A data processing method, device, apparatus, and storage medium

Abstract

The present disclosure provides a data processing method and device, equipment and storage medium, relating to the technical field of computer. The method mainly comprises: obtaining to-be-processed data, the to-be-processed data comprising historical association data of historical objects and current business data of a target object; calculating a weighted proportion of normal historical objects in the historical objects according to the historical association data; calculating a characteristic value of an influence attribute of the target object according to the historical association data and the current business data; and performing classification processing on the target object according to a classification model, the weighted proportion and the characteristic value to obtain a data processing result.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a data processing method and device, equipment and storage medium. BACKGROUND

[0002] In the big data era, a large amount of data will be generated in various industries. In order to extract more effective information from the data, the data often needs to be classified and processed, so as to manage, analyze or store the data according to the categories of the data. For example, in the e-commerce field, order information is classified into good review orders and bad review orders; in the logistics field, shipping order information is classified into normal shipping orders and risk shipping orders; and in the Internet field, user information is classified into ordinary users and advertising users.

[0003] In the prior art, data is usually classified and processed by manual operation. However, for a large amount of data, this method has a long processing period and wastes a lot of manpower. In addition, the data processing result may be inaccurate due to insufficient experience of the data processing personnel. Furthermore, different processing standards of the data processing personnel may result in non-uniform data processing results. SUMMARY

[0004] The present disclosure provides a data processing method, device, equipment and storage medium to at least solve the above technical problems in the prior art.

[0005] According to a first aspect of the present disclosure, a data processing method is provided, which comprises: obtaining to-be-processed data, the to-be-processed data comprising historical association data of historical objects and current business data of a target object; calculating a weighted proportion of normal historical objects in the historical objects according to the historical association data; calculating a characteristic value of an influence attribute of the target object according to the historical association data and the current business data; and classifying and processing the target object according to a classification model, the weighted proportion and the characteristic value, to obtain a data processing result.

[0006] In an implementation, the calculating of the weighted proportion of the normal historical objects in the historical objects according to the historical association data comprises: calculating a first proportion of the number of normal historical objects in the total number of historical objects in different historical stages according to the historical association data, and calculating a second proportion of the number of failed historical objects in the number of abnormal historical objects; and calculating the weighted proportion of the normal historical objects in the historical objects according to the first proportion and the second proportion. The weighted proportion of the normal historical objects in the historical objects is calculated according to the following formula: Wherein, x is the weighting proportion, A1, A2 and An represent the total number of historical objects in different historical stages respectively, B1, B2 and Bm represent the number of normal historical objects in different historical stages respectively, a, b and g represent the weighting coefficients of different historical stages respectively, C represents the number of abnormal historical objects in the historical objects, and D represents the number of failed historical objects in the historical objects.

[0007] In an implementation, the influence attribute includes a path attribute, and the calculating the characteristic value of the influence attribute of the target object according to the historical correlation data and the current service data includes: calculating a third proportion of the number of normal historical objects corresponding to the path attribute to the total number of historical objects according to the historical correlation data; calculating an average value of the start point index value and the end point index value of the path attribute according to the current service data; calculating a first characteristic value of the path attribute of the target object according to the travel mode index value of the target object, the third proportion and the average value; and calculating the first characteristic value of the path attribute of the target object according to the following formula: Wherein, y is the first characteristic value, E is the total number of historical objects corresponding to the path attribute, F is the number of normal historical objects corresponding to the path attribute, G1 is the start point index value of the path attribute, G2 is the end point index value of the path attribute, H is the travel mode index value, and d, e and e are weighting coefficients respectively.

[0008] In an implementation, the influence attribute includes an environment attribute, and the calculating the characteristic value of the influence attribute of the target object according to the historical correlation data and the current service data includes: calculating a ratio of the duration of the environment attribute to the preset travel time of the target object according to the current service data; calculating a second characteristic value of the environment attribute of the target object according to the ratio, the environment index value corresponding to the environment attribute and the degree parameter corresponding to the environment attribute; and calculating the second characteristic value of the environment attribute of the target object according to the following formula: z = m × t × u × 100, wherein z is the second characteristic value, m is the environment index value, t is the ratio, and u is the degree parameter.

[0009] In an implementation, the classifying the target object according to the classification model, the weighting proportion and the characteristic value to obtain a data processing result includes: calculating a whole index value of the target object according to the weighting proportion, the first characteristic value and the second characteristic value; classifying the target object according to the classification model and the whole index value to obtain the data processing result; and calculating the whole index value of the target object according to the following formula: Q = ax + by - cz, wherein Q is the whole index value, x is the weighting proportion, y is the first characteristic value, z is the second characteristic value, and a, b and c are weight parameters respectively.

[0010] In an implementation, the classification model is a support vector machine model, and the classifying the target object according to the classification model and the overall index value to obtain the data processing result comprises: determining the overall index value and a consumption index value corresponding to the target object as a target vector point; and classifying the target vector point according to the support vector machine model to obtain the data processing result.

[0011] In an implementation, the method further comprises: adjusting the weight parameter according to the weighted proportion, the first feature value and the second feature value to obtain an adjusted weight parameter.

[0012] According to a second aspect of the present disclosure, a data processing apparatus is provided, comprising: an acquisition module configured to acquire to-be-processed data, the to-be-processed data comprising historical correlation data of historical objects and current business data of a target object; a first calculation module configured to calculate a weighted proportion of normal historical objects in the historical objects according to the historical correlation data; a second calculation module configured to calculate a feature value of an influence attribute of the target object according to the historical correlation data and the current business data; and a classifying module configured to classify the target object according to a classification model, the weighted proportion and the feature value to obtain a data processing result.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory connected with the at least one processor; wherein

[0016] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the present disclosure.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to enable the computer to perform the method of the present disclosure.

[0018] The data processing method, device, equipment and storage medium of the present disclosure first acquire the to-be-processed data, the to-be-processed data including the historical association data of the historical object and the current business data of the target object, then calculate the weighted proportion of the normal historical object in the historical object according to the historical association data, and calculate the characteristic value of the influence attribute of the target object according to the historical association data and the current business data, and finally classify the target object according to the classification model, the weighted proportion and the characteristic value to obtain the data processing result. Thus, the weighted proportion of the normal historical object in the historical object associated with the target object and the characteristic value of the influence attribute of the target object are extracted, and the weighted proportion and the characteristic value can accurately represent the characteristics of the target object. Finally, the automatic classification of the target object is realized according to the classification model combined with the weighted proportion and the characteristic value, thereby reducing the human consumption, improving the accuracy of the data processing result, and avoiding the problem that the data processing results are not unified due to different data processing standards of the data processing personnel.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will be more apparent from the following detailed description read in conjunction with the accompanying drawings, in which:

[0021] In the drawings, identical or corresponding reference numerals indicate identical or corresponding parts.

[0022] Figure 1 A flowchart of a data processing method according to a first embodiment of the present disclosure is shown;

[0023] Figure 2 A flowchart of a data processing method according to a third embodiment of the present disclosure is shown;

[0024] Figure 3 A flowchart of a data processing method according to a fifth embodiment of the present disclosure is shown;

[0025] Figure 4 A structural diagram of a data processing device according to an eighth embodiment of the present disclosure is shown;

[0026] Figure 5 A structural diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] In order to make the purposes, characteristics and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0028] Figure 1 A flowchart of a data processing method according to a first embodiment of the present disclosure is shown in FIG. 1, which mainly includes the following steps. Figure 1

[0029] In step S101, the data to be processed is obtained, which includes historical association data of a historical object and current business data of a target object.

[0030] In the present embodiment, the data to be processed is first obtained, which includes historical association data of a historical object and current business data of a target object. The target object is an object that needs to be classified and processed, the historical object is an object associated with the target object and having completed its business processing, the current business data is data related to the current business of the target object, and the historical association data is data related to the business of the historical object.

[0031] ​In an implementable manner, the source of the data to be processed can be various, for example, in the logistics field, the target object can be a target waybill that needs to be classified, the historical object can be a historical waybill associated with the target waybill and having completed a delivery task, the current business data can be cities passed by a delivery path of the target waybill, a delivery mode of the target waybill, and a weather condition of a date of the target waybill, and the historical associated data can be a total number of historical waybills, whether the historical waybills are punctual, whether the historical waybills are delayed, and whether the historical waybills are cancelled due to delay, and the like, wherein, if the historical waybills belong to the same logistics company as the target waybill, the historical waybills can be considered to be associated with the target waybill, or if the historical waybills are of the same type of goods as the target waybill, the historical waybills can be considered to be associated with the target waybill, and the like, and the delivery mode of the target waybill can be air delivery, high-speed rail delivery, road delivery, sea delivery, and the like; in the aviation field, the target object can be a target flight that needs to be classified, the historical object can be a historical flight associated with the target flight and having completed a flight task, the current business data can be cities passed by a flight path of the target flight, a flight time of the target flight, and a weather condition of the flight time of the target flight, and the historical associated data can be a total number of historical flights, whether the historical flights are punctual, whether the historical flights are late, and whether the historical flights are cancelled due to delay, and the like, wherein, if the historical flights belong to the same airline company as the target flight, the historical flights can be considered to be associated with the target flight, or if the historical flights are of the same take-off airport as the target flight, the historical flights can be considered to be associated with the target flight, and the like. It should be emphasized that the source of the data to be processed can be more various than the above.

[0032] In step S102, a weighted proportion of normal historical objects in the historical objects is calculated according to the historical associated data.

[0033] In the embodiment, the weighted proportion of the normal historical objects in the historical objects needs to be calculated according to the historical associated data, wherein the normal historical object is a historical object that has normally completed a business processing matter; according to a time at which the historical object has completed the business processing matter, the historical object can be classified into different historical stages, and a corresponding weight coefficient is added to each historical stage, i.e., a weighting coefficient, and then based on the weighting coefficient, a sum of proportions of the normal historical objects in all historical stages in the historical objects in the historical stage is the weighted proportion.

[0034] In an implementable manner, taking the logistics field as an example, if the historical stages include a current year, a current quarter, and a current month, and the normal historical object is a punctual waybill, the weighted proportion x of the punctual waybills in the historical waybills can be calculated according to the following formula (I) log :

[0035] x log = × R year + × R quarter + × Rmonth , formula (one)

[0036] wherein R year is the proportion of on-time delivery orders in the current year to the total number of historical delivery orders in the current year; R quarter is the proportion of on-time delivery orders in the current quarter to the total number of historical delivery orders in the current quarter; R month is the proportion of on-time delivery orders in the current month to the total number of historical delivery orders in the current month; and a, b and g are the weighting coefficients corresponding to the current year, the current quarter and the current month respectively, which can be set according to actual conditions.

[0037] In an implementation, taking the aviation field as an example, if the historical stage includes the current quarter, the current month and the current week, the normal historical object is an on-time flight, and the weighted proportion x fli of on-time flights in historical flights can be calculated according to formula (two) as follows:

[0038] x fli = aR quarter + bR month + gR week , formula (two)

[0039] wherein R quarter is the proportion of on-time flights in the current quarter to the total number of historical flights in the current quarter; R month is the proportion of on-time flights in the current month to the total number of historical flights in the current month; R week is the proportion of on-time flights in the current week to the total number of historical flights in the current week; and a, b and g are the weighting coefficients corresponding to the current quarter, the current month and the current week respectively, which can be set according to actual conditions.

[0040] Step S103: calculating the characteristic value of the influence attribute of the target object according to the historical correlation data and the current business data.

[0041] In this embodiment, it is also necessary to calculate the feature values ​​of the impact attributes of the target object based on historical correlation data and current business data. The impact attribute is the attribute that affects the classification result of the target object, i.e., the attribute that affects the data processing result corresponding to the target object. The feature value of the impact attribute is used to characterize the degree of influence of the impact attribute on the data processing result of the target object. Taking the logistics field as an example, if the target waybill is a waybill that has not yet been used for its delivery business, and the data processing result characterizes whether the target waybill is a normal waybill, then the impact attribute could be the delivery route of the target waybill and the weather conditions of the delivery date of the target waybill, etc. Taking the aviation field as an example, if the target flight is a flight that has not yet been used for its flight business, and the data processing result characterizes whether the target flight is on time, then the impact attribute could be the cities the target flight's flight path passes through and the weather conditions of the flight time of the target flight, etc.

[0042] In one possible implementation, taking the logistics field as an example, if the influencing attribute is the delivery route of the target waybill, and the starting city of the delivery route is J and the ending city is K, then the characteristic value y of the influencing attribute of the target object can be calculated according to the following formula (iii). log :

[0043]

[0044] Where ε is the weighting coefficient of the influencing attribute, and ε can be set according to the actual situation; G J The index value is for city J, the starting point; G K G represents the index value for the destination city K. J and G K The rules can be set according to the actual situation. Preferably, the indicator values ​​can be set to decrease sequentially for first-tier cities, second-tier cities, third-tier cities, fourth-tier cities, and towns.

[0045] In one possible implementation, taking the aviation field as an example, if the influencing attribute is the weather conditions during the flight time of the target flight, and the weather conditions are rain, then the characteristic value z of the influencing attribute of the target object can be calculated according to the following formula (iv). fli :

[0046] z fli =×m rain Formula (IV)

[0047] Where t is the ratio of the duration of the rain to the estimated flight time of the target flight, and m rain The index value corresponding to rain, m rain The weather condition index value can be set according to the actual situation. Preferably, the setting rule for the weather condition index value is that the more favorable the weather conditions are for flight, the smaller the corresponding index value.

[0048] In step S104, the target object is classified according to the classification model, the weighted proportion and the feature value, and a data processing result is obtained.

[0049] In this embodiment, the calculated weighted proportion and feature value are input into the classification model, the target object is classified by the classification model, and a data processing result is obtained. Since the weighted proportion and feature value can accurately represent the characteristics of the target object, the accuracy of the final data processing result can be improved.

[0050] In an implementation manner, the classification model can be a decision tree (DT) model, a support vector machine (SVM) model, a random forest (RF) model, a gradient boosting decision tree (GBDT) model, etc.

[0051] In the first embodiment of the present disclosure, the weighted proportion of the normal historical object in the historical objects associated with the target object is extracted, and the feature value of the influence attribute of the target object. The weighted proportion and the feature value can accurately represent the characteristics of the target object. Finally, the classification model is combined with the weighted proportion and the feature value to realize the automatic classification of the target object, thereby reducing the labor consumption, improving the accuracy of the data processing result, and avoiding the problem that the data processing results are not unified due to different data processing standards of data processing personnel.

[0052] In the second embodiment of the present disclosure, step S102 mainly includes:

[0053] According to the historical association data, a first proportion of the number of normal historical objects in the total number of historical objects in different historical stages is calculated, and a second proportion of the number of failed historical objects in the number of abnormal historical objects is calculated. According to the first proportion and the second proportion, the weighted proportion of the normal historical objects in the historical objects is calculated.

[0054] In this embodiment, first, according to the historical association data, the first proportion of the number of normal historical objects in the total number of historical objects in different historical stages is calculated, and the second proportion of the number of failed historical objects in the number of abnormal historical objects is calculated. Then, according to the first proportion and the second proportion, the weighted proportion of the normal historical objects in the historical objects is calculated. Specifically, the normal historical object is a historical object that has completed a business processing matter; the failed historical object is a historical object that has not completed a business processing matter; and the abnormal historical object is a historical object that has completed a business processing matter but does not meet the requirements of the business processing matter.

[0055] In an implementation manner, the weighted proportion of the normal historical object in the historical objects can be calculated according to the following formula (five):

[0056]

[0057] wherein x is a weighted proportion, A1, A2 and An represent the total number of historical objects in different historical stages respectively, B1, B2 and Bn represent the number of normal historical objects in different historical stages respectively, a, b and g represent the weighting coefficients of different historical stages respectively, a, b and g can be set by oneself according to actual conditions, C represents the number of abnormal historical objects in the historical objects, and D represents the number of failed historical objects in the historical objects. Specifically, the first proportion in the formula (five) is that is, the first proportion of the number of normal historical objects in the first historical stage to the total number of historical objects in the first historical stage; that is, the first proportion of the number of normal historical objects in the second historical stage to the total number of historical objects in the second historical stage; that is, the first proportion of the number of normal historical objects in the nth historical stage to the total number of historical objects in the nth historical stage; that is, the second proportion of the number of all failed historical objects in the to-be-processed data to the number of all abnormal historical objects in the to-be-processed data.

[0058] In an implementable manner, taking the logistics field as an example, if the normal historical object is a normal waybill that normally completes a business processing matter, the failed historical object is a failed waybill that is returned because of delay, the abnormal historical object is a delayed waybill that is delayed to arrive, and all historical objects in the to-be-processed data are divided into three historical stages, which are an overall historical stage corresponding to all historical objects, a current quarter and a current month, then the first proportion in the formula (five) is that is, the first proportion of the number of all normal waybills in the to-be-processed data to the number of all historical waybills in the to-be-processed data; that is, the first proportion of the number of normal waybills in the current quarter to the total number of historical waybills in the current quarter; that is, the first proportion of the number of normal waybills in the current month to the total number of historical waybills in the current month; that is, the second proportion of the number of all failed waybills in the to-be-processed data to the number of all delayed waybills in the to-be-processed data, preferably, a, b and g in the formula (five) can be 15%, 25% and 60% respectively.

[0059] In an implementable manner, taking the aviation field as an example, if the normal historical object is a normal flight that normally completes a business processing matter, the failed historical object is a failed flight that is cancelled because of delay, the abnormal historical object is a delayed flight that is delayed to arrive, and all historical objects in the to-be-processed data are divided into three historical stages, which are a current quarter, a current month and a current week, then the first proportion in the formula (five) is that is, the first proportion of the number of normal flights in the current quarter to the total number of historical flights in the current quarter; i.e. the first proportion of the number of normal flights in the current month to the total number of historical flights in the current month; i.e. the first proportion of the number of normal flights in the current week to the total number of historical flights in the current week; i.e. the second proportion of the number of failed flights in the to-be-processed data to the number of delayed flights in the to-be-processed data, preferably, a, β and γ in formula (five) can be 15%, 25% and 60% respectively.

[0060] In the second embodiment of the present disclosure, when calculating the weighted proportion of normal historical objects in the historical objects, the first proportion of the number of normal historical objects in different historical stages to the total number of historical objects and the second proportion of the number of failed historical objects to the number of abnormal historical objects are combined, not only the proportion of normal historical objects is considered, but also the number of failed historical objects and the number of abnormal historical objects are considered, so that the final weighted proportion can fully and accurately reflect the completion of the business processing matters of the historical objects, thereby further improving the accuracy of the data processing result.

[0061] Figure 2 Fig. 2 shows a flowchart of a data processing method according to a third embodiment of the present disclosure, and Figure 2 As shown in Fig. 2, the influence attribute includes a path attribute, and step S103 mainly includes:

[0062] Step S201: calculating, according to historical correlation data, a third proportion of the number of normal historical objects corresponding to the path attribute to the total number of historical objects.

[0063] In the present embodiment, first, according to the historical correlation data, a third proportion of the number of normal historical objects corresponding to the path attribute to the total number of historical objects corresponding to the path attribute is calculated, wherein the path attribute is a path that the target object needs to pass through to complete its corresponding business processing matter. Taking the logistics field as an example, the path attribute can be a route that a target waybill needs to pass through, for example, the path attribute of a target waybill can be Beijing-Guangdong, and the third proportion is the proportion of the number of normal historical waybills with the path attribute of Beijing-Guangdong to the total number of historical waybills with the path attribute of Beijing-Guangdong. Taking the aviation field as an example, the path attribute can be a route that a target flight needs to pass through, for example, the path attribute of a target flight can be Shanghai-Tianjin, and the third proportion is the proportion of the number of normal historical flights with the path attribute of Shanghai-Tianjin to the total number of historical flights with the path attribute of Shanghai-Tianjin.

[0064] Step S202: calculating, according to current business data, an average value of the start point index value and the end point index value of the path attribute.

[0065] In the embodiment, the average value of the start point indicator value and the end point indicator value of the path attribute is also calculated according to the current business data. Taking the logistics field as an example, the start point indicator value can be the indicator value of the start city in the target waybill route; the end point indicator value can be the indicator value of the end city in the target waybill route. Taking the aviation field as an example, the start point indicator value can be the indicator value of the departure airport in the target flight route, and the end point indicator value can be the indicator value of the landing airport in the target flight route.

[0066] In an implementable manner, in the logistics field, the indicator value of a city can be shown in Table 1 as follows:

[0067] Table 1

[0068] First-tier city Second-tier city Third-tier city Fourth-tier city Township 100 90 80 70 60

[0069] In the aviation field, the indicator value of an airport can also be set according to actual conditions, and the setting rule can be that the larger the proportion of normal flights corresponding to the airport in all historical flights corresponding to the airport, the larger the indicator value of the airport.

[0070] In step S203, the first feature value of the path attribute of the target object is calculated according to the travel mode indicator value of the target object, the third proportion, and the average value.

[0071] In the embodiment, the first feature value of the path attribute of the target object is calculated according to the travel mode indicator value of the target object, the third proportion of the number of normal historical objects corresponding to the path attribute in the total number of historical objects, and the average value of the start point indicator value and the end point indicator value of the path attribute, wherein the travel mode of the target object is the mode of the target object from the start point of the path to the end point of the path. Taking the logistics field as an example, the travel mode of the target object can be shipping, high-speed rail transportation, road transportation, and sea transportation, etc. Taking the aviation field as an example, the travel mode of the target object can be direct and stopover, etc.

[0072] In an implementable manner, in the logistics field, the travel mode indicator value of the target object can be shown in Table 2 as follows:

[0073] Table 2

[0074] Shipping High-speed rail transport Road transport Marine transport 100 90 80 70

[0075] In the aviation field, the travel mode indicator value of the target object can be set according to actual conditions, and the setting rule can be that the indicator value of direct is larger than the indicator value of stopover.

[0076] In an implementable manner, the first feature value of the path attribute of the target object is calculated according to the following formula (six):

[0077]

[0078] wherein y is the first characteristic value of the path attribute, E is the total number of historical objects corresponding to the path attribute, F is the number of normal historical objects corresponding to the path attribute, i.e. the third proportion of the number of normal historical objects corresponding to the path attribute to the total number of historical objects; G1 is the start point index value of the path attribute, and G2 is the end point index value of the path attribute, i.e. the average of the start point index value and the end point index value of the path attribute; H is the travel mode index value, and δ, σ and ∈ are weighting coefficients, preferably, δ, σ and ∈ can be 40%, 40% and 20% respectively.

[0079] In the third embodiment of the present disclosure, the path attribute is taken as the influence attribute, and the first characteristic value of the path attribute of the target object is calculated according to the historical association data and the current business data, the first characteristic value representing the influence degree of the path attribute on the data processing result of the target object, and subsequently, the target object is classified according to the first characteristic value, which can improve the accuracy of the data processing result.

[0080] In the fourth embodiment of the present disclosure, the influence attribute includes the environment attribute, and step S103 further includes:

[0081] According to the current business data, the ratio of the duration of the environment attribute to the preset travel time of the target object is calculated; and according to the ratio, the environment index value corresponding to the environment attribute and the degree parameter corresponding to the environment attribute, the second characteristic value of the environment attribute of the target object is calculated.

[0082] In the present embodiment, firstly, the ratio of the duration of the environment attribute to the preset travel time of the target object is calculated according to the current business data, and then the second characteristic value of the environment attribute of the target object is calculated according to the ratio, the environment index value corresponding to the environment attribute and the degree parameter corresponding to the environment attribute. Specifically, the environment attribute is the weather condition of the day when the target object performs the corresponding business processing matter, and the environment attribute can be sunny, rainy, snowy and foggy, etc., the duration of the environment attribute is the duration of the weather condition; the preset travel time of the target object is the duration required by the target object to complete the business processing matter; the environment index value corresponding to the environment attribute is the index value corresponding to the environment attribute; and the degree parameter corresponding to the environment attribute is a parameter corresponding to the degree of the environment attribute, for example, if the weather condition of the day when the target object performs the corresponding business processing matter is heavy rain, the environment attribute is rain, and the degree parameter of the environment attribute is a parameter corresponding to “heavy”.

[0083] In an implementable manner, in the fields of logistics and aviation, the environment index value corresponding to the environment attribute can be as shown in Table Three:

[0084] Table Three

[0085] Sunny Rain Snow Fog 0 60 80 100

[0086] The degree parameters of the environmental attribute can be shown in Table Four as follows:

[0087] Table Four

[0088] Small Medium Large 20％ 40％ 60％

[0089] In an implementable manner, the second characteristic value of the environmental attribute of the target object can be calculated according to the following formula (Seven):

[0090] z = m x t x u x 100, formula (Seven)

[0091] wherein z is the second characteristic value, m is the environmental index value, t is the ratio, and u is the degree parameter. It is emphasized that if the path attribute of the target object passes through multiple cities, multiple characteristic values corresponding to the environmental attributes of the multiple cities can be calculated respectively, and then the average value of the multiple characteristic values is taken as the second characteristic value.

[0092] In the fourth embodiment of the present disclosure, the environmental attribute is taken as the influence attribute, and the second characteristic value of the environmental attribute of the target object is calculated according to the current business data, the second characteristic value representing the influence degree of the environmental attribute on the data processing result of the target object, and subsequent classification of the target object according to the second characteristic value can improve the accuracy of the data processing result.

[0093] Figure 3 A flowchart of a data processing method according to the fifth embodiment of the present disclosure is shown in FIG. 5. As shown in FIG. 5, step S104 mainly includes: Figure 3

[0094] Step S301, calculating the overall index value of the target object according to the weighted proportion, the first characteristic value and the second characteristic value.

[0095] In the present embodiment, the overall index value of the target object is first calculated according to the weighted proportion, the first characteristic value and the second characteristic value, and the overall index value is used to represent the overall characteristics of the target object.

[0096] In an implementable manner, the overall index value of the target object can be calculated according to the following formula (Eight):

[0097] Q = ax + by - cz, formula (Eight)

[0098] wherein Q is the overall index value, x is the weighted proportion, y is the first characteristic value, z is the second characteristic value, a, b and c are weight parameters respectively, a, b and c can be set according to actual conditions, and preferably a, b and c can be 0.4, 0.6 and 1 respectively.

[0099] Step S302, classifying the target object according to the classification model and the overall index value to obtain a data processing result.​

[0100] In this embodiment, the overall index value is input into the classification model, which then classifies the target object based on the overall index value to obtain the data processing result.

[0101] In the sixth embodiment of this disclosure, the classification model is a support vector machine model, and step S302 mainly includes:

[0102] The overall index value and the consumption index value corresponding to the target object are determined as the target vector points; the target vector points are classified according to the support vector machine model to obtain the data processing results.

[0103] In this embodiment, the overall index value and the consumption index value corresponding to the target object are first determined as the target vector point. The consumption index value is the index value corresponding to the material consumption required by the target object to complete its business processing. Taking the logistics field as an example, the consumption index value can be the freight of the target waybill; taking the aviation field as an example, the consumption index value can be the ticket price of the target flight. Then, the target vector point is classified according to the support vector machine model to obtain the data processing result.

[0104] In one possible implementation, the support vector machine model can be trained as follows: First, training data is acquired, which can be X = {X1, X2, ..., X...} n In this context, X1 is a vector point composed of the overall index value q1 and its consumption index value p1 of the first historical object, which can be represented as (q1, p1). X2 is a vector point composed of the overall index value q2 and its consumption index value p2 of the second historical object, which can be represented as (q2, p2), and so on. Furthermore, the training data can be labeled into two categories, such as normal historical objects and abnormal historical objects, depending on the actual situation. Then, the training data is input into the support vector machine model for training, yielding the optimal linear equation ω for the support vector machine to partition the training data. T X i +=0, where ω is the normal vector, X i Let b be the vector point corresponding to different historical objects, and let b be the displacement, thus determining the trained support vector machine model.

[0105] In one possible implementation, the process of inputting training data into a support vector machine model for training is as follows: the straight line formed by all vector points in the training data X can be represented by the formula ω. T X i The plus sign is used to represent the value of the formula, and the value of the formula is represented by Y = {Y1, Y2, ..., Y}. n} indicates that, assuming there exists a straight line (hyperplane) such that ω T X i+=0, all vector points are classified according to the straight line and formula (IX):

[0106]

[0107] wherein Y i is the value corresponding to X i , then among all hyperplanes that can correctly classify all vector points, the hyperplane that satisfies the maximum margin is found: and a Lagrange multiplier a i is introduced for each constraint, and the following formula (X) is obtained:

[0108]

[0109] wherein L represents the Lagrange function, and a can be calculated according to formula (X). The support vector set is composed of all X i for which a k is not equal to 0. The value of b can be calculated from any element (X k , Y k ) in the support vector set, and thus the best linear equation of the support vector machine for classifying the training data is obtained, wherein X k is the support vector, and Y i is the value corresponding to the support vector. In the training process, the decision boundary can be Y T (ω i X +)≥1.

[0110] In an implementation, taking the logistics field as an example, if the target waybill belongs to a waybill that has not yet performed its delivery service, and the data processing result represents whether the target waybill is a normal waybill, then according to the completion of the historical waybills, the training data is labeled as normal waybills and abnormal waybills, and the normal waybills can be represented by 1 and the abnormal waybills can be represented by -1. Finally, according to the support vector machine model, the target vector point of the target waybill is classified and processed, and the data processing result obtained can represent whether the target waybill is a normal waybill. Then, the business personnel can manage the target waybill according to the data processing result, for example, analyze whether the target waybill should be received for delivery service, or analyze whether the target waybill should be financed, etc. It should be emphasized that the data processing method of the present disclosure can be used as a waybill risk assessment method when applied in the logistics field.

[0111] In an implementable manner, taking the aviation field as an example, if the target flight belongs to a flight that has not yet carried out its flight operation, and the data processing result represents whether the target flight is a late flight, the training data is labeled as an on-time flight and a late flight according to the completion of the historical flights, the on-time flight can be represented by 1, and the late flight can be represented by -1, and finally the target vector point of the target flight is classified by the support vector machine model, and the data processing result obtained can represent whether the target flight is a late flight, and then the business personnel can manage the target flight according to the data processing result, for example, analyze whether the target flight should be selected for travel. It should be emphasized that the data processing method of the present disclosure can be used as a flight risk assessment method when applied in the aviation field.

[0112] In the fifth and sixth embodiments of the present disclosure, first, the overall index value of the target object is calculated according to the weighted proportion, the first characteristic value and the second characteristic value, and then the target object is classified according to the support vector machine model, the overall index value and the consumption index value corresponding to the target object, to obtain the data processing result, which can ensure the visualization of the data processing result and improve the accuracy of the data processing result.

[0113] In the seventh embodiment of the present disclosure, the data processing method further comprises:

[0114] The weight parameter is adjusted according to the weighted proportion, the first characteristic value and the second characteristic value to obtain an adjusted weight parameter.

[0115] In the present embodiment, the weight parameter is adjusted according to the weighted proportion, the first characteristic value and the second characteristic value, that is, a, b and c in formula (8) can be adjusted according to the weighted proportion, the first characteristic value and the second characteristic value to obtain an adjusted weight parameter, and the overall index value of the target object can be calculated according to the adjusted weight parameter subsequently.

[0116] In an implementable manner, the adjustment rule for adjusting the weight parameter can be: if the weighted proportion is greater than a first preset threshold, the value of the weight parameter a is reduced; if the first characteristic value is greater than a second preset threshold, the value of the weight parameter b is reduced; and if in the actual situation, the second characteristic value corresponds to more non-sunny weather conditions in the environmental attribute, the value of the weight parameter c is reduced. In this way, the influence of the weighted proportion, the path factor and the environmental factor on the data processing result can be appropriately weakened, and the accuracy of the data processing result can be improved.

[0117] In the seventh embodiment of the present disclosure, the weight parameter is adjusted according to the weighted proportion, the first characteristic value and the second characteristic value to obtain an adjusted weight parameter, and the overall index value of the target object is calculated according to the adjusted weight parameter subsequently, which can improve the accuracy of the overall index value and further improve the accuracy of the data processing result.

[0118] Figure 4 Fig. 8 shows a structural schematic diagram of a data processing apparatus according to an eighth embodiment of the present disclosure, which mainly comprises: Figure 4

[0119] The data processing apparatus comprises: an acquisition module 10, configured to acquire to-be-processed data, the to-be-processed data comprising historical correlation data of historical objects and current business data of a target object; a first calculation module 11, configured to calculate a weighted proportion of normal historical objects in the historical objects according to the historical correlation data; a second calculation module 12, configured to calculate a characteristic value of an influence attribute of the target object according to the historical correlation data and the current business data; and a classification processing module 13, configured to perform classification processing on the target object according to a classification model, the weighted proportion and the characteristic value, to obtain a data processing result.

[0120] In an implementation, the first calculation module 11 comprises: a first calculation submodule, configured to calculate a first proportion of a number of normal historical objects in a total number of historical objects in different historical stages according to the historical correlation data, and calculate a second proportion of a number of failed historical objects in a number of abnormal historical objects; and a second calculation submodule, configured to calculate the weighted proportion of the normal historical objects in the historical objects according to the first proportion and the second proportion, and calculate the weighted proportion of the normal historical objects in the historical objects according to the following formula: wherein x is the weighted proportion, A1, A2 and An represent the total number of historical objects in different historical stages respectively, B1, B2 and Bn represent the number of normal historical objects in different historical stages respectively, a, β and γ represent weighting coefficients of different historical stages respectively, C represents the number of abnormal historical objects in the historical objects, and D represents the number of failed historical objects in the historical objects.

[0121] In an implementation, the influence attribute comprises a path attribute, and the second calculation module 12 comprises: a third calculation submodule, configured to calculate a third proportion of a number of normal historical objects corresponding to the path attribute in the total number of historical objects according to the historical correlation data; a fourth calculation submodule, configured to calculate an average value of a start point index value and an end point index value of the path attribute according to the current business data; and a fifth calculation submodule, configured to calculate a first characteristic value of the path attribute of the target object according to a travel mode index value of the target object, the third proportion and the average value, and calculate the first characteristic value of the path attribute of the target object according to the following formula: wherein y is the first characteristic value, E is the total number of historical objects corresponding to the path attribute, F is the number of normal historical objects corresponding to the path attribute, G1 is the start point index value of the path attribute, G2 is the end point index value of the path attribute, H is the travel mode index value, and a, β and γ are weighting coefficients respectively.

[0122] ​In an implementable manner, the influence attribute comprises an environmental attribute, and the second calculation module 12 comprises: a sixth calculation submodule, configured to calculate a ratio of a duration of the environmental attribute to a preset travel time of the target object according to the current service data; and a seventh calculation submodule, configured to calculate a second characteristic value of the environmental attribute of the target object according to the ratio, an environmental index value corresponding to the environmental attribute, and a degree parameter corresponding to the environmental attribute; and the seventh calculation submodule is further configured to calculate the second characteristic value of the environmental attribute of the target object according to the following formula: z = m × t × u × 100, wherein z is the second characteristic value, m is the environmental index value, t is the ratio, and u is the degree parameter.

[0123] In an implementable manner, the classification processing module 13 comprises: an eighth calculation submodule, configured to calculate an overall index value of the target object according to the weighted proportion, the first characteristic value, and the second characteristic value; and a classification processing submodule, configured to perform classification processing on the target object according to the classification model and the overall index value to obtain the data processing result; and the eighth calculation submodule is further configured to calculate the overall index value of the target object according to the following formula: Q = ax + by - cz, wherein Q is the overall index value, x is the weighted proportion, y is the first characteristic value, z is the second characteristic value, and a, b, and c are weight parameters respectively.

[0124] In an implementable manner, the classification model is a support vector machine model, and the classification processing submodule comprises: a determination unit, configured to determine the overall index value and a consumption index value corresponding to the target object as a target vector point; and a classification unit, configured to perform classification processing on the target vector point according to the support vector machine model to obtain the data processing result.

[0125] In an implementable manner, the data processing apparatus further comprises: an adjustment module, configured to adjust the weight parameters according to the weighted proportion, the first characteristic value, and the second characteristic value to obtain adjusted weight parameters.

[0126] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device and a readable storage medium.

[0127] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0128] AsFigure 5 As shown, the device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0129] A plurality of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; the storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0130] The computing unit 501 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as a data processing method. For example, in some embodiments, a data processing method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of a data processing method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform a data processing method by any other appropriate means, such as by means of firmware.

[0131] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0132] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0133] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0135] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0136] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server is generally established by computer programs running on the respective computers and having a client-server relationship to each other. The servers can be cloud servers, servers of a distributed system, or servers combined with a blockchain.

[0137] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, in series, or in a different order, without departing from the desired results of the technology disclosed herein, which are not limited herein.

[0138] In addition, the terms "first", "second", etc., are used herein only to describe different instances, and do not imply or suggest relative importance or a number of the indicated technical features. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0139] The above merely provides the specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present disclosure, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A data processing method, characterized in that, The method includes: Acquire the data to be processed, which includes historical association data of historical objects and current business data of the target object; Based on the historical correlation data, calculate the first proportion of the number of normal historical objects to the total number of historical objects in different historical stages, and the second proportion of the number of historical objects that failed to be calculated to the number of abnormal historical objects. Calculate the weighted ratio of normal historical objects in the historical objects based on the first ratio and the second ratio; Based on the historical correlation data and the current business data, calculate the feature value of the impact attribute of the target object; The target object is classified according to the classification model, the weighting ratio, and the feature value to obtain the data processing result.

2. The method according to claim 1, characterized in that, The calculation of the weighting ratio of normal historical objects in the historical objects includes: The weighting ratio of normal historical objects in the historical objects is calculated using the following formula: ， in, The weighting ratio is... , and These represent the total number of historical objects in different historical periods. , and These represent the number of normal historical objects in different historical stages. , and These represent the weighting coefficients for different historical periods. This represents the number of abnormal historical objects in the historical object list. This represents the number of failed historical objects in the historical object set.

3. The method according to claim 1, characterized in that, The impact attributes include path attributes. The step of calculating the feature values ​​of the impact attributes of the target object based on the historical association data and the current business data includes: Based on the historical association data, calculate the third proportion of the number of normal historical objects corresponding to the path attribute to the total number of historical objects; Based on the current business data, calculate the average value of the starting point index value and the ending point index value of the path attribute; Based on the target object's travel mode index value, the third ratio, and the average value, calculate the first feature value of the target object's path attribute; The first feature value of the path attribute of the target object is calculated according to the following formula: ， in, The first feature value, This represents the total number of historical objects corresponding to the path attribute. The number of normal historical objects corresponding to the path attribute. This is the starting point index value for the path attribute. This represents the endpoint indicator value of the path attribute. This is the value of the travel mode indicator. , and These are the weighting coefficients.

4. The method according to claim 3, characterized in that, The influencing attributes include environmental attributes. The step of calculating the feature values ​​of the influencing attributes of the target object based on the historical correlation data and the current business data includes: Based on the current business data, calculate the ratio of the duration of the environmental attribute to the preset travel time of the target object; Based on the ratio, the environmental index value corresponding to the environmental attribute, and the degree parameter corresponding to the environmental attribute, calculate the second characteristic value of the environmental attribute of the target object; The second characteristic value of the environmental attribute of the target object is calculated according to the following formula: ， in, The second eigenvalue, The environmental index value, The ratio is... The degree parameter is as described.

5. The method according to claim 4, characterized in that, The step of classifying the target object according to the classification model, the weighting ratio, and the feature value to obtain the data processing result includes: Calculate the overall index value of the target object based on the weighting ratio, the first feature value, and the second feature value; Based on the classification model and the overall index value, the target object is classified to obtain the data processing result; The overall index value of the target object is calculated according to the following formula: ， in, The overall index value, The weighting ratio is... Let z be the first eigenvalue and z be the second eigenvalue. , , These are the weight parameters.

6. The method according to claim 5, characterized in that, The classification model is a support vector machine model. The process of classifying the target object based on the classification model and the overall index value to obtain the data processing result includes: The overall indicator value and the consumption indicator value corresponding to the target object are determined as the target vector point; Based on the support vector machine model, the target vector points are classified to obtain the data processing results.

7. The method according to claim 5, characterized in that, The method further includes: The weighting parameters are adjusted based on the weighting ratio, the first feature value, and the second feature value to obtain the adjusted weighting parameters.

8. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire data to be processed, which includes historical association data of historical objects and current business data of target objects; The first calculation module is used to calculate the weighting ratio of normal historical objects in the historical objects based on the historical association data. The second calculation module is used to calculate the feature value of the influence attribute of the target object based on the historical correlation data and the current business data; The classification processing module is used to classify the target object according to the classification model, the weighting ratio, and the feature value to obtain the data processing result; The first calculation module includes: a first calculation submodule, configured to calculate, based on the historical association data, a first ratio of the number of normal historical objects to the total number of historical objects in different historical stages, and a second ratio of the number of historical objects that failed to be calculated to the number of abnormal historical objects; and to calculate, based on the first ratio and the second ratio, a weighted ratio of normal historical objects among the historical objects.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images