Data visualization method, apparatus, electronic device, and computer readable medium

Abstract

Embodiments of the present disclosure disclose a data visualization method, device, electronic equipment and computer readable medium. A specific implementation of the method comprises: obtaining influence factor information of a historical time period and transfer information of each group of homogenized items in the historical time period to obtain a set of item transfer information groups; performing data preprocessing on each item transfer information in each item transfer information group in the set of influence factor information and item transfer information groups to obtain influence factor data and a set of transfer data groups; performing quantile regression processing on each transfer data group in the set of influence factor data and transfer data groups to obtain a set of coefficient groups; taking the mean of each corresponding coefficient in the set of coefficient groups to obtain a set of average coefficients; and performing visualization processing on the set of coefficient groups and the set of average coefficients. The implementation can accurately determine the relationship between each factor and the item transfer amount, thereby mining more information to guide business adjustment.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more particularly to data visualization methods, apparatus, electronic devices, and computer-readable media. Background Technology

[0002] Factor analysis is a technique for determining the relationships between variables. Currently, in the field of goods transfer, the common methods for determining the relationship between various other factors and the volume of goods transfer are: using univariate analysis or manual analysis to determine the relationship between various other influencing factors and the volume of goods transfer.

[0003] However, when using the above method, the following technical problems often arise:

[0004] First, univariate analysis does not have the ability to isolate other factors, and is prone to drawing erroneous conclusions.

[0005] Second, manual analysis relies too heavily on human judgment, and people at different transfer locations have different experiences and operate differently, which may lead to cognitive biases and result in biased final analysis results. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide data visualization methods, apparatuses, electronic devices, and computer-readable media to address one or more of the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide a data visualization method, which includes: acquiring influencing factor information and transfer information of each group of homogeneous items within a historical time period, to obtain a set of item transfer information groups, wherein the influencing factor information includes a temperature value sequence, and the item transfer information in the set of item transfer information groups includes: item identification, item original value, and a sub-information sequence, and the sub-information in the sub-information sequence includes an item transfer quantity sequence; performing data preprocessing on the influencing factor information and each item transfer information in each item transfer information group in the set of item transfer information groups to generate influencing factor data and transfer data, to obtain a set of influencing factor data and transfer data groups; performing quantile regression processing on each transfer data group in the influencing factor data and the set of transfer data groups to generate a coefficient group, to obtain a set of coefficient groups; taking the mean of each corresponding coefficient in the set of coefficient groups to obtain an average coefficient set; and performing visualization processing on the set of coefficient groups and the average coefficient set.

[0009] Secondly, some embodiments of this disclosure provide a data visualization apparatus, comprising: an acquisition unit configured to acquire influencing factor information and transfer information of each group of homogeneous items within a historical time period, thereby obtaining a set of item transfer information groups, wherein the influencing factor information includes a temperature value sequence, and the item transfer information in the set of item transfer information groups includes: item identifier, item original value, and a sequence of sub-information, and the sub-information in the sequence of sub-information in the set of item transfer information groups includes a sequence of item transfer volume; a preprocessing unit configured to perform data preprocessing on the influencing factor information and each item transfer information in each item transfer information group in the set of item transfer information groups to generate influencing factor data and transfer data, thereby obtaining a set of influencing factor data and transfer data groups; a quantile regression unit configured to perform quantile regression processing on each transfer data group in the set of influencing factor data and transfer data groups to generate a set of coefficient groups; a mean averaging unit configured to average the corresponding coefficients in the set of coefficient groups to obtain a set of average coefficients; and a visualization unit configured to perform visualization processing on the set of coefficient groups and the set of average coefficients.

[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0012] The above-described embodiments of this disclosure have the following beneficial effects: Through the data visualization methods of some embodiments of this disclosure, the relationship between various factors and the amount of goods transferred can be determined more accurately, thereby uncovering more information to guide business adjustments. Specifically, the reason for easily arriving at erroneous conclusions is that single-factor analysis does not have the ability to separate other factors. Based on this, the data visualization method of some embodiments of this disclosure first obtains influencing factor information and transfer information of each group of homogeneous goods within the historical time period, resulting in a set of goods transfer information groups. The influencing factor information includes a temperature value sequence, and the goods transfer information in the set of goods transfer information groups includes: goods identification, original goods value, and a sub-information sequence. The sub-information in the sub-information sequence of the set of goods transfer information groups includes a sequence of goods transfer amounts. Then, data preprocessing is performed on the influencing factor information and each item transfer information in each item transfer information group in the set of goods transfer information groups to generate influencing factor data and transfer data, resulting in a set of influencing factor data and transfer data groups. This standardizes data of different dimensions, facilitating subsequent processing. Next, quantile regression is performed on each transfer data group in the aforementioned influencing factor data and transfer data set to generate coefficient sets. Thus, regression analysis is conducted on the variables at different quantile levels to obtain coefficients representing the sensitivity of the transfer volume to various factors. Then, the average of the corresponding coefficients in the coefficient set is calculated to obtain an average coefficient set. This average coefficient can be used as a benchmark to determine the sensitivity of the transfer volume to various factors. Finally, the coefficient set and the average coefficient set are visualized. This visualization visually and intuitively displays the influence of factors on goods at different quantiles, facilitating decision-making and business adjustments. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1 These are flowcharts of some embodiments of the data visualization method according to this disclosure;

[0015] Figure 2These are schematic diagrams illustrating the structure of some embodiments of the data visualization apparatus disclosed herein;

[0016] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0022] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] refer to Figure 1 The diagram illustrates a flow 100 of some embodiments of a data visualization method according to the present disclosure. This data visualization method includes the following steps:

[0024] Step 101: Obtain information on influencing factors and transfer information of homogeneous items in each historical time period to obtain a set of item transfer information groups.

[0025] In some embodiments, the entity executing the data visualization method can acquire information on influencing factors and the transfer information of each group of homogeneous items within a historical time period via wired or wireless connections, thereby obtaining a set of item transfer information groups. The influencing factor information may include a temperature value sequence, and the item transfer information in the set of item transfer information groups further includes: item identifier, original item value, and a sequence of sub-information. The sub-information in the sequence of sub-information in the set of item transfer information groups may include a sequence of item transfer quantities. The item identifier can be used to uniquely identify an item. The homogeneous items can be items with the same or similar functions.

[0026] In some optional implementations of certain embodiments, the sub-information in the sub-information sequence of the aforementioned item transfer information set may further include: a transfer value sequence and a transfer promotion activity Boolean value sequence. The aforementioned influencing factor information may further include: a festival day Boolean value sequence, a weekend Boolean value sequence, an extreme weather Boolean value sequence, and a special situation Boolean value sequence. A festival day Boolean value can be used to indicate whether a day is a festival day. A weekend Boolean value can be used to indicate whether a day is a weekend. An extreme weather Boolean value can be used to indicate whether the weather on a day is extreme weather. A special situation Boolean value can be used to indicate whether a situation other than a festival day, weekend, and extreme weather occurred on a day. A value of 1 can be used to indicate that a day is a festival day, a weekend, and the weather is extreme weather, or a special situation has occurred. A value of 0 can be used to indicate that a day is not a festival day, not a weekend, and the weather is not extreme weather, or no special situation has occurred.

[0027] Each piece of information in the sub-information sequence of the above-mentioned item transfer information set corresponds to a different item transfer location in turn. Each item transfer quantity, transfer value, and reduction value in the item transfer quantity sequence, transfer value sequence, and reduction value sequence of the above-mentioned item transfer information set correspond to a different day in the above-mentioned historical time period in turn.

[0028] Step 102: Perform data preprocessing on each item transfer information in each item transfer information group in the set of influencing factor information and item transfer information to generate influencing factor data and transfer data, thus obtaining the set of influencing factor data and transfer data.

[0029] In some embodiments, the executing entity performs data preprocessing on each item transfer information in each item transfer information group in the above-mentioned influencing factor information and the above-mentioned item transfer information group set to generate influencing factor data and transfer data, thereby obtaining an influencing factor data and transfer data group set, which may include the following steps:

[0030] The first step is to standardize the quantitative information in the aforementioned influencing factors and item transfer information to obtain standardized data. This standardization process can be normalization. The quantitative information in the aforementioned influencing factors and item transfer information can be temperature values, original item value, item transfer quantity, and transfer value.

[0031] The second step is to replace the quantitative information in the above-mentioned influencing factors information and the above-mentioned item transfer information with the corresponding standardized data to obtain the influencing factors data and transfer data.

[0032] In some optional implementations of certain embodiments, the transfer data in the aforementioned set of transfer data may include: a normalized sequence of transferred goods, a normalized sequence of original goods value, a normalized sequence of transferred value, a normalized sequence of value reduction ratio, and a Boolean value sequence of transfer promotion activities. The aforementioned influencing factor data may include: a normalized sequence of temperature values, a Boolean value sequence for festival days, a Boolean value sequence for weekends, a Boolean value sequence for extreme weather, and a Boolean value sequence for special circumstances.

[0033] The aforementioned implementing entity performs standardization processing on the quantitative information in the aforementioned influencing factors and the aforementioned goods transfer information to obtain standardized data, which may include the following steps:

[0034] The first step is to determine the ratio of the difference between the original value of the item in each sub-information sequence and the transfer value in each transfer value sequence to the original value of the item, as represented by the item transfer information, as the daily value reduction ratio of the item at each item transfer location, thus obtaining the value reduction ratio sequence.

[0035] The second step is to determine the average value reduction ratio as the mean of each value reduction ratio in the above value reduction ratio sequence.

[0036] The third step is to take the square root of the average of the sum of the squares of the differences between each value reduction ratio in the above value reduction ratio sequence and the above average value reduction ratio, to obtain the square root value of the value reduction ratio.

[0037] The fourth step is to divide the difference between each value reduction ratio in the above value reduction ratio sequence and the above average value reduction ratio by the above value reduction ratio open value to obtain the normalized value reduction ratio of the item represented by the above item transfer information at each item transfer location on a daily basis, thus obtaining the normalized value reduction ratio sequence.

[0038] The fifth step is to take the average value of each temperature value in the above temperature value sequence to obtain the average temperature value.

[0039] The sixth step is to take the square root of the sum of the squares of the differences between each temperature value in the above temperature value sequence and the above average temperature value to obtain the square root value of the temperature value.

[0040] Step 7: Divide the difference between each temperature value and the average temperature value by the square root of the average temperature value to obtain the normalized temperature value for each day, thus obtaining the normalized temperature value sequence.

[0041] As an example, the normalized value reduction ratio can be determined using the following formula:

[0042]

[0043]

[0044] Where i, j, and k represent serial numbers. K represents the number of days within the aforementioned historical time period. P represents the original value. P0 represents the transferred value. P[i] represents the original value of the item included in the i-th item transfer information in the item transfer information group. P0[i][j][k] represents the k-th transfer value sequence in the transfer value sequence of the j-th sub-information sequence within the i-th item transfer information in the item transfer information group. C0 represents the value reduction ratio. C0[i][j][k] represents the value reduction ratio of the item represented by the i-th item transfer information in the item transfer information group at the j-th item transfer location within the aforementioned historical time period on the k-th day. C represents the normalized value reduction ratio. C[i][j][k] represents the normalized value reduction ratio of the item represented by the i-th item transfer information in the item transfer information group at the j-th item transfer location within the aforementioned historical time period on the k-th day.

[0045] The normalized temperature value can be determined using the following formula:

[0046]

[0047] Where k represents the sequence number. T represents the normalized temperature value. T[k] represents the normalized temperature value of the kth day within the above historical time period. T0 represents the temperature value. T0[k] represents the kth temperature value in the above temperature value sequence.

[0048] Step 103: Perform quantile regression on each transition data group in the influencing factor data and transition data group set to generate coefficient groups, thus obtaining a set of coefficient groups.

[0049] In some embodiments, the executing entity performs quantile regression processing on each transition data group in the aforementioned influencing factor data and the aforementioned transition data group set to generate coefficient groups, thereby obtaining a set of coefficient groups. This may include the following steps:

[0050] The first step is to set up a linear model.

[0051] The second step is to use the above linear model as a constraint to find the minimum value of the pre-set objective function.

[0052] The third step is to determine the minimum value of the objective function. When the objective function is minimized, the coefficients of each linear term and the constant term in the linear model are determined as the coefficients in the coefficient set.

[0053] In some alternative implementations of certain embodiments, the execution entity setting a linear model may include the following steps:

[0054] The first step is to set the unknown coefficients for the constant term, and to set the unknown coefficients for the linear term corresponding to the normalized value reduction ratio, the Boolean value for transfer promotion activities, the Boolean value for festival days, the normalized temperature value, the Boolean value for weekends, the Boolean value for extreme weather, and the Boolean value for special circumstances.

[0055] The second step involves using the standardized goods transfer volume as the dependent variable, and the standardized value reduction ratio, transfer promotion activity Boolean value, festival day Boolean value, standardized temperature value, weekend Boolean value, extreme weather Boolean value, and special case Boolean value as independent variables. The sum of the products of the unknown coefficients of the above constant terms and the unknown coefficients of each set linear term with the corresponding independent variables is used to determine the linear model.

[0056] As an example, the above linear model could be:

[0057] S'[i][j][k]=a+ac*C[i][j][k]+ah*H[i][j][k]+av*V[k]+at*T[k]+aw*W[k]+ae*E[k]+ao*O[k]

[0058] Where 'a' represents the unknown coefficient of the constant term. 'ac', 'ah', 'av', 'at', 'aw', 'ae', and 'ao' represent the unknown coefficients of each linear term. 'C[i][j][k]' represents the normalized value reduction ratio of the item represented by the i-th item transfer information in the item transfer information group, at the j-th item transfer location within the aforementioned historical time period on the k-th day. 'H[i][j][k]' represents the k-th Boolean value of the transfer promotion activity in the j-th sub-information of the i-th item transfer information in the item transfer information group. 'V' represents the festival day Boolean value. 'V[k]' represents the k-th festival day Boolean value in the aforementioned festival day Boolean value sequence. 'T' represents the temperature value. 'T[k]' represents the k-th temperature value in the aforementioned temperature value sequence. 'W' represents the weekend Boolean value. 'W[k]' represents the k-th weekend Boolean value in the aforementioned weekend Boolean value sequence. 'E' represents the extreme weather Boolean value. 'E[k]' represents the k-th extreme weather Boolean value in the aforementioned extreme weather Boolean value sequence. 'O' represents the special case Boolean value. O[k] represents the k-th special case Boolean value in the above special case Boolean value sequence. S' represents the fitted value. S'[i][j][k] represents the fitted value for the item transfer volume of the item represented by the i-th item transfer information in the item transfer information group, which is located at the j-th item transfer location in each item transfer location and on the k-th day of the above historical time period.

[0059] Optionally, the above objective function can be set through the following steps:

[0060] The first step is to determine the absolute value of the difference between the normalized item transfer volume in each transfer data group in the above transfer data set and the fitted value of the above linear model as the deviation value, thus obtaining the deviation value set.

[0061] The second step involves determining the objective function as the sum of the product of the deviation value satisfying the first preset condition and the target quantile in the aforementioned deviation value set, and the product of the deviation value satisfying the second preset condition and the target coefficient. The first preset condition is that the standardized item transfer volume corresponding to the deviation value is greater than or equal to the fitted value of the linear model; the second preset condition is that the standardized item transfer volume corresponding to the deviation value is less than the fitted value of the linear model; and the sum of the target coefficient and the target quantile is one.

[0062] As an example, the objective function mentioned above could be:

[0063]

[0064]

[0065]

[0066] Where obj() represents the objective function. τ represents the objective quantile. MIN represents the minimum value. (1-τ) represents the objective coefficient. u and v represent the deviation values. u[i][j][k] and v[i][j][k] characterize the deviation between the k-th item transfer quantity in the item transfer quantity sequence of the j-th sub-information of the i-th item transfer information group and the corresponding fitted value of the item transfer quantity.

[0067] Optionally, the execution entity, using the aforementioned linear model as a constraint, may solve for the minimum value of a pre-set objective function by including the following steps:

[0068] The first step is to select one of the quantiles mentioned above as the target quantile.

[0069] As an example, the quantiles mentioned above can be 0, 20, 40, 60, 80, or 100.

[0070] The second step is to assign initial values ​​to the unknown coefficients of the constant term and the unknown coefficients of each linear term in the above linear model, thus obtaining the linear model to be optimized.

[0071] Third, perform the following optimization sub-steps:

[0072] The first optimization sub-step involves determining the fitted value corresponding to the transfer amount of each standardized item in the above transfer data set based on the linear model to be optimized.

[0073] The second optimization sub-step involves substituting the target quantile, the transfer amount of each standardized item in the aforementioned transfer data set, and the corresponding fitted value into the objective function to obtain the objective function value.

[0074] The third optimization sub-step, in response to determining that the optimization termination condition is met, sets the objective function value to the minimum value of the objective function, and selects an unselected quantile from the aforementioned quantiles as the target quantile, continuing the above optimization sub-steps. The optimization termination condition can be that the minimum value of the objective function is less than a preset value, or that the number of times the optimization sub-steps are executed equals a preset number at the target quantile. In practice, the preset value and preset number of executions can be set according to actual application needs; no limitation is made here.

[0075] Optionally, the aforementioned execution entity may also, in response to determining that the aforementioned optimization termination condition is not met, reassign values ​​to the unknown constant term coefficients and the unknown coefficients of each linear term in the linear model to be optimized, and continue executing the aforementioned optimization sub-steps.

[0076] The steps described above, including the quantile regression processing performed on each transfer data group in the aforementioned influencing factor data and transfer data set to generate coefficient sets and the various sub-steps included therein, constitute an inventive point of this disclosure. This addresses two technical problems mentioned in the background art: 1) "Single-factor analysis lacks the ability to separate other factors, easily leading to erroneous conclusions" and 2) "Manual analysis relies too heavily on human judgment, and the experience and operations of people in different transfer locations vary, potentially leading to cognitive biases and biased final analysis results." The factors causing these problems are often as follows: single-factor analysis lacks the ability to separate other factors; manual analysis relies too heavily on human judgment; and the experience and operations of people in different transfer locations vary, potentially leading to cognitive biases. Solving these factors can improve the accuracy of the results. To achieve this, this disclosure introduces a linear model and an objective function. The linear model is used to fit the relationship between the transfer volume of goods and other factors, avoiding the drawbacks of single-factor analysis's inability to separate other factors. Furthermore, the value of the objective function is continuously reduced by adjusting the coefficients in the linear model. Therefore, when the objective function reaches its minimum value, the values ​​of each coefficient in the linear model are determined.

[0077] Step 104: Take the average value of each corresponding coefficient in the coefficient set to obtain the average coefficient set.

[0078] In some embodiments, the executing entity may take the average of the corresponding coefficients in the set of coefficient groups to obtain an average coefficient set. Here, the corresponding coefficients in the set of coefficient groups refer to the coefficients in each coefficient group that correspond to the same variable.

[0079] Step 105: Visualize the set of coefficient groups and the set of average coefficients.

[0080] In some embodiments, the coefficients in each coefficient group of the aforementioned coefficient group set sequentially correspond to pre-set quantiles, and the coefficient group set includes the coefficients of different categories of information in the sub-information of the aforementioned item transfer information group set. The aforementioned execution entity performs visualization processing on the aforementioned coefficient group set and the aforementioned average coefficient set, which may include the following steps:

[0081] Using quantiles as the x-axis and coefficients as the y-axis, generate and display line graphs showing the relationship between the coefficients and average coefficients of the same category of data in the above coefficient set and the above average coefficient set and the above quantiles.

[0082] Optionally, the visualization processing of the above-mentioned set of coefficient groups and the above-mentioned set of average coefficients may further include:

[0083] Using quantiles as the x-axis and coefficients as the y-axis, generate and display line graphs showing the relationship between the coefficients and averages of the same group of homogeneous items in the aforementioned coefficient set and average coefficient set and the aforementioned quantiles.

[0084] The above-described embodiments of this disclosure have the following beneficial effects: Through the data visualization methods of some embodiments of this disclosure, the relationship between various factors and the amount of goods transferred can be determined more accurately, thereby uncovering more information to guide business adjustments. Specifically, the reason for easily arriving at erroneous conclusions is that single-factor analysis does not have the ability to separate other factors. Based on this, the data visualization method of some embodiments of this disclosure first obtains influencing factor information and transfer information of each group of homogeneous goods within the historical time period, resulting in a set of goods transfer information groups. The influencing factor information includes a temperature value sequence, and the goods transfer information in the set of goods transfer information groups includes: goods identification, original goods value, and a sub-information sequence. The sub-information in the sub-information sequence of the set of goods transfer information groups includes a sequence of goods transfer amounts. Then, data preprocessing is performed on the influencing factor information and each item transfer information in each item transfer information group in the set of goods transfer information groups to generate influencing factor data and transfer data, resulting in a set of influencing factor data and transfer data groups. This standardizes data of different dimensions, facilitating subsequent processing. Next, quantile regression is performed on each transfer data group in the aforementioned influencing factor data and transfer data set to generate coefficient sets. Thus, regression analysis is conducted on the variables at different quantile levels to obtain coefficients representing the sensitivity of the transfer volume to various factors. Then, the average of the corresponding coefficients in the coefficient set is calculated to obtain an average coefficient set. This average coefficient can be used as a benchmark to determine the sensitivity of the transfer volume to various factors. Finally, the coefficient set and the average coefficient set are visualized. This visualization visually and intuitively displays the influence of factors on goods at different quantiles, facilitating decision-making and business adjustments.

[0085] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a data visualization device, which are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0086] like Figure 2As shown, the data visualization device 200 in some embodiments includes: an acquisition unit 201, a preprocessing unit 202, a quantile regression unit 203, a mean-taking unit 204, and a visualization unit 205. The acquisition unit 201 is configured to acquire influencing factor information and transfer information of each group of homogeneous items within a historical time period, thereby obtaining a set of item transfer information groups. The influencing factor information includes a temperature value sequence, and the item transfer information in the set of item transfer information groups includes: item identifier, original item value, and a sequence of sub-information. The sub-information in the sequence of sub-information in the set of item transfer information groups includes a sequence of item transfer volume. The preprocessing unit 202 is configured to perform data preprocessing on each item transfer information in each item transfer information group within the influencing factor information and the set of item transfer information groups, thereby generating influencing factor data and transfer data, thus obtaining a set of influencing factor data and transfer data groups. The quantile regression unit 203 is configured to perform quantile regression processing on each transfer data group within the influencing factor data and the set of transfer data groups, thereby generating a set of coefficient groups, thus obtaining a set of coefficient groups. The mean-taking unit 204 is configured to take the mean of each corresponding coefficient in the set of coefficient groups, thus obtaining a set of average coefficients. The visualization unit 205 is configured to perform visualization processing on the set of coefficient groups and the set of average coefficients.

[0087] It is understandable that the units described in the data visualization device 200 and the reference Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the data visualization device 200 and the units contained therein, and will not be repeated here.

[0088] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0089] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0090] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0091] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0092] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0093] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0094] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire information on influencing factors over a historical time period and transfer information of each group of homogeneous items within the historical time period, obtaining a set of item transfer information groups, wherein the influencing factor information includes a temperature value sequence, and the item transfer information in the item transfer information group set includes: item identification, item original value, and a sequence of sub-information, and the sub-information in the sub-information sequence of the item transfer information group set includes a sequence of item transfer quantities; perform data preprocessing on the influencing factor information and each item transfer information in each item transfer information group in the item transfer information group set to generate influencing factor data and transfer data, obtaining a set of influencing factor data and transfer data groups; perform quantile regression processing on the influencing factor data and each transfer data group in the transfer data group set to generate a set of coefficient groups, obtaining a set of coefficient groups; take the mean of each corresponding coefficient in the set of coefficient groups to obtain a set of average coefficients; and perform visualization processing on the set of coefficient groups and the set of average coefficients.

[0095] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a preprocessing unit, a quantile regression unit, a mean-taking unit, and a visualization unit. The names of these units do not necessarily limit the specific unit itself; for example, the acquisition unit may also be described as "a unit that acquires information on influencing factors over a historical time period and transfer information of each group of homogeneous items within the aforementioned historical time period, thereby obtaining a set of item transfer information groups."

[0098] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

Claims

1. A data visualization method, comprising: Information on influencing factors and transfer information of homogeneous items in historical time periods is obtained to obtain a set of item transfer information groups. The influencing factor information includes a temperature value sequence, and the item transfer information in the set of item transfer information groups includes: item identifier, item original value and sub-information sequence. The sub-information in the sub-information sequence of the set of item transfer information groups includes an item transfer quantity sequence. Data preprocessing is performed on each item transfer information in each item transfer information group within the influencing factor information and item transfer information group set to generate influencing factor data and transfer data, resulting in an influencing factor data and transfer data group set. This includes: standardizing each quantitative information in the influencing factor information and item transfer information to obtain each standardized data; and replacing each quantitative information in the influencing factor information and item transfer information with the corresponding standardized data to obtain influencing factor data and transfer data. Quantile regression processing is performed on the influencing factor data and each transfer data group in the transfer data set to generate a coefficient set, which includes: setting a linear model; solving for the minimum value of a pre-set objective function using the linear model as a constraint; in response to determining that the objective function has reached its minimum value, when the objective function reaches its minimum value, the values ​​of each linear term coefficient and constant term coefficient in the linear model are determined as coefficients in the coefficient set, wherein setting the linear model includes: setting unknown constant term coefficients, and setting unknown linear term coefficients for the normalized value reduction ratio, transfer promotion activity Boolean value, festival day Boolean value, normalized temperature value, weekend Boolean value, extreme weather Boolean value, and special case Boolean value; using the normalized item transfer volume as... The dependent variable includes the standardized value reduction ratio, the Boolean value of the transfer promotion activity, the Boolean value of the festival day, the standardized temperature value, the Boolean value of the weekend, the Boolean value of the extreme weather, and the Boolean value of the special situation. The independent variables are the constant term coefficient unknowns and the sum of the products of each set of linear term coefficient unknowns and their corresponding independent variables, which constitute the linear model. The objective function is set through the following steps: the absolute value of the difference between the standardized item transfer amount in each transfer data group in the transfer data group set and the fitted value of the linear model is determined as the deviation value, resulting in a deviation value set; the product of the deviation value in the deviation value set that satisfies the first preset condition and the target quantile, and the product of the deviation value in the deviation value set that satisfies the second preset condition and the target coefficient are used to determine the objective function. The average coefficient set is obtained by taking the mean of each corresponding coefficient in the set of coefficient groups. The set of coefficient groups and the set of average coefficients are visualized. Wherein, each sub-information in the sub-information sequence of the item transfer information set corresponds sequentially to each item transfer location, and each item transfer quantity, transfer value, and reduction value in the item transfer quantity sequence, transfer value sequence, and reduction value sequence of the item transfer information set corresponds sequentially to each day within the historical time period; and The process of standardizing the quantitative information in the influencing factor information and the item transfer information to obtain standardized data includes: The ratio of the difference between the original value of the item in each sub-information sequence and the transfer value in each transfer value sequence to the original value of the item is determined as the daily value reduction ratio of the item represented by the item transfer information at each item transfer location, thus obtaining the value reduction ratio sequence. The mean of each value reduction ratio in the value reduction ratio sequence is determined as the average value reduction ratio; The square root of the sum of the squares of the differences between each value reduction ratio and the average value reduction ratio in the value reduction ratio sequence is taken to obtain the square root value of the value reduction ratio. Divide the difference between each value reduction ratio in the value reduction ratio sequence and the average value reduction ratio by the square root of the value reduction ratio to obtain the normalized value reduction ratio of the item represented by the item transfer information at each item transfer location on a daily basis, thus obtaining the normalized value reduction ratio sequence. The average temperature value is obtained by averaging the individual temperature values ​​in the temperature value sequence. The square root of the sum of the squares of the differences between each temperature value and the average temperature value in the temperature value sequence is taken to obtain the square root of the temperature value. Divide the difference between each temperature value and the average temperature value by the square root of the temperature value to obtain the normalized temperature value for each day, thus obtaining a normalized temperature value sequence.

2. The method according to claim 1, wherein, The sub-information sequence in the set of item transfer information groups also includes: transfer value sequence, transfer promotion activity Boolean value sequence, and the influencing factor information also includes: festival day Boolean value sequence, weekend Boolean value sequence, extreme weather Boolean value sequence, and special situation Boolean value sequence.

3. The method according to claim 2, wherein, The coefficients in each coefficient group in the set of coefficient groups correspond sequentially to the pre-set quantiles. The set of coefficient groups includes the coefficients of different categories of information in the sub-information of the item transfer information set. as well as The visualization processing of the set of coefficient groups and the set of average coefficients includes: Using quantiles as the x-axis and coefficients as the y-axis, generate and display line graphs showing the relationship between the coefficients and average coefficients of the same category of data in the set of coefficient groups and the set of average coefficients and the respective quantiles.

4. The method according to claim 3, wherein, The visualization process for the set of coefficient groups and the set of average coefficients further includes: Using quantiles as the x-axis and coefficients as the y-axis, line graphs are generated and displayed for the coefficients and averages of the same group of homogeneous items in the set of coefficient groups and the set of average coefficients, respectively, and their relationship with each quantile.

5. A data visualization device, comprising: The acquisition unit is configured to acquire information on influencing factors during a historical time period and transfer information of each group of homogeneous items during the historical time period, thereby obtaining a set of item transfer information groups. The influencing factor information includes a temperature value sequence, and the item transfer information in the set of item transfer information groups includes: item identifier, item original value, and sub-information sequence. The sub-information in the sub-information sequence of the set of item transfer information groups includes an item transfer quantity sequence. The preprocessing unit is configured to perform data preprocessing on each item transfer information in each item transfer information group within the influencing factor information and the item transfer information group set, to generate influencing factor data and transfer data, thereby obtaining an influencing factor data and transfer data group set. This includes: normalizing each quantitative information in the influencing factor information and the item transfer information to obtain normalized data; and replacing each quantitative information in the influencing factor information and the item transfer information with the corresponding normalized data to obtain the influencing factor data and transfer data. The quantile regression unit is configured to perform quantile regression processing on the influencing factor data and each transfer data group in the transfer data group set to generate a coefficient set, including: setting a linear model; solving for the minimum value of a pre-set objective function using the linear model as a constraint; in response to determining that the objective function has reached its minimum value, when the objective function reaches its minimum value, the values ​​of each linear term coefficient and constant term coefficient in the linear model are determined as coefficients in the coefficient set, wherein setting the linear model includes: setting unknown constant term coefficients, and setting unknown linear term coefficients for the normalized value reduction ratio, transfer promotion activity Boolean value, festival day Boolean value, normalized temperature value, weekend Boolean value, extreme weather Boolean value, and special case Boolean value; using the normalized value... The quantity of goods transferred is the dependent variable, and the standardized value reduction ratio, the Boolean value of the transfer promotion activities, the Boolean value of the festival day, the standardized temperature value, the Boolean value of the weekend, the Boolean value of the extreme weather, and the Boolean value of the special circumstances are the independent variables. The sum of the products of the unknown coefficients of the constant terms and the unknown coefficients of each set of linear terms with their corresponding independent variables is determined as the linear model. The objective function is set through the following steps: the absolute value of the difference between the standardized quantity of goods transferred in each transfer data group in the transfer data set and the fitted value of the linear model is determined as the deviation value, resulting in a set of deviation values; the sum of the product of the deviation values ​​in the set of deviation values ​​that satisfy the first preset condition and the target quantile, and the product of the deviation values ​​in the set of deviation values ​​that satisfy the second preset condition and the target coefficient is determined as the objective function. The averaging unit is configured to take the average of each corresponding coefficient in the set of coefficient groups to obtain an average coefficient set. A visualization unit is configured to perform visualization processing on the set of coefficient groups and the set of average coefficients; Wherein, each sub-information in the sub-information sequence of the item transfer information set corresponds sequentially to each item transfer location, and each item transfer quantity, transfer value, and reduction value in the item transfer quantity sequence, transfer value sequence, and reduction value sequence of the item transfer information set corresponds sequentially to each day within the historical time period; and The process of standardizing the quantitative information in the influencing factor information and the item transfer information to obtain standardized data includes: The ratio of the difference between the original value of the item in each sub-information sequence and the transfer value in each transfer value sequence to the original value of the item is determined as the daily value reduction ratio of the item represented by the item transfer information at each item transfer location, thus obtaining the value reduction ratio sequence. The mean of each value reduction ratio in the value reduction ratio sequence is determined as the average value reduction ratio; The square root of the sum of the squares of the differences between each value reduction ratio and the average value reduction ratio in the value reduction ratio sequence is taken to obtain the square root value of the value reduction ratio. Divide the difference between each value reduction ratio in the value reduction ratio sequence and the average value reduction ratio by the square root of the value reduction ratio to obtain the normalized value reduction ratio of the item represented by the item transfer information at each item transfer location on a daily basis, thus obtaining the normalized value reduction ratio sequence. The average temperature value is obtained by averaging the individual temperature values ​​in the temperature value sequence. The square root of the sum of the squares of the differences between each temperature value and the average temperature value in the temperature value sequence is taken to obtain the square root of the temperature value. Divide the difference between each temperature value and the average temperature value by the square root of the temperature value to obtain the normalized temperature value for each day, thus obtaining a normalized temperature value sequence.

6. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-4.

7. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-4.

Images