CN115907217A - Data processing method, device, equipment and computer storage medium - Google Patents
Data processing method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN115907217A CN115907217A CN202211661004.5A CN202211661004A CN115907217A CN 115907217 A CN115907217 A CN 115907217A CN 202211661004 A CN202211661004 A CN 202211661004A CN 115907217 A CN115907217 A CN 115907217A
- Authority
- CN
- China
- Prior art keywords
- economic situation
- prediction model
- data
- target
- sales
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The application discloses a data processing method, a data processing device, data processing equipment and a computer storage medium. The data processing method comprises the following steps: acquiring sales data of a target object at each preset time point in a first preset time period; constructing target prediction models under different economic situation grades according to the sales data of each preset time point in the first preset time period, wherein the target prediction models are used for predicting the sales values of different time points; and determining the sales value of the target object at the target time point under the target economic situation grade based on the target prediction model, thereby realizing accurate prediction of the sales value of the target object.
Description
Technical Field
The present application relates to the field of financial data processing, and in particular, to a data processing method, apparatus, device, and computer storage medium.
Background
In recent years, chinese economy fluctuates greatly, the problem of credit risk management is increasingly prominent, and risk control and management of enterprise customers are more complicated, so that sales income of enterprises in a future period needs to be accurately predicted, and the maximum debt total amount born by the enterprises can be scientifically and objectively evaluated.
At present, the method for predicting future sales income of enterprises mainly comprises two major categories, specifically as follows:
in the first category, the income prediction related knowledge is solidified into rules according to expert experience and business development trend, and the rules are utilized to predict the future sales income of enterprises. However, this method is liable to have the following problems: the expert experience used in the rule is subjective, the cognition of different experts on the future sales income prediction is different, and when the rule adopts different expert experiences, different prediction results can be obtained, so that a user cannot obtain an accurate prediction result by using the rule; meanwhile, the external environment and the business development of the bank are rapid, so that the rules cannot timely follow the changes of the industry, and the user cannot accurately predict the future sales income of the enterprise by using the rules.
In the second category, the deep learning model is used for predicting the future sales income of the enterprise, but the model is relatively crude and cannot accurately predict the future sales income of the enterprise.
The method aims to solve the problem that in the prior art, no matter a curing rule is adopted to predict future sales income of an enterprise, or a deep learning model is adopted to predict future sales income of the enterprise, an accurate prediction result cannot be obtained.
Disclosure of Invention
The embodiment of the application provides a data processing method, a data processing device, a data processing apparatus and a computer storage medium, wherein a target prediction model under different economic situation grades is constructed by adopting sales data of a target object at each preset time point in a first preset time period, so that the technical purpose of predicting sales values of the target object at different economic situation grades and different preset time points through the target prediction model is achieved, and the technical effect of accurately predicting the sales values of the target object is achieved.
In a first aspect, an embodiment of the present application provides a data processing method, where the method includes: acquiring sales data of a target object at each preset time point in a first preset time period; according to the sales data of each preset time point in a first preset time period, constructing target prediction models under different economic situation grades, wherein the target prediction models are used for predicting sales values of different time points; and determining the sales value of the target object at the target time point under the target economic situation level based on the target prediction model.
In one embodiment, constructing the target prediction model under different economic situation levels according to the sales data of each preset time point in the first preset time period comprises the following steps: constructing a plurality of prediction models based on sales data of each preset time point in a first preset time period; and fitting a prediction model for each economic situation grade from the plurality of prediction models to serve as a target prediction model of the economic situation grade.
In one embodiment, building a plurality of predictive models based on sales data for each preset time point within a first preset time period includes: constructing an initial prediction model by adopting an autoregressive model based on sales data of each preset time point in a first preset time period; predicting sales data of the target object at each preset time point in a first preset time period by adopting an initial prediction model; calculating a difference value between the sales data obtained at each preset time point and the sales data obtained by prediction; and simulating the error term of the initial prediction model for multiple times by adopting a Monte Carlo simulation method based on the difference value of each preset time point to obtain multiple prediction models.
In one embodiment, one prediction model is adapted for each economic situation level from a plurality of prediction models as a target prediction model for the economic situation level, comprising: obtaining sales income threshold values corresponding to different economic situation grades; and on the basis of sales income threshold values corresponding to different economic situation grades, adapting a prediction model for each economic situation grade from a plurality of prediction models to serve as a target prediction model of the economic situation grade.
In one embodiment, obtaining sales revenue thresholds corresponding to different economic situational levels includes: acquiring preset parameter values corresponding to different economic situation grades; calculating the average value and the standard deviation of the sales data in a first preset time period; calculating the average value and the standard deviation of the sales data and preset parameter values corresponding to different economic situation grades by adopting a first calculation formula to obtain sales income threshold values corresponding to the different economic situation grades, wherein the first calculation formula comprises the following steps: th _ Incomej = Avg _ Income + w j * Std _ Income; th _ Incomer denotes the j-Th economySales revenue threshold for situational ratings, avg-Income represents the average of sales data, w j The preset parameter value representing the j-th economic situation rating and Std-Income representing the standard deviation of sales data.
In one embodiment, based on sales income thresholds corresponding to different economic situation grades, a prediction model is adapted to each economic situation grade from a plurality of prediction models to serve as a target prediction model of the economic situation grade, and the method comprises the following steps: predicting sales prediction data of the target object at each preset time point in a second preset time period by adopting each prediction model to obtain a prediction data group corresponding to each prediction model; calculating a similarity value between a prediction data set generated by each prediction model and a sales income threshold corresponding to each economic situation grade; reserving m groups of prediction data groups with the highest similarity values for each economic situation grade; and on the basis of the prediction model corresponding to the prediction data set reserved for each economic situation grade, adapting a prediction model for each economic situation grade to serve as a target prediction model of the economic situation grade.
In one embodiment, in a case where a group of prediction data sets with the highest similarity value is reserved for each economic situation level, based on a prediction model corresponding to the prediction data set reserved for each economic situation level, adapting a prediction model for each economic situation level as a target prediction model for the economic situation level includes: and taking the prediction model corresponding to the prediction data group reserved for each economic situation grade as a target prediction model of the economic situation grade.
In one embodiment, in a case that a plurality of prediction data sets with the highest similarity values are reserved in each economic situation level, one prediction model is adapted to each economic situation level based on a prediction model corresponding to the prediction data set reserved in each economic situation level, and the adaptation of one prediction model to each economic situation level is used as a target prediction model of the economic situation level, and the adaptation of the prediction model to each economic situation level comprises the following steps: generating m based on the prediction data set retained for each economic situation level i The method comprises the following steps of combining data, wherein each economic situation grade in the data combination corresponds to one group of prediction data groups, and i represents the total grade number of the economic situation grades; sequentially detecting each of the data combinationsWhether the predicted sales data of the economic situation grade is lower than the predicted sales data of the economic situation grade or not is judged according to the predicted sales data of the preset time point, and if the predicted sales data of the economic situation grade is higher than the predicted sales data of the economic situation grade, an error sequence is recorded for the data combination; reserving n data combinations with the least misordering times; and on the basis of the prediction model corresponding to each economic situation grade in the reserved data combination, adapting a prediction model for each economic situation grade to serve as a target prediction model of the economic situation grade.
In one embodiment, in a case of reserving a data combination with the least number of misorders, based on a prediction model corresponding to each economic situation level in the reserved data combination, adapting a prediction model for each economic situation level as a target prediction model for the economic situation level, including: and taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the reserved data combination as a target prediction model of the economic situation grade.
In one embodiment, in a case where a plurality of data combinations with the smallest misordering times are reserved, one prediction model is adapted to each economic situation level based on a prediction model corresponding to each economic situation level in the reserved data combinations, and the method for predicting the economic situation level as the target prediction model comprises the following steps: and calculating the similarity total value of each reserved data combination in turn, wherein the similarity total value of the data combination is as follows: the sum of similarity values between the prediction data set of each economic situation grade in the data combination and a preset threshold value of the economic situation grade; and taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the data combination with the minimum similar total value as a target prediction model of the economic situation grade.
In one embodiment, determining the sales value of the target object at the target economic situation level and the target preset time point based on the target prediction model comprises: acquiring a target economic situation grade, a target prediction model corresponding to the target economic situation grade and a target preset time point; and determining the sales value of the target object at the target preset time point under the target economic situation level by adopting the target prediction model corresponding to the target economic situation level.
In a second aspect, an embodiment of the present application provides a data processing apparatus, including: the acquisition unit is used for acquiring the sales data of each preset time point of the target object in a first preset time period; the construction unit is used for constructing target prediction models under different economic situation grades according to the sales data of each preset time point in a first preset time period, and the target prediction models are used for predicting the sales values of the different time points; and the determining unit is used for determining the sales value of the target object at the target time point under the target economic situation level based on the target prediction model.
In one embodiment, a unit is constructed comprising: the construction subunit is used for constructing a plurality of prediction models based on the sales data of each preset time point in a first preset time period; and the adapter unit is used for adapting a prediction model for each economic situation grade from a plurality of prediction models to serve as a target prediction model of the economic situation grade.
In one embodiment, a subunit is constructed, comprising: the construction module is used for constructing an initial prediction model by adopting an autoregressive model based on the sales data of each preset time point in a first preset time period; the prediction module is used for predicting the sales data of the target object at each preset time point in a first preset time period by adopting an initial prediction model; the calculation module is used for calculating the difference value between the sales data acquired at each preset time point and the sales data obtained by prediction; and the simulation module is used for simulating the error term of the initial prediction model for multiple times by adopting a Monte Carlo simulation method based on the difference value of each preset time point to obtain multiple prediction models.
In one embodiment, an adaptorportion unit, comprising: the acquisition module is used for acquiring sales income thresholds corresponding to different economic situation grades; and the adaptation module is used for adapting a prediction model for each economic situation grade from the plurality of prediction models as a target prediction model of the economic situation grade based on sales income threshold values corresponding to different economic situation grades.
In one embodiment, an acquisition module includes: the first obtaining submodule is used for obtaining preset parameter values corresponding to different economic situation grades; the first calculation submodule is used for calculating the average value and the standard deviation of the sales data in a first preset time period; the second calculation submodule is used for calculating the average value and the standard deviation of the sales data and preset parameter values corresponding to different economic situation grades by adopting a first calculation formula to obtain sales income threshold values corresponding to the different economic situation grades,
wherein the first calculation formula: th _ Income j ＝Avg_Income+w j *Std_Income；
Th_Income j Sales revenue threshold representing the jth economic situational level, avg _ Income representing the average of sales data, w j The preset parameter value representing the j-th economic situation rating and Std-Income representing the standard deviation of sales data.
In one embodiment, an adaptation module comprises: the prediction submodule is used for predicting the predicted sales data of the target object at each preset time point in a second preset time period by adopting each prediction model to obtain a prediction data group corresponding to each prediction model; the third calculation sub-module is used for calculating a similarity value between the prediction data set generated by each prediction model and a sales income threshold value corresponding to each economic situation grade; the first retaining submodule is used for retaining m groups of prediction data groups with the highest similarity values in each economic situation grade; and the first adaptation submodule is used for adapting a prediction model for each economic situation grade based on the prediction model corresponding to the prediction data set reserved for each economic situation grade to serve as a target prediction model of the economic situation grade.
In one embodiment, the first adaptation sub-module includes: and the second adaptation submodule is used for taking the prediction model corresponding to the prediction data group reserved for each economic situation grade as the target prediction model of the economic situation grade under the condition that a group of prediction data groups with the highest similarity value is reserved for each economic situation grade.
In one embodiment, the first adaptation sub-module includes: fourth calculating submoduleA block for generating m on the basis of the prediction data group reserved for each economic situation level in the case where a plurality of prediction data groups having the highest similarity values are reserved for each economic situation level i The method comprises the following steps of combining data, wherein each economic situation grade in the data combination corresponds to one group of prediction data groups, and i represents the total grade number of the economic situation grades; the detection submodule is used for sequentially detecting the predicted sales data of each preset time point in each data combination, judging whether the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, and recording an error sequence for the data combination under the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade; the second reservation submodule is used for reserving n data combinations with the least error sequence times; and the third adaptation submodule is used for adapting a prediction model for each economic situation grade based on the prediction model corresponding to each economic situation grade in the reserved data combination to serve as a target prediction model of the economic situation grade.
In one embodiment, the third adaptation sub-module comprises: and the fourth adaptation submodule is used for taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the reserved data combination as the target prediction model of the economic situation grade under the condition that a data combination with the minimum misordering times is reserved.
In one embodiment, the third adaptation sub-module comprises: a fifth calculating sub-module, configured to calculate, in sequence, a total similarity value of each of the retained data combinations when a plurality of data combinations with the smallest misordering times are retained, where the total similarity value of each of the data combinations is: the sum of similarity values between the prediction data set of each economic situation grade in the data combination and a preset threshold value of the economic situation grade; and the fifth adaptation submodule is used for taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the data combination with the minimum similar total value as the target prediction model of the economic situation grade.
In one embodiment, the determining unit includes: the acquisition subunit is used for acquiring a target economic situation grade, a target prediction model corresponding to the target economic situation grade and a target preset time point; and the determining subunit is used for determining the sales value of the target object at the target preset time point under the target economic situation level by adopting the target prediction model corresponding to the target economic situation level.
In a third aspect, an embodiment of the present application provides a data processing apparatus, including: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the data processing method as described above.
In a fourth aspect, embodiments of the present application provide a computer storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the data processing method as above.
According to the data processing method, the data processing device, the data processing equipment and the computer storage medium, the sales data of the target object at each preset time point in the first preset time period are adopted to construct the target prediction models at different economic situation grades, the technical purpose that the sales values of the target object at different preset time points at different economic situation grades are predicted through the target prediction models is achieved, and accurate prediction of the sales values of the target object is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of a data processing method according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a data processing apparatus according to another embodiment of the present application;
fig. 3 is a schematic structural diagram of a data processing device according to yet another embodiment of the present application.
Detailed Description
Features of various aspects and exemplary embodiments of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of, and not restrictive on, the present application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" comprises 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
In order to solve the prior art problems, embodiments of the present application provide a data processing method, apparatus, device, and computer storage medium. First, a data processing method provided in an embodiment of the present application is described below.
Fig. 1 shows a schematic flowchart of a data processing method according to an embodiment of the present application. As shown in fig. 1, the data processing method includes:
s101, obtaining sales data of the target object at each preset time point in a first preset time period.
The first preset time period is a historical time period, and the duration can be set by a user in a self-defined mode. A plurality of preset time points are arranged in the first preset time period. In some embodiments, the time interval for each preset time point is the same, for example: the time interval between two adjacent preset time points may be one month, one quarter, one year, etc. The sales data at the preset time point may be a total sales value of the target object from the last preset time point to the preset time point.
S102, according to the sales data of each preset time point in the first preset time period, target prediction models under different economic situation grades are built, and the target prediction models are used for predicting the sales values of the different preset time points.
In some embodiments, the economic form may be graded according to the quality or the strength of the economic situation, and the economic situation may be graded into i grades. In the embodiment of the present application, the economic situation of the ith grade is better than that of the (i + 1) th grade.
S103, determining the sales value of the target object at the target time point under the target economic situation grade based on the target prediction model.
According to the method and the device, the target prediction models under different economic situation grades are constructed by adopting the sales data of the target object at each preset time point in the first preset time period, so that the sales values of the target object at different preset time points under different economic situation grades are predicted through the target prediction models, and the accurate prediction of the sales values of the target object is realized.
In one embodiment, the target prediction models under different economic situation levels are constructed according to the sales data of each preset time point in the first preset time period, and the method can be realized by the following steps:
the first mode is as follows: according to different economic periods spanned by the first preset time period, the first preset time period is divided into a plurality of sub-time periods, and target prediction models under different economic situations are constructed on the basis of sales data corresponding to the different sub-time periods.
The second mode is as follows: constructing a plurality of prediction models based on sales data of each preset time point in a first preset time period; and fitting a prediction model for each economic situation grade from the plurality of prediction models to serve as a target prediction model of the economic situation grade.
In one embodiment, the step of "building a plurality of prediction models based on the sales data at each preset time point in the first preset time period" in the second mode can be implemented as follows: constructing an initial prediction model by adopting an autoregressive model based on sales data of each preset time point in a first preset time period; predicting sales data of the target object at each preset time point in a first preset time period by adopting an initial prediction model; calculating a difference value between the sales data obtained at each preset time point and the sales data obtained by prediction; and on the basis of the difference value of each preset time point, simulating the error term of the initial prediction model for multiple times by adopting a Monte Carlo simulation method to obtain multiple prediction models.
In one example, based on the difference value of each preset time point, the error term of the initial prediction model is simulated for multiple times by using a monte carlo simulation method to obtain multiple prediction models, which can be implemented as follows: calculating the average value and the variance of the difference values of a plurality of preset time points; constructing positive-space distribution of the difference values based on the average value and the variance of the difference values of a plurality of preset time points; and (3) based on the positive-too distribution of the difference values, adopting a Monte Carlo simulation method to simulate the error terms of the initial prediction model for multiple times to obtain multiple prediction models.
In one embodiment, the step of "adapting a prediction model for each economic situation level from a plurality of prediction models as a target prediction model for an economic situation level" in the second manner can be implemented as follows: obtaining sales income threshold values corresponding to different economic situation grades; and on the basis of sales income threshold values corresponding to different economic situation grades, one prediction model is adapted to each economic situation grade from the multiple prediction models to serve as a target prediction model of the economic situation grade.
In one embodiment, obtaining sales revenue thresholds corresponding to different economic situational levels may be accomplished by: acquiring preset parameter values corresponding to different economic situation grades; calculating the average value and the standard deviation of the sales data in a first preset time period; using a first calculation formulaCalculating the average value and the standard deviation of the sales data and preset parameter values corresponding to different economic situation grades to obtain sales income threshold values corresponding to different economic situation grades, wherein the first calculation formula comprises the following steps: th _ Incomej = Avg _ Income + w j * Std _ Income; th _ Incomer represents sales revenue threshold for the j economic situational rating, avg _ Incomer represents the average of sales data, w j The preset parameter value representing the j-th economic situation rating and Std-Income representing the standard deviation of sales data.
In one example, the preset parameter value corresponding to the economic situation level satisfies the following condition: 1. the preset parameter value of the economic situation grade representing the stable economic condition is 0,2, and the preset parameter value with high economic situation grade is larger than the preset parameter value with low economic situation grade; 3. the preset parameter value of the lowest economic situation grade is more than or equal to-Avg _ Income/Std _ Income, so that the sales Income threshold value of the lowest economic situation grade is more than or equal to 0.
In one example, the preset parameter value corresponding to the economic situation level further satisfies the following condition: w is a j ＝w j+1 + s, where s = (Avg _ inclusion/Std _ inclusion)/(i-z), i is the total number of grades of economic situational grade, and z is the number of grades representing an economically stable economic situational grade.
In one embodiment, based on sales income thresholds corresponding to different economic situation levels, a prediction model with prediction data most conforming to the economic situation is matched for each economic situation level from a plurality of prediction models, and the target prediction model as the economic situation level can be realized in a plurality of ways, specifically as follows:
the first scheme comprises the following steps:
based on sales income thresholds corresponding to different economic situation grades, a prediction model with prediction data most conforming to the economic situation is matched for each economic situation grade from a plurality of prediction models and is used as a target prediction model of the economic situation grade, and the method can be realized by the following steps:
s201, predicting the predicted sales data of the target object at each preset time point in a second preset time period by using each prediction model to obtain a prediction data set corresponding to each prediction model.
In one example, the second predetermined time period is a future time period, and the duration may be customized by the user. A plurality of preset time points are set in the second preset time period, and the time interval of each preset time point is the same, for example: the time interval between two adjacent preset time points may be one month, one quarter, one year, etc.
In one example, the predicted sales data for a plurality of predictive models is shown in Table 1:
TABLE 1 predictive sales data sheet
S202, calculating a similarity value between the prediction data set generated by each prediction model and a sales income threshold corresponding to each economic situation grade.
In one example, the similarity between the prediction data set generated by the prediction model and the sales revenue threshold corresponding to the economic situation level is calculated by the following formula:
In one example, the similarity between the prediction data set generated by each prediction model and the sales revenue threshold corresponding to each economic situation level is shown in table 2:
TABLE 2 table of similarity values
S203, reserving a group of prediction data groups with the highest similarity value for each economic situation grade;
and S204, taking the prediction model corresponding to the prediction data group reserved for each economic situation grade as a target prediction model of the economic situation grade.
Scheme II:
based on sales income threshold values corresponding to different economic situation grades, matching a prediction model with prediction data most conforming to the economic situation for each economic situation grade from a plurality of prediction models to serve as a target prediction model of the economic situation grade, and realizing the method by the following steps:
s301, predicting sales prediction data of the target object at each preset time point in a second preset time period by using each prediction model to obtain a prediction data group corresponding to each prediction model.
And S302, calculating a similarity value between the prediction data set generated by each prediction model and a sales income threshold corresponding to each economic situation grade.
S303, reserving m groups of prediction data groups with the highest similarity values at each economic situation level, wherein m is larger than 1.
S304, generating m based on the prediction data set reserved for each economic situation grade i And a data combination, wherein each economic situation grade corresponds to one group of prediction data groups in the data combination, and i represents the total grade number of the economic situation grades.
In one example, m i The combination of the data combinations is shown in table 3:
| economic situation class 1 | Economic situation grade 2 | …… | Economic situation grade i |
| m prediction data sets | m prediction data sets | …… | m prediction data sets |
TABLE 3 combination of data combinations
S305, sequentially detecting the predicted sales data of each preset time point in each data combination, judging whether the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, and recording an error sequence for the data combination under the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade;
in one example, the forecasted sales data in a certain data combination, as shown in Table 4:
| 1 month in the future | Future 2 months | …… | Future k months | |
| Economic situation class 1 | Y1,1 | Y1,2 | …… | Y1,k |
| Economic situation class 2 | Y2,1 | Y2,2 | …… | Y2,k |
| …… | …… | …… | …… | …… |
| Economic situation grade i | Yi,1 | Yi,2 | …… | Yi,k |
If the predicted sales data of the future 1 month in the table 4 has the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, recording an error sequence for the data combination of the table 4; if the predicted sales data of 2 months in the future in the table 4 have the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, recording an error sequence for the data combination of the table 4; if the predicted sales data of the future k months in table 4 do not have the situation that the predicted sales data with low economic situation level is higher than the predicted sales data with high economic situation level, the misorder is not recorded.
S306, reserving a data combination with the least error sequence times.
And S307, taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the reserved data combination as a target prediction model of the economic situation grade.
The third scheme is as follows:
based on sales income threshold values corresponding to different economic situation grades, matching a prediction model with prediction data most conforming to the economic situation for each economic situation grade from a plurality of prediction models to serve as a target prediction model of the economic situation grade, and realizing the method by the following steps:
s401, predicting the predicted sales data of the target object at each preset time point in a second preset time period by using each prediction model to obtain a prediction data group corresponding to each prediction model.
S402, calculating a similarity value between the prediction data set generated by each prediction model and a sales income threshold value corresponding to each economic situation grade.
And S403, keeping m groups of prediction data groups with the highest similarity value at each economic situation level, wherein m is larger than 1.
S404, generating m based on the prediction data group reserved by each economic situation grade i And a data combination, wherein each economic situation grade corresponds to one group of prediction data groups in the data combination, and i represents the total grade number of the economic situation grades.
S405, detecting the predicted sales data of each preset time point in each data combination in sequence, judging whether the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, and recording an error sequence for the data combination under the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade.
S406, n data combinations with the minimum misordering times are reserved, and n is larger than 1.
S407, sequentially calculating a total similarity value of each reserved data combination, where the total similarity value of the data combination is: and the sum of similarity values between the prediction data set of each economic situation grade in the data combination and a preset threshold value of the economic situation grade.
In one example, assuming there are 3 economic situational levels, 3 data combinations are retained, and a similar total value for each retained data combination is shown in table 5:
and S408, taking the prediction model corresponding to the prediction data group corresponding to each economic situation level in the data combination with the minimum similar total value as a target prediction model of the economic situation level.
In one example, if the S3 value corresponding to < TOP5, TOP2, TOP3> is the smallest, then when predicting the business sales income of a k month future at a level of 1 economic situation, then the prediction model corresponding to TOP5 is adopted; when the sales income of an enterprise is predicted at the future k months of the economic situation level 2, a prediction model corresponding to TOP2 is adopted; and when the sales income of the enterprise is predicted at the future k months of the economic situation level 3, adopting a prediction model corresponding to TOP 3.
In one embodiment, determining the sales value of the target object at the target economic situation level and the target preset time point based on the target prediction model comprises: acquiring a target economic situation grade, a target prediction model corresponding to the target economic situation grade and a target preset time point; and determining the sales value of the target object at a target preset time point under the target economic situation grade by adopting a target prediction model corresponding to the target economic situation grade.
In other words, if the user wants to obtain the sales value of the target preset time point of the target object at the target economic situation level, the target economic situation level and the target preset time point are input, and at this time, the processor determines the sales value of the target preset time point of the target object at the target economic situation level based on the target prediction model corresponding to the target economic situation level, so that the technical effect of accurate prediction is achieved.
Fig. 2 shows a schematic structural diagram of a data processing apparatus according to an embodiment of the present application. As shown in fig. 2, the data processing apparatus includes:
the acquiring unit 210 is configured to acquire sales data of a target object at each preset time point within a first preset time period;
the building unit 220 is configured to build target prediction models under different economic situation grades according to sales data of each preset time point within a first preset time period, where the target prediction models are used for predicting sales values of different time points;
and the determining unit 230 is used for determining the sales value of the target object at the target time point under the target economic situation level based on the target prediction model.
According to the method and the device, the target prediction models under different economic situation grades are constructed by adopting the sales data of the target object at each preset time point in the first preset time period, the technical purpose of predicting the sales values of the target object at different preset time points under different economic situation grades through the target prediction models is achieved, and the technical effect of accurately predicting the sales values of the target object is achieved.
Fig. 3 shows a hardware structure diagram of a data processing device according to an embodiment of the present application.
The data processing device may comprise a processor 301 and a memory 302 in which computer program instructions are stored.
Specifically, the processor 301 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the application.
The processor 301 realizes any one of the data processing methods in the above-described embodiments by reading and executing computer program instructions stored in the memory 302.
In one example, the data processing device may also include a communication interface 303 and a bus 310. As shown in fig. 3, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 to complete communication therebetween.
The communication interface 303 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present application.
In addition, in combination with the data processing method in the foregoing embodiments, the embodiments of the present application may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the data processing methods in the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (12)
1. A data processing method, characterized in that the data processing method comprises:
acquiring sales data of a target object at each preset time point in a first preset time period;
constructing target prediction models under different economic situation grades according to the sales data of each preset time point in the first preset time period, wherein the target prediction models are used for predicting the sales values of different time points;
and determining the sales value of the target object at a target time point under a target economic situation level based on the target prediction model.
2. The processing method according to claim 1, wherein constructing the target prediction model under different economic situation levels according to the sales data of each preset time point in the first preset time period comprises:
constructing a plurality of prediction models based on the sales data of each preset time point in the first preset time period;
and adapting a prediction model for each economic situation level from the plurality of prediction models as a target prediction model for the economic situation level.
3. The process of claim 2, wherein constructing a plurality of predictive models based on sales data for each of the predetermined time points within the first predetermined time period comprises:
constructing an initial prediction model by adopting an autoregressive model based on the sales data of each preset time point in the first preset time period;
predicting the sales data of the target object at each preset time point in the first preset time period by adopting the initial prediction model;
calculating a difference value between the sales data obtained at each preset time point and the sales data obtained by prediction;
and simulating the error term of the initial prediction model for multiple times by adopting a Monte Carlo simulation method based on the difference value of each preset time point to obtain multiple prediction models.
4. The process of claim 2, wherein fitting a prediction model for each economic situation level from the plurality of prediction models as a target prediction model for the economic situation level comprises:
obtaining sales income threshold values corresponding to different economic situation grades;
and on the basis of sales income threshold values corresponding to the different economic situation grades, one prediction model is adapted to each economic situation grade from the plurality of prediction models to serve as a target prediction model of the economic situation grade.
5. The process of claim 4, wherein obtaining sales revenue thresholds for different economic situational levels comprises:
acquiring preset parameter values corresponding to different economic situation grades;
calculating the average value and the standard deviation of the sales data in the first preset time period;
calculating the average value and standard deviation of the sales data and preset parameter values corresponding to different economic situation grades by adopting a first calculation formula to obtain sales income threshold values corresponding to different economic situation grades,
wherein the first calculation formula: th _ inclusion = Avg _ inclusion + w n *Std_Income；
Th _ Incomer represents the sales revenue threshold for the nth economic situational class, avg _ Incomer represents the average of the sales data, w n A preset parameter value representing the nth economic situational grade, std-inclusion representing the standard deviation of the sales data.
6. The processing method according to claim 4, wherein the step of adapting a prediction model for each economic situational level from the plurality of prediction models as a target prediction model for the economic situational level based on the sales revenue threshold corresponding to the different economic situational levels comprises:
predicting the predicted sales data of the target object at each preset time point in a second preset time period by adopting each prediction model to obtain a predicted data group corresponding to each prediction model;
calculating a similarity value between the prediction data set generated by each prediction model and a sales income threshold value corresponding to each economic situation grade;
reserving m groups of prediction data groups with the highest similarity values for each economic situation grade;
and on the basis of the prediction model corresponding to the prediction data set reserved for each economic situation grade, adapting a prediction model for each economic situation grade to serve as a target prediction model of the economic situation grade.
7. The processing method according to claim 6,
under the condition that each economic situation level reserves a group of prediction data groups with the highest similarity value, a prediction model is adapted to each economic situation level based on a prediction model corresponding to the prediction data group reserved for each economic situation level, and the prediction model is used as a target prediction model of the economic situation level and comprises the following steps: taking the prediction model corresponding to the prediction data set reserved for each economic situation grade as a target prediction model of the economic situation grade;
under the condition that a plurality of groups of prediction data groups with the highest similarity values are reserved at each economic situation level, a prediction model is adapted to each economic situation level on the basis of a prediction model corresponding to the prediction data group reserved at each economic situation level, and the prediction model is used as a target prediction model of the economic situation level and comprises the following steps:
generating m based on the prediction data set retained for each economic situation level i A data combination, wherein each economic situation grade corresponds to one group of prediction data groups in the data combination, and the i represents the total grade number of the economic situation grade;
sequentially detecting the predicted sales data of each preset time point in each data combination, judging whether the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade, and recording an error sequence for the data combination under the condition that the predicted sales data with low economic situation grade is higher than the predicted sales data with high economic situation grade;
reserving n data combinations with the least misordering times;
and on the basis of the prediction model corresponding to each economic situation grade in the reserved data combination, adapting a prediction model for each economic situation grade to serve as a target prediction model of the economic situation grade.
8. The processing method according to claim 7,
under the condition that a data combination with the least misordering times is reserved, a prediction model is adapted to each economic situation grade based on a prediction model corresponding to each economic situation grade in the reserved data combination, and the prediction model is used as a target prediction model of the economic situation grade and comprises the following steps: taking a prediction model corresponding to a prediction data set corresponding to each economic situation grade in the reserved data combination as a target prediction model of the economic situation grade;
under the condition that a plurality of data combinations with the least misordering times are reserved, on the basis of a prediction model corresponding to each economic situation level in the reserved data combinations, a prediction model is adapted to each economic situation level to serve as a target prediction model of the economic situation level, and the method comprises the following steps of:
and sequentially calculating the similarity total value of each reserved data combination, wherein the similarity total value of the data combination is as follows: the sum of similarity values between the prediction data set of each economic situation grade in the data combination and a preset threshold value of the economic situation grade;
and taking the prediction model corresponding to the prediction data group corresponding to each economic situation grade in the data combination with the minimum similar total value as the target prediction model of the economic situation grade.
9. The processing method according to claim 1, wherein determining the sales value of the target object at a target economic situation level and a target preset time point based on the target prediction model comprises:
acquiring a target economic situation grade, a target prediction model corresponding to the target economic situation grade and a target preset time point;
and determining the sales value of the target object at a target preset time point under the target economic situation level by adopting a target prediction model corresponding to the target economic situation level.
10. A data processing apparatus, characterized in that the apparatus comprises:
the acquisition unit is used for acquiring sales data of each preset time point of the target object in a first preset time period;
the building unit is used for building target prediction models under different economic situation grades according to the sales data of each preset time point in the first preset time period, and the target prediction models are used for predicting sales values of different time points;
and the determining unit is used for determining the sales value of the target object at a target time point under a target economic situation grade based on the target prediction model.
11. A data processing apparatus, characterized in that the apparatus comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a data processing method as claimed in any one of claims 1-9.
12. A computer storage medium having computer program instructions stored thereon which, when executed by a processor, implement a data processing method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211661004.5A CN115907217A (en) | 2022-12-22 | 2022-12-22 | Data processing method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211661004.5A CN115907217A (en) | 2022-12-22 | 2022-12-22 | Data processing method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115907217A true CN115907217A (en) | 2023-04-04 |
Family
ID=86472794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211661004.5A Pending CN115907217A (en) | 2022-12-22 | 2022-12-22 | Data processing method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907217A (en) |
-
2022
- 2022-12-22 CN CN202211661004.5A patent/CN115907217A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147456B (en) | Image classification method and device, readable storage medium and terminal equipment | |
| CN108280542B (en) | User portrait model optimization method, medium and equipment | |
| EP3678072A1 (en) | Model integration method and device | |
| CN108829718B (en) | Data processing method and device | |
| CN110930218B (en) | Method and device for identifying fraudulent clients and electronic equipment | |
| CN114662926A (en) | Scientific and technological enterprise evaluation method and device, equipment and medium thereof | |
| CN112085517A (en) | Coupon issuing method and device, electronic equipment and readable storage medium | |
| CN115907217A (en) | Data processing method, device, equipment and computer storage medium | |
| CN112346995B (en) | Banking industry-based test risk prediction model construction method and device | |
| CN114399224A (en) | Data processing method, device, equipment, medium and product | |
| CN114677139A (en) | Method and device for determining loan amount, equipment, product and readable storage medium | |
| CN114298825A (en) | Method and device for extremely evaluating repayment volume | |
| CN113627730A (en) | Enterprise evaluation method, device, equipment and computer storage medium | |
| CN112419025A (en) | User data processing method and device, storage medium and electronic equipment | |
| CN112529303A (en) | Risk prediction method, device, equipment and storage medium based on fuzzy decision | |
| CN111476281B (en) | Information popularity prediction method and device | |
| CN114547101B (en) | Data quality evaluation method, device, equipment and storage medium for data center | |
| CN113297478B (en) | Information pushing method and device based on user life cycle and electronic equipment | |
| CN116703608A (en) | Training method, device, equipment and storage medium for evaluation factor selection model | |
| CN115795259A (en) | User value determination method, device, equipment, medium and product | |
| CN116012125A (en) | Income prediction method, income prediction device, electronic equipment and computer storage medium | |
| CN115659599A (en) | Data processing method and device | |
| CN116911857A (en) | Information processing method, device, equipment, medium and product | |
| CN116739606A (en) | Credit risk prediction model construction method, apparatus, device and storage medium | |
| CN115879959A (en) | Channel complaint risk determination method, device, equipment, medium and product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |