Method, device, equipment, medium and program product for analyzing business data

Abstract

This application discloses a method, apparatus, device, medium, and program product for analyzing business data, belonging to the field of data processing. The method includes: acquiring at least two types of business data for a target business; for a first type of business data among the at least two types, calculating the uncertainty of a second type of business data given the first type of business data, obtaining an uncertainty score corresponding to the first type of business data, where the first type of business data is any one of the at least two types, and the second type of business data is any other type of business data besides the first type; selecting key types of business data from the at least two types of business data whose uncertainty scores satisfy a first score condition; and analyzing the key types of business data. This application, by calculating the uncertainty score corresponding to each type of business data, can determine the key types of business data, and further, by analyzing the key types of business data, can obtain more accurate analysis results for the target business.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, apparatus, equipment, medium, and program product for analyzing business data. Background Technology

[0002] In some business scenarios, it is necessary to analyze and mine business data to provide decision support.

[0003] In related technologies, different categories of business data are often analyzed separately, and the results are combined to create an analysis report. For example, for merchant operations, sales and customer data are acquired. Regression analysis of the sales data's time series is used to predict future sales trends; and cluster analysis of customer data is performed to segment customers into different groups, predicting potential future customer groups. The analysis report is then generated by combining the results of the sales and customer data analyses.

[0004] The business data analysis methods provided by related technologies actually assume that different types of business data meet the same distribution conditions. However, these assumptions may not actually be met, and the output analysis report may not be accurate. Summary of the Invention

[0005] This application provides a method, apparatus, device, medium, and program product for analyzing business data. By calculating the uncertainty score corresponding to each type of business data, this application can identify key types of business data, and then by analyzing the key types of business data, it can obtain more accurate analysis results for the target business.

[0006] According to one aspect of this application, a method for analyzing business data is provided, the method comprising:

[0007] Obtain at least two types of business data for the target business;

[0008] For the first type of business data in at least two types of business data, calculate the degree of uncertainty of the second type of business data given the first type of business data, and obtain the uncertainty score corresponding to the first type of business data. The first type of business data is any one of the at least two types of business data, and the second type of business data is other types of business data besides the first type of business data.

[0009] From at least two types of business data, select key business data whose uncertain scores meet the first score condition; analyze the key business data.

[0010] According to another aspect of this application, a method for analyzing merchant operating data is provided, the method comprising:

[0011] Obtain at least two types of merchant operation data from the target merchant;

[0012] For the first type of merchant operating data in at least two types of merchant operating data, calculate the uncertainty of the second type of merchant operating data given the first type of merchant operating data, and obtain the uncertainty score corresponding to the first type of merchant operating data. The first type of merchant operating data is any one of the at least two types of merchant operating data, and the second type of merchant operating data is other types of merchant operating data besides the first type of merchant operating data.

[0013] From at least two types of merchant operating data, select key merchant operating data whose uncertain scores meet the first score condition; analyze the key merchant operating data.

[0014] According to another aspect of this application, a business data analysis apparatus is provided, the apparatus comprising:

[0015] The acquisition module is used to acquire at least two types of business data for the target business.

[0016] The calculation module is used to calculate the degree of uncertainty of the second type of business data given the first type of business data in at least two types of business data, and to obtain the uncertainty score corresponding to the first type of business data. The first type of business data is any one of the at least two types of business data, and the second type of business data is other types of business data besides the first type of business data.

[0017] The filtering module is used to filter out key business data whose uncertain scores meet the first score condition from at least two types of business data;

[0018] The analysis module is used to analyze key business data.

[0019] In an optional embodiment, the second type of business data corresponds to at least two values;

[0020] The calculation module is further configured to obtain the probability of each of the at least two values ​​under the second type of business data given the first type of business data, and to obtain at least two probability values.

[0021] Based on the at least two probability values, the information entropy is calculated, and the information entropy is used to measure the degree of uncertainty of the second type of business data given the first type of business data;

[0022] Based on the information entropy, the uncertain score corresponding to the first type of business data is obtained.

[0023] In an optional embodiment, the first type of business data corresponds to m first values, and the second type of business data corresponds to n second values, where m and n are integers greater than one.

[0024] The acquisition module is further configured to acquire the probability of the second type of business data acquiring each second value when the first type of business data acquires each first value, thereby obtaining m*n value probabilities;

[0025] The calculation module is also used to calculate m first information entropies based on the m*n value probabilities, wherein each of the m first information entropies is calculated based on the n value probabilities corresponding to a first value;

[0026] The m first information entropies are weighted and summed to obtain the second information entropy, where the weight of each first information entropy is the probability of the corresponding first value.

[0027] The second information entropy is determined as the information entropy.

[0028] In an optional embodiment, the filtering module is further configured to filter out the key category of business data from the at least two categories of business data whose uncertainty score is less than a first score threshold;

[0029] or,

[0030] From the at least two types of business data, select the key type of business data whose uncertain scores rank in the top p when sorted from smallest to largest, where p is a positive integer.

[0031] In an optional embodiment, the calculation module is further configured to calculate the contribution score of each type of business data in the at least two types of business data to the business strategy;

[0032] A weighted summation is performed on the contribution score and the uncertainty score of each type of business data to obtain the criticality score of each type of business data;

[0033] The filtering module is further configured to filter out the key business data whose key scores satisfy the second score condition from the at least two types of business data.

[0034] In an optional embodiment, the calculation module is further configured to obtain a business strategy model, the business strategy model including at least two model parameters, the at least two model parameters corresponding one-to-one with the at least two types of business data, and the business strategy model being configured to output the execution probability of the business strategy based on the at least two types of business data;

[0035] Based on the product of the at least two types of business data and the at least two model parameters according to their corresponding relationships, the contribution score of each type of business data to the business strategy is obtained.

[0036] In an optional embodiment, the filtering module is further configured to filter out the key business data whose criticality score is greater than the second score threshold from the at least two types of business data;

[0037] or,

[0038] From the at least two types of business data, select the top q key business data items when the key scores are sorted from largest to smallest, where q is a positive integer.

[0039] In an optional embodiment, the apparatus further includes an output module, which is used to generate improvement suggestions for the target business based on the analysis results of the key business data.

[0040] The analysis results and improvement suggestions are output as a business report for the target business.

[0041] In an optional embodiment, the analysis module is further configured to analyze the relationship between the key business data and the business indicators of the target business, and obtain the analysis results of the key business data.

[0042] In an optional embodiment, the target business is merchant operation business, and the at least two types of business data are different categories of merchant operation data;

[0043] or,

[0044] The target business is teaching business, and the at least two types of business data are different categories of teaching data;

[0045] or,

[0046] The target business is delivery business, and the at least two types of business data are different categories of delivery data;

[0047] or,

[0048] The target business is tourism business, and the at least two types of business data are different categories of tourism data.

[0049] According to one aspect of this application, a computer device is provided, comprising: a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the above-mentioned method for analyzing business data, or method for analyzing merchant operating data.

[0050] According to another aspect of this application, a computer-readable storage medium is provided, which stores a computer program that is loaded and executed by a processor to implement the above-mentioned method for analyzing business data or a method for analyzing merchant operating data.

[0051] According to another aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned method for analyzing business data or merchant operating data.

[0052] The beneficial effects of the technical solutions provided in this application include at least the following:

[0053] In this embodiment of the application, at least two types of business data will be acquired, the uncertainty of other types of business data after each type of business data is given will be calculated, the uncertainty score corresponding to each type of business data will be obtained, and then the key types of business data that meet the first score condition will be screened out and the key types of business data will be analyzed.

[0054] It is understandable that the smaller the uncertainty score corresponding to a certain type of business data, the more certain the other types of business data are after that type of business data is given. Therefore, the given type of business data is more critical among at least two types of business data. The analysis results obtained by analyzing the key type of business data can better represent the overall analysis results, and the final output of the overall analysis results is more accurate. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram illustrating the principle of a business data analysis method provided in one embodiment of this application.

[0057] Figure 2 This is a flowchart of a business data analysis method provided in one embodiment of this application.

[0058] Figure 3 This is a schematic diagram of a method for calculating an uncertain fraction provided in one embodiment of this application.

[0059] Figure 4This is a flowchart of a method for calculating an uncertain fraction provided in one embodiment of this application.

[0060] Figure 5 This is a flowchart of a method for calculating an uncertain fraction provided in another embodiment of this application.

[0061] Figure 6 This is a flowchart of a business data analysis method provided in another embodiment of this application.

[0062] Figure 7 This is a flowchart of a merchant operation data analysis method provided in one embodiment of this application.

[0063] Figure 8 This is a flowchart of a method for analyzing merchant operating data provided in another embodiment of this application.

[0064] Figure 9 This is a flowchart of a teaching data analysis method provided in one embodiment of this application.

[0065] Figure 10 This is a flowchart of a teaching data analysis method provided in another embodiment of this application.

[0066] Figure 11 This is a flowchart of a delivery data analysis method provided in one embodiment of this application.

[0067] Figure 12 This is a flowchart of a delivery data analysis method provided in another embodiment of this application.

[0068] Figure 13 This is a flowchart of a tourism data analysis method provided in one embodiment of this application.

[0069] Figure 14 This is a flowchart of a tourism data analysis method provided in another embodiment of this application.

[0070] Figure 15 This is a structural block diagram of a business data analysis device provided in one embodiment of this application.

[0071] Figure 16 This is a structural block diagram of a computer device provided in an exemplary embodiment of this application.

[0072] Figure 17 This is a structural block diagram of a computer device provided in another exemplary embodiment of this application. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be further described below with reference to the accompanying drawings. It should be noted that the information (including but not limited to tabular data), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. Furthermore, regarding related information, the relevant information processor will adhere to the principles of legality, legitimacy, and necessity, clearly define the purpose, method, and scope of the relevant information processing, obtain the consent of the relevant information subject, and take necessary technical and organizational measures to ensure the security of the relevant information.

[0074] First, a brief introduction to the relevant terms used in this application will be given.

[0075] Business data refers to the relevant data generated by the target business. Specifically, business data is the data generated during the operation of the target business. By analyzing business data, we can understand the operation of the target business. Therefore, the analysis results based on business data can provide support for decision-making in the target business.

[0076] Optionally, target business areas include merchant operations, education, delivery, and tourism. For example, business data for merchant operations includes categories such as sales data, inventory data, customer data, competitor data, and market trend data. For example, business data for education includes categories such as learning duration, learning methods, and number of students. For example, business data for delivery includes categories such as delivery time, number of deliveries, and delivery area. For example, business data for tourism includes categories such as number of tourists, travel dates, and travel destinations.

[0077] In each business scenario, it is necessary to analyze the business data of each scenario in order to understand the operation of the business and provide corresponding decision support. Figure 1 A schematic diagram illustrating the principle of a business data analysis method provided in an exemplary embodiment of this application is shown, illustratively described by way of the method being executed by a computer device. Figure 1 Computer device 10 is shown, which performs a business data analysis process 100.

[0078] In the analysis process 100, at least two types of business data for the target business are acquired. Figure 1 The diagram illustrates k types of business data for acquiring the target business, denoted as business data 1, business data 2, and so on, up to business data k. For each type of business data, the uncertainty of other types of business data is calculated given each type of business data, resulting in an uncertainty score for each type of business data.

[0079] "Given" refers to the operation of setting business data to a known state.

[0080] Figure 1 In this process, the uncertainty of business data 2 to business data k is calculated given business data 1, resulting in uncertainty score 1 for business data 1; the uncertainty of business data 1, business data 3 to business data k is calculated given business data 2, resulting in uncertainty score 2 for business data 2; and so on, k uncertainty scores can be calculated, and each of the k uncertainty scores corresponds one-to-one with the given k types of business data.

[0081] After calculating k uncertain scores, key business data whose uncertain scores meet a first score condition are selected from the k types of business data. This key business data is then analyzed to obtain the analysis results. In one embodiment, key business data with uncertain scores less than a first score threshold are selected from the k types of business data. Optionally, the first score threshold is a preset score threshold. In another embodiment, key business data whose uncertain scores rank among the top p when sorted from smallest to largest are selected from the k types of business data. Optionally, p is a preset sorting threshold, for example, p = 1.

[0082] It should be noted that the smaller the uncertainty score corresponding to a certain type of business data, the more certain the other types of business data are after that type of business data is given. Therefore, the given type of business data is more critical among all the business data. The analysis results obtained by analyzing the key type of business data can better represent the overall analysis results, and thus the output of the overall analysis results is more accurate.

[0083] In some embodiments, the business data analysis method provided in this application is executed by a computer device, which includes at least one of a terminal and a server. The terminal device types include at least one of: smartphones, smartwatches, in-vehicle terminals, wearable devices, smart TVs, tablets, e-book readers, MP3 players, MP4 players, laptops, and desktop computers.

[0084] In some embodiments, the server may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms.

[0085] Figure 2A flowchart illustrating a business data analysis method provided in an exemplary embodiment of this application is shown, in which the method is... Figure 1 The computer device shown is used to illustrate, for example, the method including:

[0086] Step 220: Obtain at least two types of business data for the target business;

[0087] The target businesses include merchant operations, education, delivery, and tourism. Different businesses correspond to different business data, and each business has multiple types of business data. Business data refers to the data generated during the operation of the target businesses.

[0088] In one embodiment, after collecting at least two types of business data for the target business, a data preprocessing process is performed to obtain updated at least two types of business data. Optionally, the data preprocessing process includes cleaning, noise reduction, normalization, and other processing steps on the collected at least two types of business data.

[0089] Optionally, the data preprocessing process can be implemented through the following steps.

[0090] 1. Missing value handling: For missing data in at least two types of business data, methods such as mean filling and median filling can be used to fill the missing data to ensure the uniformity and integrity of the data structure.

[0091] 2. Outlier handling: Detect outliers in at least two types of business data and handle them using appropriate methods, such as deleting outliers or replacing them with the mean.

[0092] 3. Data Normalization: Normalize each data point from at least two categories of business data to the interval [0, 1] for subsequent analysis and calculation. For illustration, assume an original data point is x. i The normalized data is y i The data normalization formula is:

[0093]

[0094] Where X contains the original data x i All data within the category to which it belongs.

[0095] Data normalization aligns each type of business data from at least two different categories into the same data space, facilitating subsequent data processing and analysis within that shared space. For example, through data preprocessing, the original sales data (e.g., 100 items sold per day) can be normalized to a value of 0.2, and the original sales data (e.g., 200 items sold per day) can be normalized to a value of 0.4. Similarly, the original inventory data (e.g., 1000 remaining inventory items in the first quarter) can be normalized to a value of 0.5, and the original inventory data (e.g., 1500 remaining inventory items in the second quarter) can be normalized to a value of 0.75. In this way, both sales and inventory data will be normalized to the same data space.

[0096] Step 240: For the first type of business data in at least two types of business data, calculate the degree of uncertainty of the second type of business data given the first type of business data, and obtain the uncertainty score corresponding to the first type of business data.

[0097] The first type of business data is any one of at least two types of business data, and the second type of business data is any other type of business data besides the first type.

[0098] In this embodiment, for each of at least two types of business data, the uncertainty of other types of business data is calculated given the current type of business data, resulting in an uncertainty score corresponding to the current type of business data. The uncertainty score measures the uncertainty of other types of business data given a certain type of business data. Optionally, the uncertainty can be measured by calculating information entropy. Information entropy is a common concept in information theory, used to describe the uncertainty of possible events occurring from an information source.

[0099] In one embodiment, the second type of business data includes multiple other types of business data. The sub-uncertainty of each other type of business data is calculated given the first type of business data. Based on the sub-uncertainty of each other type of business data, the uncertainty score corresponding to the first type of business data is obtained.

[0100] This is illustrative, involving at least two types of business data, including k types of business data, namely business data 1 to business data k, used as an example to illustrate the calculation of the uncertain score corresponding to business data 1. Specifically, for example... Figure 3 As shown, the uncertainty of business data 2 given business data 1 is calculated to obtain the first sub-uncertainty; the uncertainty of business data 3 given business data 1 is calculated to obtain the second sub-uncertainty; and so on, the uncertainty of business data k given business data 1 is calculated to obtain the (k-1)th sub-uncertainty; based on the first to the (k-1)th sub-uncertainty, the uncertainty score 1 corresponding to business data 1 is obtained.

[0101] Optionally, the uncertainty score for the first type of business data can be obtained by weighted averaging of the sub-uncertainties of each type of other business data. (Illustrative example, such as...) Figure 3 As shown, the weighted average of the first to (k-1)th sub-uncertainties is calculated to obtain the uncertainty score 1 corresponding to business data 1. Optionally, the weighting of each sub-uncertainty corresponds to the type of each other business data category. For example... Figure 3 As shown, the weighted weight corresponding to the first sub-uncertainty is the weight 2 corresponding to business data 2, the weighted weight corresponding to the second sub-uncertainty is the weight 3 corresponding to business data 3, and the weighted weight corresponding to the (k-1)th sub-uncertainty is the weight k corresponding to business data k.

[0102] Optionally, the weighted weights corresponding to the sub-uncertainty levels of each other business data category are parameters obtained by training an artificial intelligence model. In this case, an artificial intelligence model will be trained. The input to this model is at least two categories of business data, and the output is key business data. The model parameters to be trained are the weighted weights corresponding to each category of business data. For example, the weighted weight for category A business data is 'a', the weighted weight for category B business data is 'b', and the weighted weight for category C business data is 'c'. It can be understood that this application uses an artificial intelligence model to calculate the uncertainty score corresponding to each category of business data; that is, this application uses an artificial intelligence model to determine key business data, which can improve the accuracy of the determined key business data.

[0103] Step 260: From at least two types of business data, select key types of business data whose uncertain scores meet the first score condition;

[0104] For each of the at least two categories of business data, the smaller the uncertainty score corresponding to the current category of business data, the more certain the other categories of business data are after the current category of business data is given, and thus the given current category of business data is more critical. In one embodiment, critical categories of business data with uncertainty scores less than a first score threshold are selected from the at least two categories of business data; for example, critical categories of business data with uncertainty scores less than 0.1 are selected from the at least two categories of business data. Optionally, if the number of categories with uncertainty scores greater than 0.1 is greater than a first preset number, the business data category with the smallest uncertainty score is selected to avoid selecting too many critical categories of business data.

[0105] At this point, the above embodiment will determine the key business data by using the first score threshold. The operation is simple and easy to implement, and it can effectively determine the key business data.

[0106] In another embodiment, from at least two types of business data, key business data that rank among the top p in terms of uncertain scores when sorted from smallest to largest, where p is a positive integer, are selected. For example, the uncertain scores corresponding to at least two types of business data are sorted in ascending order, and the top three business data are identified as key business data. Optionally, after selecting the top p smallest key business data, further selection is made for key business data with uncertain scores less than a first preset score to avoid the uncertain scores corresponding to the top p smallest business data still being too large, thus preventing the identification of false key business data.

[0107] At this point, the above embodiment will determine key business data by card ranking, which is simple to operate, easy to implement, and can effectively determine key business data.

[0108] Step 280: Analyze key business data.

[0109] In one embodiment, the correlation between key business data and target business metrics is analyzed to obtain the analysis results for the key business data. Optionally, the correlation can be calculated using the following formula:

[0110]

[0111] In this context, it is assumed that both key business data and business metrics have n possible values, x i y represents the i-th value in the key business data. i This represents the i-th value of the business metric, and r represents the correlation between key business data and the business metric. The calculated correlation (degree of correlation) is output as the analysis result. This represents the average value of n key business data categories. This represents the average value of n business indicators.

[0112] In one embodiment, after analyzing key business data, improvement suggestions for the target business are generated based on the analysis results. For example, if the key business data has a weak correlation with a first indicator, the improvement suggestions would include increasing the correlation between the key business data and the first indicator. The analysis results and improvement suggestions are then output as a business report for the target business.

[0113] Optionally, business reports may include text descriptions, charts, data analysis, and other formats.

[0114] In summary, this application provides a business data analysis method applicable to various business scenarios. By calculating uncertainty scores, key business data categories are filtered out, and then analyzed. The analysis results of these key business data categories are output as the overall analysis results, thus improving the accuracy of the overall analysis results. Optionally, at least two types of business data are collected again at regular intervals to redetermine the key business data categories, thereby updating the analysis results and ensuring their real-time nature.

[0115] The following section will use the example of the second category of business data including one category of other business data to illustrate the calculation process of the uncertainty score for the first category of business data. Similarly, when the second category of business data includes multiple categories of other business data, the degree of sub-certainty can be calculated for each category of other business data in a similar manner, and then the uncertainty score for the first category of business data can be calculated based on the degree of sub-certainty of each category of other business data.

[0116] based on Figure 2 In the optional embodiment shown, the second type of business data corresponds to at least two values, and step 240 includes... Figure 4 Steps 420 to 460 are shown.

[0117] Step 420: Obtain the probability of at least two values ​​corresponding to the second type of business data given the first type of business data, and obtain the probability of at least two values.

[0118] Step 440: Based on at least two probability values, calculate the information entropy, which is used to measure the degree of uncertainty of the second type of business data given the first type of business data.

[0119] Step 460: Based on information entropy, obtain the uncertain score corresponding to the first type of business data.

[0120] Optionally, the information entropy can be defined as the uncertain fraction corresponding to the first type of business data.

[0121] As illustrated in Table 1 below, at least two types of business data include business data 1 and business data 2, where business data 2 has values ​​of 0.1, 0.2, and 0.3. Table 1 shows that, given business data 1, the probability of business data 2 taking the value 0.1 is 20%, the probability of taking the value 0.2 is 30%, and the probability of taking the value 0.3 is 50%.

[0122] Table 1

[0123] Business Data 1 Business Data 2 Business Data 1 0.1(20％) Business Data 1 0.2(30％) Business Data 1 0.3(50％)

[0124] Based on these three probability values, information entropy is calculated to obtain the degree of uncertainty of business data 2 given business data 1.

[0125] As an illustration, the formula for calculating information entropy is:

[0126]

[0127] Where X includes three values ​​of business data 2, n is 3, x i p(x) represents the i-th value of business data 2. i Let represent the probability of the i-th value given business data 1, and let H(X) represent the information entropy of business data 2 given business data 1.

[0128] Understandably, this application, by calculating information entropy, can more accurately quantify the criticality of different categories of business data, and by analyzing key categories of business data, can provide more accurate overall analysis results.

[0129] In one embodiment, the first type of business data corresponds to m first values, and the second type of business data corresponds to n second values, where m and n are integers greater than one; step 240 includes Figure 5 Steps 510 to 550 are shown.

[0130] Step 510: Obtain the probability that the second type of business data will obtain each second value when the first type of business data obtains each first value, and obtain m*n value probabilities.

[0131] Step 520: Based on the m*n probability values, calculate m first information entropies. Each of the m first information entropies is calculated based on the n probability values ​​corresponding to a first value.

[0132] Step 530: Perform a weighted summation on the m first information entropies to obtain the second information entropy. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0133] Step 540: Determine the second information entropy as the information entropy;

[0134] Step 550: Obtain the uncertain score corresponding to the first type of business data based on information entropy.

[0135] Optionally, the information entropy can be defined as the uncertain fraction corresponding to the first type of business data.

[0136] As illustrated in Table 2 below, at least two types of business data include Business Data 1 and Business Data 2. Business Data 1 corresponds to values ​​of 0.3 and 0.4, and Business Data 2 corresponds to values ​​of 0.1, 0.2, and 0.3. Table 2 shows that, given a value of 0.3 for Business Data 1, the probability of obtaining a value of 0.1 for Business Data 2 is 20%, the probability of obtaining a value of 0.2 is 30%, and the probability of obtaining a value of 0.3 is 50%. Furthermore, given a value of 0.4 for Business Data 1, the probability of obtaining a value of 0.1 for Business Data 2 is 10%, the probability of obtaining a value of 0.2 is 20%, and the probability of obtaining a value of 0.3 is 70%.

[0137] Table 2

[0138]

[0139]

[0140] Based on the six possible values ​​mentioned above, two first information entropies are calculated, each corresponding to one value of business data 1. A weighted sum is then performed on the two first information entropies to obtain a second information entropy, where the weight of each first information entropy includes the probability of one value of business data 1.

[0141] The second information entropy is calculated illustratively using the following formula:

[0142]

[0143] Where X includes the three possible values ​​of business data 2, Y includes the three possible values ​​of business data 1, P(x|y) represents the probability of a possible value of business data 2 given a possible value of business data 1, and P(y) represents the probability of a possible value of business data 1. This represents a first information entropy.

[0144] Understandably, this application, by calculating information entropy, can more accurately quantify the criticality of different business data, and by analyzing key types of business data, can provide more accurate overall analysis results.

[0145] Figure 6 A flowchart illustrating a business data analysis method provided in an exemplary embodiment of this application is shown, illustratively described by way of the method being performed by a computer device. The method includes:

[0146] Step 610: Obtain at least two types of business data for the target business;

[0147] The target businesses include merchant operations, education, delivery, and tourism. Different businesses have different business data, and each business has multiple types of business data. For a detailed explanation of step 610, please refer to step 220 above.

[0148] Step 620: For the first type of business data in at least two types of business data, calculate the uncertainty of the second type of business data given the first type of business data, and obtain the uncertainty score corresponding to the first type of business data.

[0149] The first type of business data is any one of at least two types of business data, and the second type of business data is any other type of business data besides the first type.

[0150] For a detailed explanation of step 620, please refer to step 240 above.

[0151] Step 630: Calculate the contribution score of each type of business data to the business strategy in at least two types of business data.

[0152] Business strategy is the execution strategy for a business. For example, launching new products in a merchant business is a business strategy, expanding student enrollment in an educational business is a business strategy, updating rider equipment in a delivery business is a business strategy, and increasing advertising in a tourism business is a business strategy.

[0153] Contribution score is used to measure the role of each type of business data in executing business strategies.

[0154] In one embodiment, the business strategy includes multiple business strategies. The contribution score of each type of business data in at least two types of business data to each business strategy is calculated to obtain the contribution score corresponding to each type of business strategy. For example, the business strategy includes business strategy 1 and business strategy 2. The contribution score of each type of business data to business strategy 1 is calculated to obtain contribution score 1; and the contribution score of each type of business data to business strategy 2 is calculated to obtain contribution score 2. Based on the average of contribution score 1 and contribution score 2, the contribution score corresponding to each type of business data is calculated.

[0155] In one embodiment, a business strategy model is pre-established. The business strategy model includes at least two model parameters, which correspond one-to-one with at least two types of business data. The business strategy model is used to output the execution probability of the business strategy based on at least two types of business data.

[0156] Optionally, the business strategy model is a logistic regression model, and the expression of the business strategy model is as follows:

[0157]

[0158] Where, β i Let x represent the i-th model parameter. i Let represent the i-th type of business data. In the above expression, it is assumed that there are p model parameters and p types of business data. β0 is a constant, and P(Y=1|X) represents the probability of executing a business strategy based on at least two types of business data.

[0159] In one embodiment, the contribution score of each type of business data to the business strategy is obtained by multiplying at least two types of business data with at least two model parameters according to their corresponding relationships.

[0160] That is, for the i-th type of business data, the contribution score of the i-th type of business data to the business strategy is represented by β. i x i .

[0161] In the above embodiments, by calculating the contribution score of each type of business data to the business strategy, the absolute criticality of each type of business data can be obtained, and thus more accurate key business data can be determined below.

[0162] In one embodiment, when training a business strategy model, the following steps are performed: The dataset is divided into a training set and a test set. On the training set, a logistic regression algorithm is used to build the business strategy model. On the test set, the performance of the business strategy model, such as accuracy and recall, is evaluated.

[0163] Step 640: Perform a weighted summation of the contribution score and uncertainty score for each type of business data to obtain the criticality score for each type of business data;

[0164] The contribution score and uncertainty score for each type of business data have been calculated above. A weighted sum of these scores yields the criticality score for each type of business data. Optionally, the criticality score for each type of business data can be calculated using the following formula:

[0165] CI i =αPS i +βH(X|Y i );

[0166] Among them, CI i PS represents the criticality score of the i-th type of business data. i H(X|Y) represents the contribution score corresponding to the i-th type of business data. i Let represent the uncertain score corresponding to the i-th type of business data, and α and β be the weighted weights corresponding to the critical score and uncertain score, respectively. Optionally, the weighted weights can be empirical values. Alternatively, the weighted weights can be parameters obtained by training an artificial intelligence model.

[0167] Step 650: From at least two types of business data, select key business data whose key scores meet the second score condition;

[0168] For each of the at least two types of business data, the higher the criticality score of the current type of business data, the more critical the current type of business data is. In other words, the analysis results of the current type of business data are more representative of the analysis results of all types of business data. In this case, the overall analysis results obtained are more focused and more accurate.

[0169] In one embodiment, key business data with a criticality score greater than a second score threshold are selected from at least two types of business data. For example, key business data with a criticality score greater than 0.8 are selected from at least two types of business data. Optionally, if the number of categories with a criticality score greater than 0.8 is greater than a second preset number, the business data category with the highest criticality score is selected to avoid selecting too many key business data categories.

[0170] At this point, the above embodiment will determine the key business data by using the second score threshold. The operation is simple and easy to implement, and it can effectively determine the key business data.

[0171] In another embodiment, from at least two types of business data, key business data that rank among the top q in terms of criticality score when sorted from largest to smallest, where q is a positive integer, are selected. For example, the criticality scores corresponding to at least two types of business data are sorted in descending order, and the top three business data are identified as key business data. Optionally, after selecting the top q key business data, further selection is made for key business data with criticality scores greater than a second preset score to avoid identifying false key business data where the criticality scores of the top q business data are still too small.

[0172] At this point, the above embodiment will determine key business data by card ranking, which is simple to operate, easy to implement, and can effectively determine key business data.

[0173] Step 660: Analyze key business data.

[0174] For a detailed explanation of step 660, please refer to step 280 above.

[0175] In summary, the above embodiments combine the uncertainty score and contribution score of each type of business data to determine the criticality score of each type of business data. This not only assesses the criticality of each type of business data from the perspective of its relative criticality compared to other types of business data, but also assesses the criticality of each type of business data from the perspective of its absolute criticality. Therefore, a more accurate criticality score can be generated for each type of business data, thereby enabling a more accurate identification of key types of business data.

[0176] Application Scenario Examples

[0177] The following section will introduce how the above-mentioned business data analysis methods are applied to merchant operations.

[0178] Figure 7 A flowchart illustrating an exemplary embodiment of this application of a method for analyzing merchant operating data is shown, exemplified by the method being executed by a computer device. The method includes:

[0179] Step 720: Obtain at least two types of merchant operation data from the target merchant;

[0180] Target merchants refer to the merchants targeted by the analytical methods provided in this application. At least two types of merchant operating data are included, such as sales data, inventory data, customer data, competitor data, and market trend data.

[0181] Sales data refers to data related to the sales of goods, such as sales price, sales quantity, sales time, and sales location. Inventory data refers to data related to the inventory of goods, such as the quantity of goods in stock, the production date of goods in stock, and the types of goods in stock. Customer data refers to data related to the merchant's customers, such as the age range of the main customer group and customers' historical purchase records. Competitor data includes data related to merchants that compete with the current merchant, such as their sales data, establishment date, and customer reviews. Market trend data includes current market trend data, including the product IDs with the highest search volume, the product IDs with the highest sales volume, and the product IDs with the highest ratings, etc.

[0182] In related technologies, when analyzing merchant business data, only internal merchant data (including sales data, inventory data, and customer data) is analyzed, without analyzing competitor data and market trend data. Optionally, this application also considers external merchant data and integrates it into the overall analysis process, thereby providing more accurate and comprehensive data analysis results.

[0183] In one embodiment, merchant internal data is obtained from various business systems of the target business. For example, sales data is obtained from the sales system of the target business; inventory data is obtained from the inventory system of the target business; and customer data is obtained from the customer management system of the target business. Additionally, market trend data and competitor data are manually collected and input into the data analysis system of this application.

[0184] Step 740: For the first type of merchant operating data in at least two types of merchant operating data, calculate the degree of uncertainty of the second type of merchant operating data given the first type of merchant operating data, and obtain the uncertainty score corresponding to the first type of merchant operating data;

[0185] The first category of merchant operating data includes any one of the at least two categories of merchant operating data, while the second category includes other categories of merchant operating data besides the first category.

[0186] In this embodiment, for each of the at least two types of merchant operating data, the uncertainty of other types of merchant operating data is calculated given the current type of merchant operating data, resulting in an uncertainty score corresponding to the current type of merchant operating data. The uncertainty score measures the uncertainty of other types of merchant operating data given a certain type of merchant operating data. Optionally, the uncertainty can be measured by calculating information entropy. Information entropy is a common concept in information theory, used to describe the uncertainty of possible events occurring from an information source.

[0187] In one embodiment, the second type of merchant operating data corresponds to at least two values.

[0188] Given the operating data of the first type of merchant, obtain the probability of at least two values ​​corresponding to the operating data of the second type of merchant, and obtain the probability of at least two values.

[0189] Information entropy is calculated based on at least two possible values. Information entropy is used to measure the degree of uncertainty of the operating data of the second type of merchant given the operating data of the first type of merchant.

[0190] Based on information entropy, the uncertain scores corresponding to the operating data of the first type of merchants are obtained.

[0191] In another embodiment, the first type of merchant operating data corresponds to m first values, and the second type of merchant operating data corresponds to n second values, where m and n are integers greater than one.

[0192] Given that the first value is obtained for each of the first-class merchant operating data, the probability of the second-class merchant operating data obtaining each of the second-class values ​​is obtained, resulting in m*n probability values.

[0193] Based on m*n probability values, m first information entropies are calculated. Each of the m first information entropies is calculated based on the n probability values ​​corresponding to a first value.

[0194] The second information entropy is obtained by performing a weighted summation on the m first information entropies. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0195] The second information entropy is defined as the information entropy.

[0196] Step 760: From at least two types of merchant operating data, select key merchant operating data whose uncertain scores meet the first score condition;

[0197] For each of the at least two types of merchant operating data, the smaller the uncertainty score corresponding to the current type of merchant operating data, the more certain the other types of merchant operating data are after the current type of merchant operating data is given, and thus the given current type of merchant operating data is more critical.

[0198] In one embodiment, key merchant operating data with an uncertainty score less than a first score threshold is selected from at least two types of merchant operating data. For example, key merchant operating data with an uncertainty score less than 0.1 is selected from at least two types of merchant operating data. Optionally, if the number of categories with an uncertainty score greater than 0.1 is greater than a first preset number, the merchant operating data category with the smallest uncertainty score is selected to avoid selecting too many key merchant operating data categories.

[0199] At this point, the above embodiment will determine the key merchant operating data by using the first score threshold. The operation is simple and easy to implement, and it can effectively determine the key merchant operating data.

[0200] In another embodiment, from at least two types of merchant operating data, key merchant operating data that rank among the top p in terms of uncertain scores when sorted from smallest to largest, where p is a positive integer, are selected. For example, the uncertain scores corresponding to the at least two types of merchant operating data are sorted in ascending order, and the top three merchant operating data are identified as key merchant operating data. Optionally, after selecting the top p smallest key merchant operating data, further selection is made for key merchant operating data with uncertain scores less than a first preset score, to avoid the uncertainty scores corresponding to the top p smallest merchant operating data still being too large, thus identifying false key merchant operating data.

[0201] At this point, the above embodiment will determine the key merchant operating data through card ranking, which is simple to operate, easy to implement, and can effectively determine the key merchant operating data.

[0202] Step 780: Analyze the operating data of key merchant categories.

[0203] In one embodiment, the relationship between key merchant operating data and target merchant operating metrics is analyzed to obtain the analysis results of the key merchant operating data. For example, merchant operating metrics include net profit, which is a key merchant operating metric. Assuming the identified key merchant operating data is customer data, meaning customer data is the most important among at least two types of merchant operating data, the relationship between customer data and net profit is analyzed to obtain the analysis results. For example, if the main customer age group in the first quarter is 10-20 years old, and the main customer age group in the second quarter is 15-25 years old, and the net profit in the first quarter is less than that in the second quarter, the analysis results indicate that the 15-25 year old age group is the merchant's primary target audience. Optionally, the analysis results can be presented through statistical analysis, visualization charts, etc.

[0204] In one embodiment, after analyzing the operating data of key merchant categories, improvement suggestions for merchant operations are generated based on the analysis results. The analysis results and improvement suggestions are then output as a merchant operation report. Optionally, the merchant operation report includes text descriptions, charts, data analysis, and other content.

[0205] For example, based on the analysis of customer data, the improvement suggestions generated for merchants' business operations could be to target the 15-25 age group as the target audience for their products.

[0206] In summary, the embodiments of this application provide a data analysis method for merchant business operations. This method calculates an uncertain score for each type of merchant business data in at least two categories. The analysis result of the key category of merchant business data, whose uncertain scores satisfy a first score condition, is taken as the final analysis result. In this case, the key category of merchant business data is the more critical merchant business data among the at least two categories. This key category of merchant business data can more accurately represent the merchant's business situation, thereby providing merchants with more accurate decision support and enabling them to make more accurate decisions.

[0207] Figure 8 A flowchart illustrating an exemplary embodiment of this application of a method for analyzing merchant operating data is shown, exemplified by the method being executed by a computer device. The method includes:

[0208] Step 810: Obtain at least two types of merchant operation data from the target merchant;

[0209] For details regarding step 810, please refer to step 720 above.

[0210] Step 820: For the first type of merchant operating data in at least two types of merchant operating data, calculate the degree of uncertainty of the second type of merchant operating data given the first type of merchant operating data, and obtain the uncertainty score corresponding to the first type of merchant operating data;

[0211] Among them, the first type of merchant operating data is any one of the at least two types of merchant operating data, and the second type of merchant operating data is other types of merchant operating data besides the first type of merchant operating data.

[0212] For details regarding step 820, please refer to step 740 above.

[0213] Step 830: Calculate the contribution score of each type of merchant operating data to the merchant operating strategy in at least two types of merchant operating data;

[0214] Optional business strategies for merchants include raising product prices, launching new products, hiring more employees, and expanding supply channels.

[0215] In one embodiment, the merchant operation strategy includes multiple merchant operation strategies. The contribution score of each type of merchant operation data in at least two types of merchant operation data to each merchant operation strategy is calculated to obtain the contribution score corresponding to each type of merchant operation strategy.

[0216] For example, the merchant operation strategy includes Merchant Operation Strategy 1 and Merchant Operation Strategy 2. The contribution score of each type of merchant operation data to Merchant Operation Strategy 1 is calculated to obtain Contribution Score 1; and the contribution score of each type of merchant operation data to Merchant Operation Strategy 2 is calculated to obtain Contribution Score 2; based on the average of Contribution Score 1 and Contribution Score 2, the corresponding contribution score for each type of merchant operation data is calculated.

[0217] In one embodiment, a business strategy model is pre-established. The business strategy model includes at least two model parameters, which correspond one-to-one with at least two types of merchant operating data. The business strategy model is used to output the execution probability of the merchant operating strategy based on at least two types of merchant operating data.

[0218] Based on the product of at least two types of merchant operating data and at least two model parameters according to their corresponding relationships, the contribution score of each type of merchant operating data to the merchant operating strategy is obtained.

[0219] In the above embodiments, by calculating the contribution score of each type of merchant operating data to the merchant operating strategy, the absolute criticality of each type of merchant operating data can be obtained, and thus more accurate key merchant operating data can be determined below.

[0220] Step 840: Perform a weighted summation of the contribution score and uncertain score of the business data for each type of merchant to obtain the criticality score of the business data for each type of merchant;

[0221] In the above text, the contribution score and uncertain score of each type of merchant's operating data have been calculated. By performing a weighted summation on the contribution score and uncertain score of each type of merchant's operating data, the criticality score of each type of merchant's operating data can be obtained.

[0222] Step 850: From at least two types of merchant operating data, select key merchant operating data whose key scores meet the second score condition;

[0223] For each type of merchant operating data in at least two categories, the higher the criticality score corresponding to the current category of merchant operating data, the more critical the current category of merchant operating data is. In other words, the analysis results of the current category of merchant operating data are more representative of the analysis results of all categories of merchant operating data, and the more accurate the overall analysis results are obtained.

[0224] In one embodiment, from at least two types of merchant operating data, key merchant operating data with a key score greater than a second score threshold are selected; for example, from at least two types of merchant operating data, key merchant operating data with a key score greater than 0.8 are selected. Optionally, if the number of categories with a key score greater than 0.8 is greater than a second preset number, then the merchant operating data category with the highest key score is selected.

[0225] At this point, the above embodiment will determine the key merchant operating data by using the second score threshold. The operation is simple and easy to implement, and it can effectively determine the key merchant operating data.

[0226] In another embodiment, from at least two types of merchant operating data, the key category of merchant operating data, ranked in the top q positions when sorted from largest to smallest, is selected, where q is a positive integer. For example, the key scores corresponding to the at least two types of merchant operating data are sorted in descending order, and the top three merchant operating data are identified as key category merchant operating data. Optionally, after selecting the top q key category merchant operating data, further selection is made for key category merchant operating data with key scores greater than a second preset score, to avoid identifying false key category merchant operating data where the key scores corresponding to the top q merchant operating data are still too small.

[0227] At this point, the above embodiment will determine the key merchant operating data through card ranking, which is simple to operate, easy to implement, and can effectively determine the key merchant operating data.

[0228] Step 860: Analyze the operating data of key merchant categories.

[0229] For details regarding step 860, please refer to step 780 above.

[0230] In summary, the above embodiments combine the uncertainty score and contribution score of each type of merchant operating data to determine the criticality score of each type of merchant operating data. This assessment evaluates the criticality of each type of merchant operating data not only from the perspective of its relative criticality compared to other types of merchant operating data, but also from the perspective of its absolute criticality within each type of merchant operating data itself. Therefore, a more accurate criticality score can be generated for each type of merchant operating data, thereby enabling a more precise identification of key merchant operating data categories.

[0231] The following section will introduce how the above-mentioned business data analysis methods are applied to teaching operations.

[0232] Figure 9 A flowchart illustrating an exemplary embodiment of the present application provides a method for analyzing teaching data, exemplified by the method being performed by a computer device. The method includes:

[0233] Step 920: Obtain at least two types of teaching data for the teaching business;

[0234] The teaching business corresponds to at least two types of teaching data, which include different categories of teaching data. Optionally, teaching data includes learning duration, learning method, and number of students. Learning duration includes the amount of time each student spends learning daily / weekly / monthly / quarterly. Learning method includes the learning method used by each student, such as in-person classes at school, online classes, group tutoring, one-on-one tutoring, etc. Number of students includes the number of students in each class / grade / total number of students.

[0235] Step 940: For the first type of teaching data in at least two types of teaching data, calculate the uncertainty of the second type of teaching data given the first type of teaching data, and obtain the uncertainty score corresponding to the first type of teaching data;

[0236] The first type of teaching data is any one of at least two types of teaching data, and the second type of teaching data is any other type of teaching data besides the first type.

[0237] In this embodiment, for each of at least two types of teaching data, the uncertainty of other types of teaching data is calculated given the current type of teaching data, resulting in an uncertainty score corresponding to the current type of teaching data. The uncertainty score measures the uncertainty of other types of teaching data given a certain type of teaching data. Optionally, the uncertainty can be measured by calculating information entropy. Information entropy is a common concept in information theory, used to describe the uncertainty of possible events occurring from an information source.

[0238] In one embodiment, the second type of teaching data corresponds to at least two values.

[0239] Given the first type of teaching data, obtain the probability of at least two values ​​corresponding to the second type of teaching data, and obtain the probability of at least two values.

[0240] Information entropy is calculated based on at least two possible values. Information entropy is used to measure the degree of uncertainty of the second type of teaching data given the first type of teaching data.

[0241] Based on information entropy, the uncertain scores corresponding to the first type of teaching data are obtained.

[0242] In another embodiment, the first type of teaching data corresponds to m first values, and the second type of teaching data corresponds to n second values, where m and n are integers greater than one.

[0243] Given that the first value is obtained from the first type of teaching data, the probability of the second type of teaching data obtaining each second value is obtained, resulting in m*n probability values.

[0244] Based on m*n probability values, m first information entropies are calculated. Each of the m first information entropies is calculated based on the n probability values ​​corresponding to a first value.

[0245] The second information entropy is obtained by performing a weighted summation on the m first information entropies. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0246] The second information entropy is defined as the information entropy.

[0247] Step 960: From at least two types of teaching data, select the key type of teaching data whose uncertain scores meet the first score condition;

[0248] For each of the at least two classes of teaching data, the smaller the uncertain score corresponding to the current class of teaching data, the more certain the other classes of teaching data are after the current class of teaching data is given, and thus the given current class of teaching data is more critical.

[0249] In one embodiment, key teaching data with uncertain scores less than a first score threshold are selected from at least two types of teaching data; for example, key teaching data with uncertain scores less than 0.1 are selected from at least two types of teaching data. Optionally, if the number of categories with uncertain scores greater than 0.1 is greater than a first preset number, the teaching data category with the smallest uncertain score is selected.

[0250] At this point, the above embodiment will determine the key class of teaching data by using the first score threshold. The operation is simple and easy to implement, and it can effectively determine the key class of teaching data.

[0251] In another embodiment, from at least two types of teaching data, key teaching data that rank among the top p in terms of uncertain scores when sorted from smallest to largest, where p is a positive integer, are selected. For example, the uncertain scores corresponding to at least two types of teaching data are sorted in ascending order, and the top three teaching data are identified as key teaching data. Optionally, after selecting the top p smallest key teaching data, further selection is made for key teaching data whose uncertain scores are less than a first preset score, to avoid the uncertain scores corresponding to the top p smallest teaching data still being too large, thus identifying false key teaching data.

[0252] At this point, the above embodiment will determine the key teaching data by card ranking, which is simple to operate, easy to implement, and can effectively determine the key teaching data.

[0253] Step 980: Analyze key teaching data.

[0254] In one embodiment, the relationship between key teaching data and teaching indicators of teaching operations is analyzed to obtain the analysis results of the key teaching data. For example, teaching indicators include student grades, which is a business indicator. Assuming that the identified key teaching data is learning mode, meaning that learning mode is the most important teaching data among at least two types of teaching data, the relationship between learning mode and student grades is analyzed to obtain the analysis results. For example, students who only learn through in-person classes at school have higher grades.

[0255] In one embodiment, after analyzing key-category teaching data, suggestions for improving teaching practices are generated based on the analysis results. The analysis results and improvement suggestions are then output as a teaching report. Optionally, the teaching report includes text descriptions, charts, data analysis, and other content.

[0256] For example, regarding teaching practices, based on the analysis of learning methods, the resulting improvement suggestions are to guide students to learn only through in-person classroom learning at school as much as possible, and to provide students with a moderately relaxed academic workload.

[0257] In summary, the above embodiments provide a data analysis method for teaching operations, which calculates the uncertain score corresponding to each of at least two types of teaching data, and takes the analysis result of the key type of teaching data whose uncertain score meets the first score condition as the final analysis result. At this time, the key type of teaching data is the more critical teaching data among at least two types of teaching data. Assuming that the key type of teaching data is the learning method, the school or relevant education department can make more accurate teaching decisions.

[0258] Figure 10 A flowchart illustrating an exemplary embodiment of the present application provides a method for analyzing teaching data, exemplified by the method being performed by a computer device. The method includes:

[0259] Step 1010: Obtain at least two types of teaching data for teaching operations;

[0260] For details regarding step 1010, please refer to step 920 above.

[0261] Step 1020: For the first type of teaching data in at least two types of teaching data, calculate the uncertainty of the second type of teaching data given the first type of teaching data, and obtain the uncertainty score corresponding to the first type of teaching data;

[0262] The first type of teaching data is any one of at least two types of teaching data, and the second type of teaching data is any other type of teaching data besides the first type.

[0263] For details regarding step 1020, please refer to step 940 above.

[0264] Step 1030: Calculate the contribution score of each type of teaching data to the teaching strategy in at least two types of teaching data;

[0265] Optional teaching strategies include increasing student enrollment, hiring more teachers, adding new subjects, and expanding teaching facilities.

[0266] In one embodiment, the teaching strategy includes multiple teaching strategies, and the contribution score of each type of teaching data in at least two types of teaching data to each teaching strategy is calculated to obtain the contribution score corresponding to each type of teaching strategy.

[0267] For example, the teaching strategies include teaching strategy 1 and teaching strategy 2. The contribution score of each type of teaching data to teaching strategy 1 is calculated to obtain contribution score 1; and the contribution score of each type of teaching data to teaching strategy 2 is calculated to obtain contribution score 2; based on the average of contribution score 1 and contribution score 2, the contribution score corresponding to each type of teaching data is calculated.

[0268] In one embodiment, a business strategy model is pre-established, which includes at least two model parameters. Each of the at least two model parameters corresponds one-to-one with at least two types of teaching data. The business strategy model is used to output the execution probability of the teaching strategy based on the at least two types of teaching data.

[0269] Based on the product of at least two types of teaching data and at least two model parameters according to their corresponding relationships, the contribution score of each type of teaching data to the teaching strategy is obtained.

[0270] In the above embodiments, by calculating the contribution score of each type of teaching data to the teaching strategy, the absolute criticality of each type of teaching data can be obtained, and thus more accurate key types of teaching data can be determined below.

[0271] Step 1040: Perform a weighted summation of the contribution score and uncertain score for each type of teaching data to obtain the criticality score for each type of teaching data;

[0272] In the above text, the contribution score and uncertainty score for each type of teaching data have been calculated. By performing a weighted summation on the contribution score and uncertainty score for each type of teaching data, the criticality score for each type of teaching data can be obtained.

[0273] Step 1050: From at least two types of teaching data, select key teaching data whose key scores meet the second score condition;

[0274] For each of the at least two classes of teaching data, the higher the critical score corresponding to the current class of teaching data, the more critical the current class of teaching data is. In other words, the analysis results of the current class of teaching data are more representative of the analysis results of all classes of teaching data. In this case, the overall analysis results obtained are more focused and more accurate.

[0275] In one embodiment, key teaching data with a key score greater than a second score threshold are selected from at least two types of teaching data; for example, key teaching data with a key score greater than 0.8 are selected from at least two types of teaching data. Optionally, if the number of categories with a key score greater than 0.8 is greater than a second preset number, the teaching data category with the largest key score is selected.

[0276] At this point, the above embodiment will determine the key class teaching data by using the second score threshold. The operation is simple and easy to implement, and it can effectively determine the key class teaching data.

[0277] In another embodiment, from at least two types of teaching data, key teaching data in the category that rank among the top q when sorted in descending order of key scores, where q is a positive integer, are selected. For example, the key scores corresponding to at least two types of teaching data are sorted in descending order, and the top three teaching data are identified as key teaching data. Optionally, after selecting the top q key teaching data, further selection is made for key teaching data in the category whose key scores are greater than a second preset score, to avoid identifying false key teaching data where the key scores corresponding to the top q teaching data are still too small.

[0278] At this point, the above embodiment will determine the key teaching data by card ranking, which is simple to operate, easy to implement, and can effectively determine the key teaching data.

[0279] Step 1060: Analyze the key category of teaching data.

[0280] For details regarding step 1060, please refer to step 980 above.

[0281] In summary, the above embodiments combine the uncertain score and contribution score of each type of teaching data to determine the criticality score of each type of teaching data. This not only assesses the criticality of each type of teaching data from the perspective of its relative criticality to other types of teaching data, but also assesses the criticality of each type of teaching data from the perspective of its absolute criticality. Therefore, it can ultimately generate a more accurate criticality score for each type of teaching data, thereby more accurately identifying the key types of teaching data.

[0282] The following section will introduce how the above-mentioned business data analysis methods are applied to the delivery business.

[0283] Figure 11 A flowchart illustrating an exemplary embodiment of the present application provides a method for analyzing delivery data, exemplified by the method being performed by a computer device. The method includes:

[0284] Step 1120: Obtain at least two types of delivery data for the delivery business;

[0285] The delivery business involves at least two types of delivery data, which include different categories of delivery data. Optionally, delivery data includes delivery duration, delivery order, and delivery area. Delivery duration includes the total delivery time per rider per day / week / month / quarter; delivery order includes the number of deliveries per rider per day / week / month / quarter; and delivery area includes the coverage area covered by each rider per day / week / month / quarter. For example, rider A delivered orders within 5 kilometers on one day and orders within 10 kilometers on another day, etc.

[0286] Step 1140: For the first type of delivery data in at least two types of delivery data, calculate the uncertainty of the second type of delivery data given the first type of delivery data, and obtain the uncertainty score corresponding to the first type of delivery data;

[0287] The first type of delivery data is any one of at least two types of delivery data, and the second type of delivery data is any other type of delivery data besides the first type.

[0288] In this embodiment, for each of at least two types of delivery data, the uncertainty of other types of delivery data is calculated given the current type of delivery data, resulting in an uncertainty score corresponding to the current type of delivery data. The uncertainty score measures the uncertainty of other types of delivery data given a certain type of delivery data. Optionally, the uncertainty can be measured by calculating information entropy. Information entropy is a common concept in information theory, used to describe the uncertainty of possible events occurring from an information source.

[0289] In one embodiment, the second type of delivery data corresponds to at least two values.

[0290] Given the first type of delivery data, obtain the probability of at least two values ​​corresponding to the second type of delivery data, and obtain the probability of at least two values.

[0291] Information entropy is calculated based on at least two possible probabilities. Information entropy is used to measure the degree of uncertainty of the second type of delivery data given the first type of delivery data.

[0292] Based on information entropy, the uncertain score corresponding to the first type of delivery data is obtained.

[0293] In another embodiment, the first type of delivery data corresponds to m first values, and the second type of delivery data corresponds to n second values, where m and n are integers greater than one.

[0294] Given that the first value is obtained from the first type of delivery data, the probability of the second type of delivery data obtaining each second value is obtained, resulting in m*n probability values.

[0295] Based on m*n probability values, m first information entropies are calculated. Each of the m first information entropies is calculated based on the n probability values ​​corresponding to a first value.

[0296] The second information entropy is obtained by performing a weighted summation on the m first information entropies. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0297] The second information entropy is defined as the information entropy.

[0298] Step 1160: From at least two types of delivery data, select key type delivery data whose uncertain scores meet the first score condition;

[0299] For each of the at least two types of delivery data, the smaller the uncertainty score corresponding to the current type of delivery data, the more certain the other types of delivery data are after the current type of delivery data is given, and thus the given current type of delivery data is more critical.

[0300] In one embodiment, key delivery data with an uncertainty score less than a first score threshold is selected from at least two types of delivery data; for example, key delivery data with an uncertainty score less than 0.1 is selected from at least two types of delivery data. Optionally, if the number of categories with an uncertainty score greater than 0.1 is greater than a first preset number, the delivery data category with the smallest uncertainty score is selected.

[0301] At this point, the above embodiment will determine the key category of delivery data by using the first score threshold of the card. The operation is simple and easy to implement, and it can effectively determine the key category of delivery data.

[0302] In another embodiment, from at least two types of delivery data, key delivery data that rank among the top p in terms of uncertain scores when sorted from smallest to largest, where p is a positive integer, are selected. For example, the uncertain scores corresponding to at least two types of delivery data are sorted in ascending order, and the top three delivery data are identified as key delivery data. Optionally, after selecting the top p smallest key delivery data, further selection is made for key delivery data with uncertain scores less than a first preset score to avoid identifying false key delivery data where the uncertain scores corresponding to the top p smallest delivery data are still too large.

[0303] At this point, the above embodiment will determine the key category of delivery data by card ranking, which is simple to operate, easy to implement, and can effectively determine the key category of delivery data.

[0304] Step 1180: Analyze key category delivery data.

[0305] In one embodiment, the relationship between key delivery data and delivery metrics of the delivery business is analyzed to obtain the analysis results of the key delivery data. For example, delivery metrics include on-time delivery rate, which is a delivery metric. Assuming that the identified key delivery data is delivery range, meaning that the delivery range is the most important delivery data among at least two categories of delivery data, the relationship between delivery range and on-time delivery rate is analyzed to obtain the analysis results. For example, the analysis results show that the on-time delivery rate for a rider's furthest delivery range of 10km is greater than the on-time delivery rates for riders' furthest delivery ranges of 8km and 20km.

[0306] In one embodiment, after analyzing key category delivery data, improvement suggestions for delivery operations are generated based on the analysis results; the analysis results and improvement suggestions are then output as a delivery report. Optionally, the delivery report includes text descriptions, charts, data analysis, and other content.

[0307] For example, for delivery services, based on the analysis of delivery range, the improvement suggestion generated is to set the rider's maximum delivery range to 10km to ensure on-time delivery rate.

[0308] In summary, the above embodiments provide a data analysis method for delivery operations. This method calculates the uncertain score for each of at least two types of delivery data, and uses the analysis results of key delivery data whose uncertain scores satisfy a first score condition as the final analysis result. Here, key delivery data refers to the more critical delivery data among the at least two types of delivery data. Assuming the key delivery data represents the delivery range, the delivery platform can then determine a more accurate maximum delivery range for riders, thereby improving on-time delivery rates.

[0309] Figure 12 A flowchart illustrating an exemplary embodiment of the present application provides a method for analyzing delivery data, exemplified by the method being performed by a computer device. The method includes:

[0310] Step 1210: Obtain at least two types of delivery data for the delivery business;

[0311] For details regarding step 1210, please refer to step 1120 above.

[0312] Step 1220: For the first type of delivery data in at least two types of delivery data, calculate the uncertainty of the second type of delivery data given the first type of delivery data, and obtain the uncertainty score corresponding to the first type of delivery data;

[0313] The first type of delivery data is any one of at least two types of delivery data, and the second type of delivery data is any other type of delivery data besides the first type.

[0314] For details regarding step 1220, please refer to step 1140 above.

[0315] Step 1230: Calculate the contribution score of each type of delivery data to the delivery strategy in at least two types of delivery data;

[0316] Optional delivery strategies include recruiting more riders and upgrading rider equipment.

[0317] In one embodiment, the delivery strategy includes multiple delivery strategies, and the contribution score of each type of delivery data in at least two types of delivery data to each delivery strategy is calculated to obtain the contribution score corresponding to each type of delivery strategy.

[0318] For example, the delivery strategy includes delivery strategy 1 and delivery strategy 2. The contribution score of each type of delivery data to delivery strategy 1 is calculated to obtain contribution score 1; and the contribution score of each type of delivery data to delivery strategy 2 is calculated to obtain contribution score 2; based on the average of contribution score 1 and contribution score 2, the contribution score corresponding to each type of delivery data is calculated.

[0319] In one embodiment, a business strategy model is pre-established, which includes at least two model parameters, each corresponding to at least two types of delivery data. The business strategy model is used to output the execution probability of the delivery strategy based on the at least two types of delivery data.

[0320] Based on the product of at least two types of delivery data and at least two model parameters according to their corresponding relationships, the contribution score of each type of delivery data to the delivery strategy is obtained.

[0321] In the above embodiments, by calculating the contribution score of each type of delivery data to the delivery strategy, the absolute criticality of each type of delivery data can be obtained, and thus more accurate key delivery data can be determined below.

[0322] Step 1240: Perform a weighted summation of the contribution score and uncertainty score for each type of delivery data to obtain the criticality score for each type of delivery data;

[0323] In the above text, the contribution score and uncertainty score of each type of delivery data have been calculated. By performing a weighted summation on the contribution score and uncertainty score of each type of delivery data, the criticality score of each type of delivery data can be obtained.

[0324] Step 1250: From at least two types of delivery data, select the key category of delivery data whose key scores meet the second score condition;

[0325] For each of the at least two categories of delivery data, the higher the criticality score of the current category of delivery data, the more critical the current category of delivery data is. In other words, the analysis results of the current category of delivery data are more representative of the analysis results of all categories of delivery data. In this case, the overall analysis results obtained are more focused and more accurate.

[0326] In one embodiment, key delivery data with a critical score greater than a second score threshold is selected from at least two types of delivery data; for example, key delivery data with a critical score greater than 0.8 is selected from at least two types of delivery data. Optionally, if the number of categories with a critical score greater than 0.8 is greater than a second preset number, the delivery data category with the highest critical score is selected.

[0327] At this point, the above embodiment will determine the key category delivery data by using the second score threshold of the card. The operation is simple and easy to implement, and it can effectively determine the key category delivery data.

[0328] In another embodiment, from at least two types of delivery data, key delivery data that rank among the top q in terms of criticality score when sorted from largest to smallest, where q is a positive integer, are selected. For example, the criticality scores corresponding to at least two types of delivery data are sorted from largest to smallest, and the top three delivery data are identified as key delivery data. Optionally, after selecting the top q key delivery data, further selection is made for key delivery data with criticality scores greater than a second preset score to avoid identifying false key delivery data where the criticality scores of the top q delivery data are still too small.

[0329] At this point, the above embodiment will determine the key category of delivery data by card ranking, which is simple to operate, easy to implement, and can effectively determine the key category of delivery data.

[0330] Step 1260: Analyze key category delivery data.

[0331] For details regarding step 1260, please refer to step 1180 above.

[0332] In summary, the above embodiments combine the uncertainty score and contribution score of each type of delivery data to determine the criticality score of each type of delivery data. This not only assesses the criticality of each type of delivery data from the perspective of its relative criticality compared to other types of delivery data, but also from the perspective of the absolute criticality of each type of delivery data itself. Therefore, a more accurate criticality score can be generated for each type of delivery data, thereby enabling a more accurate identification of critical delivery data categories.

[0333] The following section will introduce how the aforementioned business data analysis methods are applied to the tourism business.

[0334] Figure 13 A flowchart illustrating an exemplary embodiment of the present application of a method for analyzing tourism data is shown, exemplified by the method being performed by a computer device. The method includes:

[0335] Step 1320: Obtain at least two types of tourism data for the tourism business;

[0336] The tourism business involves at least two types of tourism data, each encompassing different categories of tourism data. Optionally, tourism data may include tourist arrivals, travel dates, and tourist destinations. Tourist arrivals include the daily number of visitors received by each tourist destination; travel dates include the opening and / or closed dates of each tourist destination; and tourist destinations include the IDs of the tourist destinations included in the analysis.

[0337] Step 1340: For the first type of tourism data in at least two types of tourism data, calculate the degree of uncertainty of the second type of tourism data given the first type of tourism data, and obtain the uncertainty score corresponding to the first type of tourism data;

[0338] The first category of tourism data includes any one of the at least two categories of tourism data, while the second category includes other types of tourism data besides the first category.

[0339] In this embodiment, for each of at least two types of tourism data, the uncertainty of other types of tourism data is calculated given the current type of tourism data, resulting in an uncertainty score corresponding to the current type of tourism data. The uncertainty score measures the uncertainty of other types of tourism data given a certain type of tourism data. Optionally, the uncertainty can be measured by calculating information entropy. Information entropy is a common concept in information theory, used to describe the uncertainty of possible events occurring from an information source.

[0340] In one embodiment, the second type of tourism data corresponds to at least two values.

[0341] Given the first type of tourism data, obtain the probability of at least two values ​​corresponding to the second type of tourism data, and obtain the probability of at least two values.

[0342] Information entropy is calculated based on at least two possible probabilities. Information entropy is used to measure the degree of uncertainty of second-type tourism data given first-type tourism data.

[0343] Based on information entropy, the uncertain scores corresponding to the first type of tourism data are obtained.

[0344] In another embodiment, the first type of tourism data corresponds to m first values, and the second type of tourism data corresponds to n second values, where m and n are integers greater than one.

[0345] Given that the first type of tourism data has each first value, the probability of the second type of tourism data having each second value is obtained, resulting in m*n probability values.

[0346] Based on m*n probability values, m first information entropies are calculated. Each of the m first information entropies is calculated based on the n probability values ​​corresponding to a first value.

[0347] The second information entropy is obtained by performing a weighted summation on the m first information entropies. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0348] The second information entropy is defined as the information entropy.

[0349] Step 1360: From at least two types of tourism data, select key types of tourism data whose uncertain scores meet the first score condition;

[0350] For each of the at least two types of tourism data, the smaller the uncertainty score corresponding to the current type of tourism data, the more certain the other types of tourism data are after the current type of tourism data is given, and thus the given current type of tourism data is more critical.

[0351] In one embodiment, key tourism data with an uncertainty score less than a first score threshold is selected from at least two types of tourism data; for example, key tourism data with an uncertainty score less than 0.1 is selected from at least two types of tourism data. Optionally, if the number of categories with an uncertainty score greater than 0.1 is greater than a first preset number, the tourism data category with the smallest uncertainty score is selected.

[0352] At this point, the above embodiment will determine the key tourism data by using the first score threshold. The operation is simple and easy to implement, and it can effectively determine the key tourism data.

[0353] In another embodiment, from at least two types of tourism data, key tourism data that rank among the top p in terms of uncertain scores when sorted from smallest to largest, where p is a positive integer, are selected. For example, the uncertain scores corresponding to at least two types of tourism data are sorted in ascending order, and the top three tourism data are identified as key tourism data. Optionally, after selecting the top p smallest key tourism data, further selection is made for key tourism data with uncertain scores lower than a first preset score to avoid the uncertainty scores corresponding to the top p smallest tourism data still being too large, thus preventing the identification of false key tourism data.

[0354] At this point, the above embodiment will determine key tourism data by card ranking, which is simple to operate, easy to implement, and can effectively determine key tourism data.

[0355] Step 1380: Analyze key tourism data.

[0356] In one embodiment, the relationship between key tourism data and tourism indicators of the tourism business is analyzed to obtain the analysis results of the key tourism data. For example, tourism indicators include tourism spending figures, which refer to the total amount of consumption generated by the tourism business. Assuming that the identified key tourism data is tourist arrivals, meaning that tourist arrivals are the most important tourism data among at least two types of tourism data, the relationship between tourist arrivals and tourism spending figures is analyzed to obtain the analysis results. For example, the tourism spending figure when tourist arrivals are 10 million is greater than the tourism spending figures when tourist arrivals are 8 million and 15 million.

[0357] In one embodiment, after analyzing key tourism data, suggestions for improving tourism operations are generated based on the analysis results; the analysis results and improvement suggestions are then output as a tourism report. Optionally, the tourism report includes text descriptions, charts, data analysis, and other content.

[0358] For example, in the tourism business, based on the analysis of tourist numbers, the improvement suggestions generated are to increase tourism promotion, encourage more people to leave their homes, and boost tourism consumption.

[0359] In summary, the above embodiments provide a data analysis method for tourism business, which calculates the uncertain score corresponding to each type of tourism data in at least two types of tourism data, and takes the analysis result of the key type of tourism data whose uncertain score meets the first score condition as the final analysis result. At this time, the key type of tourism data is the more critical tourism data among at least two types of tourism data. Assuming that the key type of tourism data is the number of tourists, relevant departments can make more accurate decisions, such as increasing tourism promotion.

[0360] Figure 14 A flowchart illustrating an exemplary embodiment of the present application of a method for analyzing tourism data is shown, exemplified by the method being performed by a computer device. The method includes:

[0361] Step 1410: Obtain at least two types of tourism data for the tourism business;

[0362] For details regarding step 1410, please refer to step 1320 above.

[0363] Step 1420: For the first type of tourism data in at least two types of tourism data, calculate the degree of uncertainty of the second type of tourism data given the first type of tourism data, and obtain the uncertainty score corresponding to the first type of tourism data;

[0364] The first category of tourism data is any one of at least two categories of tourism data, while the second category of tourism data is any other type of tourism data besides the first category.

[0365] For details regarding step 1420, please refer to step 1340 above.

[0366] Step 1430: Calculate the contribution score of each type of tourism data to the tourism strategy in at least two types of tourism data;

[0367] Optional tourism strategies include adding more attractions, attracting more businesses, and advertising on short video platforms.

[0368] In one embodiment, the tourism strategy includes multiple tourism strategies, and the contribution score of each type of tourism data in at least two types of tourism data to each tourism strategy is calculated to obtain the contribution score corresponding to each type of tourism strategy.

[0369] For example, tourism strategies include tourism strategy 1 and tourism strategy 2. The contribution score of each type of tourism data to tourism strategy 1 is calculated to obtain contribution score 1; and the contribution score of each type of tourism data to tourism strategy 2 is calculated to obtain contribution score 2; based on the average of contribution score 1 and contribution score 2, the contribution score corresponding to each type of tourism data is calculated.

[0370] In one embodiment, a business strategy model is pre-established, which includes at least two model parameters, each corresponding to at least two types of tourism data. The business strategy model is used to output the execution probability of a tourism strategy based on the at least two types of tourism data.

[0371] Based on the product of at least two types of tourism data and at least two model parameters according to their corresponding relationships, the contribution score of each type of tourism data to the tourism strategy is obtained.

[0372] In the above embodiments, by calculating the contribution score of each type of tourism data to the tourism strategy, the absolute criticality of each type of tourism data can be obtained, and thus more accurate key types of tourism data can be identified below.

[0373] Step 1440: Perform a weighted summation of the contribution score and uncertainty score for each type of tourism data to obtain the criticality score for each type of tourism data;

[0374] In the above text, the contribution score and uncertainty score for each type of tourism data have been calculated. By performing a weighted summation on the contribution score and uncertainty score for each type of tourism data, the criticality score for each type of tourism data can be obtained.

[0375] Step 1450: From at least two types of tourism data, select key tourism data whose key scores meet the second score condition;

[0376] For each of the at least two categories of tourism data, the higher the criticality score of the current category of tourism data, the more critical the current category of tourism data is. In other words, the analysis results of the current category of tourism data are more representative of the analysis results of all categories of tourism data. In this case, the overall analysis results obtained are more focused and more accurate.

[0377] In one embodiment, key tourism data with a key score greater than a second score threshold are selected from at least two types of tourism data; for example, key tourism data with a key score greater than 0.8 are selected from at least two types of tourism data. Optionally, if the number of categories with a key score greater than 0.8 is greater than a second preset number, the tourism data category with the largest key score is selected.

[0378] At this point, the above embodiment will determine key tourism data by using the second score threshold. The operation is simple and easy to implement, and it can effectively determine key business data.

[0379] In another embodiment, from at least two types of tourism data, the top q key tourism data categories, where q is a positive integer, are selected based on their key scores when sorted from largest to smallest. For example, the key scores corresponding to the at least two types of tourism data are sorted from largest to smallest, and the top three tourism data categories are identified as key tourism data. Optionally, after selecting the top q key tourism data categories, further selection is made to identify key tourism data categories with key scores greater than a second preset score, to avoid identifying false key tourism data categories when the key scores corresponding to the top q tourism data categories are still too small.

[0380] At this point, the above embodiment will determine key tourism data by card ranking, which is simple to operate, easy to implement, and can effectively determine key tourism data.

[0381] Step 1460: Analyze key tourism data.

[0382] For details regarding step 1460, please refer to step 1380 above.

[0383] In summary, the above embodiments combine the uncertainty score and contribution score of each type of tourism data to determine the criticality score of each type of tourism data. This not only assesses the criticality of each type of tourism data from the perspective of its relative criticality to other types of tourism data, but also assesses the criticality of each type of tourism data from the perspective of its absolute criticality. Therefore, a more accurate criticality score can be generated for each type of tourism data, thereby enabling a more accurate identification of key types of tourism data.

[0384] Figure 15This application shows a structural block diagram of a business data analysis apparatus provided in an exemplary embodiment. The apparatus includes:

[0385] The acquisition module 1501 is used to acquire at least two types of business data for the target business.

[0386] The calculation module 1502 is used to calculate the degree of uncertainty of the second type of business data given the first type of business data in at least two types of business data, and to obtain the uncertainty score corresponding to the first type of business data. The first type of business data is any one of the at least two types of business data, and the second type of business data is other types of business data besides the first type of business data.

[0387] The filtering module 1503 is used to filter out key business data whose uncertain scores meet the first score condition from at least two types of business data;

[0388] Analysis module 1504 is used to analyze key business data.

[0389] In an optional embodiment, the second type of business data corresponds to at least two values. The calculation module 1502 is further configured to obtain the probability of each of the at least two values ​​corresponding to the second type of business data given the first type of business data, thereby obtaining the probability of at least two values.

[0390] Information entropy is calculated based on at least two possible values. Information entropy is used to measure the degree of uncertainty of the second type of business data given the first type of business data.

[0391] Based on information entropy, the uncertain score corresponding to the first type of business data is obtained.

[0392] In an optional embodiment, the first type of business data corresponds to m first values, and the second type of business data corresponds to n second values, where m and n are integers greater than one.

[0393] The acquisition module 1501 is also used to acquire the probability of the second type of business data acquiring each second value when the first type of business data acquires each first value, and to obtain m*n value probabilities.

[0394] The calculation module 1502 is also used to calculate m first information entropies based on m*n value probabilities, where each of the m first information entropies is calculated based on the n value probabilities corresponding to a first value.

[0395] The second information entropy is obtained by performing a weighted summation on the m first information entropies. The weight of each first information entropy in the m first information entropies is the probability of the corresponding first value.

[0396] The second information entropy is defined as the information entropy.

[0397] In an optional embodiment, the filtering module 1503 is further configured to filter out key business data with uncertain scores less than a first score threshold from at least two types of business data.

[0398] or,

[0399] From at least two types of business data, select the key business data that ranks in the top p when sorted from smallest to largest based on uncertain scores, where p is a positive integer.

[0400] In an optional embodiment, the calculation module 1502 is further configured to calculate the contribution score of each type of business data to the business strategy in at least two types of business data.

[0401] A weighted summation is performed on the contribution score and uncertain score of each type of business data to obtain the criticality score of each type of business data;

[0402] The filtering module 1503 is also used to filter out key business data whose key scores meet the second score condition from at least two types of business data.

[0403] In an optional embodiment, the calculation module 1502 is further configured to obtain a business strategy model, the business strategy model including at least two model parameters, the at least two model parameters corresponding one-to-one with at least two types of business data, and the business strategy model being used to output the execution probability of the business strategy based on at least two types of business data.

[0404] Based on the product of at least two types of business data and at least two model parameters according to their corresponding relationships, the contribution score of each type of business data to the business strategy is obtained.

[0405] In an optional embodiment, the filtering module 1503 is further configured to filter out key business data with a key score greater than a second score threshold from at least two types of business data.

[0406] or,

[0407] From at least two types of business data, select the key business data that rank in the top q when sorted from largest to smallest, where q is a positive integer.

[0408] In an optional embodiment, the device further includes an output module 1505. The output module 1505 is also configured to generate improvement suggestions for the target business based on the analysis results of key business data.

[0409] The analysis results and improvement suggestions are output as a business report for the target business.

[0410] In an optional embodiment, the analysis module 1504 is further configured to analyze the relationship between key business data and business indicators of the target business, and obtain the analysis results of the key business data.

[0411] In an optional embodiment, the target business is merchant operation business, and at least two types of business data are different categories of merchant operation data;

[0412] or,

[0413] The target business is teaching business, and at least two types of business data are different categories of teaching data;

[0414] or,

[0415] The target business is delivery, and at least two types of business data are different categories of delivery data;

[0416] or,

[0417] The target business is tourism, and at least two types of business data are different categories of tourism data.

[0418] In summary, in this embodiment of the application, at least two types of business data will be acquired, the uncertainty of other types of business data after each type of business data is given will be calculated, the uncertainty score corresponding to each type of business data will be obtained, and then the key types of business data that meet the first score condition will be screened out and the key types of business data will be analyzed.

[0419] It is understandable that the smaller the uncertainty score corresponding to a certain type of business data, the more certain the other types of business data are after that type of business data is given. Thus, the given type of business data is more critical among at least two types of business data. The analysis results obtained by analyzing the key type of business data can better represent the overall analysis results, and the final output of the overall analysis results is more accurate.

[0420] Figure 16This is a schematic diagram illustrating the structure of a computer device according to an exemplary embodiment. The computer device 1600 includes a Central Processing Unit (CPU) 1601, a system memory 1604 including Random Access Memory (RAM) 1602 and Read-Only Memory (ROM) 1603, and a system bus 1605 connecting the system memory 1604 and the CPU 1601. The computer device 1600 also includes a basic input / output system (I / O system) 1606 to facilitate information transfer between various devices within the computer device, and a mass storage device 1607 for storing an operating system 1613, application programs 1614, and other program modules 1615.

[0421] The basic input / output system 1606 includes a display 1608 for displaying information and an input device 1609 for user input, such as a mouse or keyboard. Both the display 1608 and the input device 1609 are connected to the central processing unit 1601 via an input / output controller 1610 connected to the system bus 1605. The basic input / output system 1606 may also include the input / output controller 1610 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1610 also provides output to a display screen, printer, or other types of output devices.

[0422] The mass storage device 1607 is connected to the central processing unit 1601 via a mass storage controller (not shown) connected to the system bus 1605. The mass storage device 1607 and its associated computer device-readable media provide non-volatile storage for the computer device 1600. That is, the mass storage device 1607 may include computer device-readable media (not shown), such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0423] Without loss of generality, the computer device readable medium may include computer device storage media and communication media. Computer device storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer device readable instructions, data structures, program modules, or other data. Computer device storage media include RAM, ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM, digital video disc (DVD) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Of course, those skilled in the art will recognize that the computer device storage media are not limited to the above-mentioned types. The system memory 1604 and mass storage device 1607 described above can be collectively referred to as memory.

[0424] According to various embodiments of this disclosure, the computer device 1600 can also be connected to a remote computer device on a network, such as the Internet. That is, the computer device 1600 can be connected to the network 1611 via a network interface unit 1612 connected to the system bus 1605, or it can use the network interface unit 1612 to connect to other types of networks or remote computer device systems (not shown).

[0425] The memory also includes one or more programs stored in the memory, and the central processing unit 1601 executes the one or more programs to implement all or part of the steps of the above-mentioned analysis method applied to business data.

[0426] Figure 17 A structural block diagram of a computer device 1700 provided in an exemplary embodiment of this application is shown. The computer device 1700 may be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The computer device 1700 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0427] Typically, computer device 1700 includes a processor 1701 and a memory 1702.

[0428] Processor 1701 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1701 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1701 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1701 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 1701 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0429] The memory 1702 may include one or more computer-readable storage media, which may be non-transitory. The memory 1702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1702 is used to store at least one instruction, which is executed by the processor 1701 to implement the business data analysis method provided in the method embodiments of this application.

[0430] In some embodiments, the computer device 1700 may also optionally include a peripheral device interface 1703 and at least one peripheral device. The processor 1701, memory 1702, and peripheral device interface 1703 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1703 via a bus, signal line, or circuit board. For example, the peripheral device may include at least one of the following: a radio frequency circuit 1704, a display screen 1705, a camera assembly 1706, an audio circuit 1707, and a power supply 1708.

[0431] Peripheral interface 1703 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1701 and memory 1702. In some embodiments, processor 1701, memory 1702 and peripheral interface 1703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1701, memory 1702 and peripheral interface 1703 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0432] The radio frequency (RF) circuit 1704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1704 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1704 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1704 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1704 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0433] Display screen 1705 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1705 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1701 for processing. In this case, display screen 1705 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1705, disposed on the front panel of computer device 1700; in other embodiments, there may be at least two display screens, disposed on different surfaces of computer device 1700 or in a folded design; in still other embodiments, display screen 1705 may be a flexible display screen, disposed on a curved or folded surface of computer device 1700. Furthermore, display screen 1705 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1705 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0434] The camera assembly 1706 is used to acquire images or videos. Optionally, the camera assembly 1706 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1706 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0435] The audio circuit 1707 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 1701 for processing, or to the radio frequency circuit 1704 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, positioned at different locations within the computer device 1700. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1701 or the radio frequency circuit 1704 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1707 may also include a headphone jack.

[0436] Power supply 1708 is used to supply power to the various components in computer device 1700. Power supply 1708 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1708 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0437] In some embodiments, the computer device 1700 further includes one or more sensors 1709. The one or more sensors 1709 include, but are not limited to, an accelerometer 1710, a gyroscope 1711, a pressure sensor 1712, an optical sensor 1713, and a proximity sensor 1714.

[0438] Accelerometer 1710 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by computer device 1700. For example, accelerometer 1710 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1701 can control display screen 1705 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1710. Accelerometer 1710 can also be used for games or for acquiring user motion data.

[0439] The gyroscope sensor 1711 can detect the orientation and rotation angle of the computer device 1700. The gyroscope sensor 1711 can work in conjunction with the accelerometer sensor 1710 to acquire 3D motion data from the user on the computer device 1700. Based on the data acquired by the gyroscope sensor 1711, the processor 1701 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0440] Pressure sensor 1712 can be disposed on the side bezel of computer device 1700 and / or on the lower layer of display screen 1705. When pressure sensor 1712 is disposed on the side bezel of computer device 1700, it can detect the user's grip signal on computer device 1700, and processor 1701 can perform left / right hand recognition or quick operation based on the grip signal collected by pressure sensor 1712. When pressure sensor 1712 is disposed on the lower layer of display screen 1705, processor 1701 can control operable controls on the UI interface based on the user's pressure operation on display screen 1705. Operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0441] Optical sensor 1713 is used to collect ambient light intensity. In one embodiment, processor 1701 can control the display brightness of display screen 1705 based on the ambient light intensity collected by optical sensor 1713. For example, when the ambient light intensity is high, the display brightness of display screen 1705 is increased; when the ambient light intensity is low, the display brightness of display screen 1705 is decreased. In another embodiment, processor 1701 can also dynamically adjust the shooting parameters of camera assembly 1706 based on the ambient light intensity collected by optical sensor 1713.

[0442] The proximity sensor 1714, also known as a distance sensor, is typically located on the front panel of the computer device 1700. The proximity sensor 1714 is used to detect the distance between the user and the front of the computer device 1700. In one embodiment, when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 is gradually decreasing, the processor 1701 controls the display screen 1705 to switch from a screen-on state to a screen-off state; when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 is gradually increasing, the processor 1701 controls the display screen 1705 to switch from a screen-off state to a screen-on state.

[0443] Those skilled in the art will understand that Figure 17 The structure shown does not constitute a limitation on the computer device 1700, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0444] This application also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the business data analysis method or the merchant operation data analysis method provided in the above method embodiments.

[0445] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the business data analysis method or the merchant operating data analysis method provided in the above-described method embodiments.

[0446] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0447] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0448] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of analyzing business data, characterized by, The method includes: Obtain at least two types of business data for the target business; For the first type of business data in the at least two types of business data, calculate the degree of uncertainty of the second type of business data given the first type of business data, and obtain the uncertainty score corresponding to the first type of business data. The first type of business data is any one of the at least two types of business data, and the second type of business data is other types of business data besides the first type of business data. From the at least two types of business data, select key business data whose uncertain scores meet the first score condition; analyze the key business data.

2. The method of claim 1, wherein, The second type of business data has at least two possible values; The calculation of the uncertainty of the second type of business data given the first type of business data, to obtain the uncertainty score corresponding to the first type of business data, includes: Given the first type of business data, obtain the probability of each of the at least two values ​​under the second type of business data, and obtain at least two probability values. Based on the at least two probability values, the information entropy is calculated, and the information entropy is used to measure the degree of uncertainty of the second type of business data given the first type of business data; Based on the information entropy, the uncertain score corresponding to the first type of business data is obtained.

3. The method according to claim 2, characterized in that, The first type of business data corresponds to m first values, and the second type of business data corresponds to n second values, where m and n are integers greater than one; The step of obtaining the probability of at least two values ​​corresponding to the at least two values ​​under the second type of business data, given the first type of business data, to obtain at least two probability values ​​includes: Given that the first type of business data obtains each first value, the probability of the second type of business data obtaining each second value is obtained, resulting in m*n value probabilities. The calculation of information entropy based on the at least two probability values ​​includes: Based on the m*n value probabilities, m first information entropies are calculated, and each of the m first information entropies is calculated based on the n value probabilities corresponding to a first value; The m first information entropies are weighted and summed to obtain the second information entropy, where the weight of each first information entropy is the probability of the corresponding first value. The second information entropy is determined as the information entropy.

4. The method according to any one of claims 1 to 3, characterized in that, The step of selecting key business data from the at least two types of business data whose uncertain scores satisfy the first score condition includes: From the at least two types of business data, select the key type of business data whose uncertainty score is less than the first score threshold; or, From the at least two types of business data, select the key type of business data whose uncertain scores rank in the top p when sorted from smallest to largest, where p is a positive integer.

5. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Calculate the contribution score of each type of business data to the business strategy in the at least two types of business data; A weighted summation is performed on the contribution score and the uncertainty score of each type of business data to obtain the criticality score of each type of business data; The step of selecting key business data from the at least two types of business data whose uncertain scores satisfy the first score condition includes: From the at least two types of business data, select the key business data whose key scores satisfy the second score condition.

6. The method according to claim 5, characterized in that, The calculation of the contribution score of each type of business data to the business strategy in the at least two types of business data includes: Obtain a business strategy model, which includes at least two model parameters, each of which corresponds one-to-one with at least two types of business data. The business strategy model is used to output the execution probability of the business strategy based on the at least two types of business data. Based on the product of the at least two types of business data and the at least two model parameters according to their corresponding relationships, the contribution score of each type of business data to the business strategy is obtained.

7. The method according to claim 5, characterized in that, The step of selecting key business data from the at least two types of business data whose key scores satisfy the second score condition includes: From the at least two types of business data, select the key type of business data whose key score is greater than the second score threshold; or, From the at least two types of business data, select the top q key business data items when the key scores are sorted from largest to smallest, where q is a positive integer.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Based on the analysis results of the key business data, improvement suggestions are generated for the target business. The analysis results and improvement suggestions are output as a business report for the target business.

9. The method according to any one of claims 1 to 8, characterized in that, The analysis of key business data includes: The relationship between the key business data and the business indicators of the target business is analyzed to obtain the analysis results of the key business data.

10. The method according to any one of claims 1 to 9, characterized in that, The target business is merchant operation business, and the at least two types of business data are different categories of merchant operation data; or, The target business is teaching business, and the at least two types of business data are different categories of teaching data; or, The target business is delivery business, and the at least two types of business data are different categories of delivery data; or, The target business is tourism business, and the at least two types of business data are different categories of tourism data.

11. A method for analyzing merchant operating data, characterized in that, The method includes: Obtain at least two types of merchant operation data from the target merchant; For the first type of merchant operating data in the at least two types of merchant operating data, calculate the degree of uncertainty of the second type of merchant operating data given the first type of merchant operating data, and obtain the uncertainty score corresponding to the first type of merchant operating data. The first type of merchant operating data is any one of the at least two types of merchant operating data, and the second type of merchant operating data is other types of merchant operating data besides the first type of merchant operating data. From the at least two types of merchant operating data, select key merchant operating data whose uncertain scores meet the first score condition; analyze the key merchant operating data.

12. A business data analysis device, characterized in that, The device includes: The acquisition module is used to acquire at least two types of business data for the target business. The calculation module is used to calculate the degree of uncertainty of the second type of business data given the first type of business data in the at least two types of business data, and to obtain the uncertainty score corresponding to the first type of business data. The first type of business data is any one of the at least two types of business data, and the second type of business data is other types of business data besides the first type of business data. The filtering module is used to filter out key business data whose uncertain scores meet the first score condition from the at least two types of business data; The analysis module is used to analyze the key business data.

13. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the business data analysis method as described in any one of claims 1 to 10.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is loaded and executed by a processor to implement the business data analysis method as described in any one of claims 1 to 10.

15. A computer program product, characterized in that, The computer program product stores a computer program that is loaded and executed by a processor to implement the business data analysis method as described in any one of claims 1 to 10.

Images