulation. At the same time, resource reuse and parallel computing can reduce overhead, and through pre-computation and caching mechanisms, repeated calculations of the full data can be avoided. In addition, users are allowed to override the model's preset weights and inject business experience, which can be widely used in marketing, financial analysis, operations management and other fields.

[0055] In some optional embodiments, in response to analysis elements determined by the user, association factors corresponding to the analysis elements are obtained, including: converting the analysis elements into quantifiable features; integrating analysis data based on the quantifiable features to establish an association relationship between the analysis elements and multiple factors; and determining the association relationship that meets the user scenario requirements as the association factor.

[0056] In this embodiment, the user-defined analysis elements are disassembled into quantifiable indicators, and the dimension differences are eliminated through data cleaning and standardization processing to form structured feature vectors. For example, "peak period" can be defined as 7:00 - 9:00 and 17:00 - 19:00. The feature weights are dynamically adjusted according to the business scenario to adapt to different analysis objectives. A feature crossing tool can be used to automatically generate combined features. Integrate user behavior logs, business data, external data, etc. to construct a unified analysis data set; calculate the Pearson correlation coefficient or mutual information value between the features and the target indicators to screen out the preliminary associated factors; based on the user scenario constraints, eliminate the candidate associated factors that do not meet the conditions. For example, "only consider the cost controllable factors", and "advertising budget" will not be a candidate during the budget freeze period.

[0057] In this way, through dynamic feature engineering and rule filtering, it is ensured that the output associated factors are strongly correlated with the user's current scenario; the entire process from the original data to the output of the associated factors is automated; at the same time, the association rules in different scenarios can be accumulated.

[0058] Using the aforementioned method for data processing to calculate the processed data, the contribution degree of different associated factors to the target indicator can be determined, and an analysis result can be generated. Before and after generating the analysis result, the user can be supported to manually adjust different influencing factors, such as adjusting different time ranges, cities, etc. Based on the conditions set by the user and combined with the actual performance of other factors, an analysis result is generated.

[0059] In the related art, there are also problems such as a relatively single visual display method for data, lack of interactivity and in-depth mining functions. At the same time, there is no dynamic interactive dashboard to intuitively analyze the influence ratio of different associated factors, and the change rate between different factors cannot be dynamically calculated according to real-time data. For example, in market promotion analysis, it is difficult to intuitively determine the specific contribution of different promotion channels to sales performance and the differences in different cities or regions from the data, and it is impossible to adjust the strategy in a timely manner according to the data, resulting in lagging or inaccurate decisions, which affect the competitiveness and development of the enterprise.

[0060] In some alternative embodiments, the aforementioned method for data processing further includes: visual presentation based on the initial analysis result, the updated analysis result, or the target analysis result.

[0061] In this embodiment, the analysis data can be presented in the form of a bar chart to show the comparison of different associated factors, or in the form of a line chart to show the trend change of the analysis data. At the same time, presenting the analysis result to the user can enable the user to quickly grasp the overall situation and key factors of the analysis data.

[0062] It can also provide a detailed data viewing function. For example, users can click on a specific area or indicator to view the detailed data of the city in depth, including the specific value or proportion of each data.

[0063] It also allows users to make trend predictions and adjustments based on analytical data. Before and after generating analysis results, users can dynamically set different filtering conditions, i.e., analysis elements, such as time, city, transport company, fleet, or driver. Different filtering conditions will limit the data scope of database queries. Corresponding reports and visual displays can be regenerated according to the settings to meet diverse analysis needs.

[0064] In addition, users can explore data on the data dashboard through interactive operations such as mouse clicks, sliding, or filtering. For example, they can click on elements in a bar chart or line chart to view detailed information, and adjust the layering conditions to instantly view data changes, etc., to achieve efficient data interaction and analysis. Through visual charts, the change curve of the analyzed data within a certain time range and the impact ratio of different factors can be viewed. By interactively switching between charts, the focus can be highlighted on specific indicators, making the influencing factors dynamically adjustable, and recommending and guiding users to view the optimal solution.

[0065] This approach, by displaying analyzed data in bar charts and line graphs, intuitively presents data trends and comparisons. This innovative visual display method combines bar charts and line graphs with analysis results, and provides rich interactive features, such as viewing detailed city data and configuring stratification conditions. This allows users to fully and deeply explore data from a macro to micro perspective, something not available on traditional data dashboards. At the same time, it displays initial, updated, or target analysis results, helping users quickly identify key factors. Users can also view BI reports configured with detailed city data and stratification conditions. Users can delve into data details and flexibly adjust stratification conditions based on their needs, enabling efficient data insights and accurate decision-making. This significantly improves the efficiency and accuracy of data analysis and is suitable for various business scenarios requiring data attribution analysis and visualization. Furthermore, it allows users to freely set stratification conditions, enabling rapid response and generation of corresponding reports and visualizations. This flexible configuration method adapts to different business scenarios and analytical needs, providing users with a personalized data insight experience.

[0066] In some alternative embodiments, after generating the analysis charts and reports, the support platform enables users to perform drill-down analysis. For example, if a user sets an analysis of the completed order volume indicator within a certain time range, in the report we provide, there is a city detail data report that supports users to generally view the increase and decrease change rates of the completed order volume in different cities. At the same time, it also supports users to directly click on a concerned city to jump to a new analysis page and conduct a detailed drill-down analysis of that city, where specific indicator data such as the order issuance volume, the number of drivers on duty, the number of completed orders, and the pick-up and drop-off speed can be viewed. These indicators also support extended analysis by time period to assist users in more intuitively viewing different influencing factors.

[0067] Through intuitive visual displays and analysis results, decision-makers can quickly understand the key information of the data, make accurate decisions in a timely manner, and avoid decision-making mistakes caused by delayed data analysis. At the same time, the city detail data viewing and hierarchical condition configuration functions enable users to deeply explore the hidden information behind the data, discover potential business opportunities and problems, and provide strong support for the enterprise to formulate refined strategies.

[0068] In this embodiment, a data processing device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0069] This embodiment provides a data processing device. Figure 2 The structural schematic diagram of the data processing device according to the embodiment of the present invention is shown, as Figure 2 shown, including:

[0070] A first acquisition module 201, configured to acquire analysis data corresponding to the analysis elements and associated factors corresponding to the analysis elements in response to the analysis elements determined by the user.

[0071] A second acquisition module 202, configured to generate the contribution weights of the associated factors to the target indicators based on the analysis data to obtain an initial analysis result, wherein a mapping relationship between the analysis elements and the target indicators is established based on a data association model.

[0072] A first generation module 203, configured to generate an updated analysis result based on the adjusted contribution weights and the analysis data in response to the adjustment of the contribution weights.

[0073] The second generation module 204 is used to obtain second analysis data corresponding to the adjusted analysis element in response to the user's adjustment of the analysis element, and generate a target analysis result based on the second analysis data and the contribution weight, wherein the analysis element and the adjusted analysis element have the same correlation factor.

[0074] In some optional implementations, the second acquisition module 202 includes:

[0075] The first unit of the second acquisition module is used to generate multiple sets including other correlation factors based on other correlation factors in the correlation factors, wherein the correlation factors include target correlation factors and other correlation factors; based on the target set in the set, generate the contribution weight difference before and after adding the target correlation factor to the target set; based on each set, obtain the contribution weight difference corresponding to the set, and take the weighted average of the multiple contribution weight differences to obtain the contribution weight of the target correlation factor to the target indicator.

[0076] In some optional implementations, the second acquisition module 202 includes:

[0077] The second unit of the second acquisition module is used to randomly generate multiple association factor sets if the number of association factors exceeds a preset number threshold; construct a first association factor set, and calculate the association factor marginal contribution of the first association factor set, wherein the first association factor set is obtained based on the first association factor in the initial association factor set, and the initial association factor set is one of the multiple association factor sets; based on the order of the association factors represented by the initial association factor set, the second association factors are added to the first association factor set one by one, and the difference in association factor marginal contribution before and after the addition of the second target association factor is calculated; based on the association factor marginal contribution of the target association factor and the average of the association factor marginal contribution difference, the contribution weight of the target association factor to the target indicator is obtained.

[0078] In some optional implementations, the first generating module 203 includes:

[0079] The first unit of the first generating module is configured to generate an updated analysis result based on the adjusted contribution weight and analysis data in response to the user's adjustment of the contribution weight; and present the updated analysis result to the user.

[0080] In some optional implementations, the first acquisition module 201 includes:

[0081] The first unit of the first acquisition module is used to convert analysis factors into quantifiable features; integrate analysis data based on the quantifiable features, establish correlation relationships between analysis factors and multiple factors; and determine correlation relationships that meet user scenario requirements as correlation factors.

[0082] In some alternative embodiments, the aforementioned apparatus for data processing further includes:

[0083] A visualization presentation module for performing visualization presentation based on the initial analysis result, the updated analysis result, or the target analysis result.

[0084] The further function descriptions of the above-mentioned respective modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.

[0085] The apparatus for data processing in this embodiment is presented in the form of functional units. Here, the unit refers to an Application Specific Integrated Circuit (ASIC) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0086] The embodiment of the present invention further provides a computer device having the above-mentioned Figure 2 shown apparatus for data processing.

[0087] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As shown in Figure 3 , the computer device includes: one or more processors 10, a memory 20, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of a graphical user interface on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 3 In

[0088] Processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, processor 10 can further include a hardware chip. The above-mentioned hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0089] Among them, the aforementioned memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0090] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0091] The memory 20 may include volatile memory, for example, random access memory; the memory may also include non-volatile memory, for example, flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0092] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 3 Taking connection through a bus as an example.

[0093] The input device 30 can receive input digital or character information, and generate key signal inputs related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (for example, a light-emitting diode), and a tactile feedback device (for example, a vibration motor), etc. The above display device includes but is not limited to a liquid crystal display, a light-emitting diode, a display, and a plasma display. In some alternative embodiments, the display device may be a touch screen.

[0094] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be processed by such software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0095] A part of the present invention can be applied as a computer program product, such as computer program instructions, which when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0096] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for data processing, characterized in that, The method includes: In response to the analysis elements determined by the user, obtaining analysis data corresponding to the analysis elements and associated factors corresponding to the analysis elements; Based on the analysis data, generating contribution weights of the associated factors to the target indicator to obtain an initial analysis result, wherein a mapping relationship between the analysis elements and the target indicator is established based on a data association model; In response to the adjustment of the contribution weights, generating an updated analysis result based on the adjusted contribution weights and the analysis data; or, In response to the adjustment of the analysis elements by the user, obtaining second analysis data corresponding to the adjusted analysis elements, and generating a target analysis result based on the second analysis data and the contribution weights, wherein the analysis elements and the adjusted analysis elements have the same associated factors.

2. The method according to claim 1, characterized in that, The generating the contribution weights of the associated factors to the target indicator based on the analysis data includes: Based on other associated factors in the associated factors, generating a plurality of sets including the other associated factors, wherein the associated factors include a target associated factor and the other associated factors; Based on the target set in the sets, generating a difference in contribution weights before and after adding the target associated factor to the target set; Based on each of the sets, obtaining the contribution weight differences corresponding to the sets, and performing weighted averaging on the plurality of contribution weight differences to obtain the contribution weight of the target associated factor to the target indicator.

3. The method according to claim 1 or 2, characterized in that, The generating the contribution weights of the associated factors to the target indicator based on the analysis data further includes: If the number of the associated factors exceeds a preset number threshold, randomly generating a plurality of sets of associated factors; Constructing a first set of associated factors, and calculating the marginal contribution of the associated factors in the first set of associated factors, wherein the first set of associated factors is obtained based on the first associated factor in the initial set of associated factors, and the initial set of associated factors is one of the plurality of sets of associated factors; Based on the order of the associated factors represented by the initial set of associated factors, sequentially adding a second associated factor to the first set of associated factors, and calculating the difference in marginal contribution of the associated factors before and after adding the second associated factor; Based on the average of the marginal contribution of the target associated factor and the difference in marginal contribution of the associated factors, obtaining the contribution weight of the target associated factor to the target indicator.

4. The method according to claim 1, wherein The generating an updated analysis result based on the adjusted contribution weights and the analysis data in response to the adjustment of the contribution weights includes: In response to the adjustment of the contribution weights by the user, generating the updated analysis result based on the adjusted contribution weights and the analysis data; Presenting the updated analysis result to the user.

5. The method according to claim 1, wherein The obtaining the associated factors corresponding to the analysis elements in response to the analysis elements determined by the user includes: Converting the analysis elements into quantifiable features; Integrating the analysis data based on the quantifiable features, and establishing an association relationship between the analysis elements and multiple factors; Determining the association relationship that meets the user scenario requirements as the associated factors.

6. The method according to claim 1, wherein The method further includes: performing visual presentation based on the initial analysis result, the updated analysis result, or the target analysis result.

7. A device for data processing, characterized in that, The apparatus includes: A first acquisition module, configured to acquire analysis data corresponding to the analysis element and associated factors corresponding to the analysis element in response to an analysis element determined by a user; A second acquisition module, configured to generate a contribution weight of the associated factor to a target indicator based on the analysis data to obtain an initial analysis result, wherein a mapping relationship between the analysis element and the target indicator is established based on a data association model; A first generation module, configured to generate an updated analysis result based on the adjusted contribution weight and the analysis data in response to an adjustment of the contribution weight; A second generation module, configured to acquire second analysis data corresponding to the adjusted analysis element in response to an adjustment of the analysis element by the user, and generate a target analysis result based on the second analysis data and the contribution weight, wherein the analysis element and the adjusted analysis element have the same associated factors.

8. A computer device, characterized in that, Comprising: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for data processing according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method for data processing according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Comprising computer instructions, the computer instructions are used to cause a computer to execute the method for data processing according to any one of claims 1 to 6.

Images