CN114897588A - Order management method and device based on data analysis - Google Patents
Order management method and device based on data analysis Download PDFInfo
- Publication number
- CN114897588A CN114897588A CN202210814718.9A CN202210814718A CN114897588A CN 114897588 A CN114897588 A CN 114897588A CN 202210814718 A CN202210814718 A CN 202210814718A CN 114897588 A CN114897588 A CN 114897588A
- Authority
- CN
- China
- Prior art keywords
- data
- order
- orders
- value
- classification
- 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.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 27
- 238000007726 management method Methods 0.000 title claims abstract description 27
- 238000012886 linear function Methods 0.000 claims abstract description 95
- 238000013507 mapping Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000010606 normalization Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 62
- 230000009466 transformation Effects 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000010187 selection method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 abstract description 10
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an order management method and device based on data analysis, wherein the method comprises the following steps: the method comprises the steps of obtaining order data packets to be classified of a designated department, carrying out feature extraction on the order data packets, carrying out space mapping to obtain target orders corresponding to all data orders, and setting a plurality of normalization linear functions for classification by using a target order setting linear classifier. The invention has the beneficial effects that: the data order classification for the designated department is realized, secondary classification of the data order is not needed, the processing efficiency of the data order is improved, and the delivery efficiency of the commodity is improved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an order management method and device based on data analysis.
Background
With the development of science and technology, online shopping gradually becomes a main mode for people to purchase commodities, in the prior art, a user places an order through an APP to form a data order, and then sends each data order to a corresponding department through a distribution center for receiving the order, and the data order is processed by the corresponding department.
Disclosure of Invention
The invention mainly aims to provide an order management method and device based on data analysis, and aims to solve the problem that the order processing efficiency is low due to the fact that data orders need to be classified secondarily.
The invention provides an order management method based on data analysis, which comprises the following steps:
obtaining order data packets to be classified based on an instruction of obtaining the order data packets by a specified department; the order data packet comprises a plurality of data orders;
performing feature extraction on each data order to obtain a multi-dimensional feature representation of each data order;
selecting a corresponding kernel function according to a preset selection method to perform space mapping on each data order to obtain a corresponding target order after each data order is mapped;
obtaining a classification standard of a designated department, and setting a plurality of normalization linear functions by adopting a preset linear classifier according to the classification standard
(ii) a Wherein,
and is and
，
a constant associated with the classification criteria is represented,
representing an offset, t being a positive integer, w representing a weight vector having the same dimensions as the target order,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
calculating the Euclidean distance between each normalized linear function and each target order, extracting the maximum Euclidean distance and the minimum Euclidean distance of each normalized linear function, and subtracting the minimum Euclidean distance from the maximum Euclidean distance to be used as the information distance of the corresponding normalized linear function;
according to the formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function of (2);
judging the transformation parameters
Whether the current is within a preset range;
and if the data order is in the preset range, classifying the data order in the order data packet based on each normalized linear function, and sending a classification result to the designated department.
Further, the determining the transformation parameter
After the step of determining whether the current time is within the preset range, the method further comprises the following steps:
if the conversion parameters are not in the preset range, adjusting the weight vectors in the normalized linear functions until the conversion parameters are in the preset range to obtain target linear functions corresponding to the normalized linear functions;
and classifying the data orders in the order data packet based on each target linear function, and sending classification results to the designated department.
Further, the step of selecting a corresponding kernel function according to a preset selection method to perform spatial mapping on each data order to obtain a corresponding target order after each data order is mapped includes:
according to the formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic is shown, n is the number of the data orders, the dimension characteristic is one of the multi-dimension characteristics,
a value corresponding to the ith dimensional characteristic representing the jth data order,
and
respectively representing the minimum value and the maximum value of the ith dimension characteristic in the order data packet;
inputting the information value of the dimension characteristic and the information of the designated department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
and performing space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
Further, before the step of performing feature extraction on each data order to obtain a multidimensional feature representation of each data order, the method further includes:
judging whether the order data packet has a data order belonging to the same template;
if so, folding the data orders belonging to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
Further, after the step of classifying the data orders in the order data packets based on the normalized linear functions and sending the classification results to the designated department if the data orders are within the preset range, the method further includes:
acquiring a time limit characteristic value of each data order;
sorting the data orders in each classification category based on the time limit characteristic value of each data order;
and issuing tasks to all the working posts according to the sequenced data orders so as to sequentially deliver the products on all the data orders.
The invention also provides an order management device based on data analysis, which comprises:
the data order acquisition module is used for acquiring order data packets to be classified based on an instruction of acquiring the order data packets by a specified department; wherein the order data packet comprises a plurality of data orders;
the characteristic extraction module is used for extracting the characteristics of each data order to obtain the multidimensional characteristic representation of each data order;
the data order mapping module is used for selecting a corresponding kernel function according to a preset selection method to perform space mapping on each data order to obtain a corresponding target order after each data order is mapped;
a function setting module for obtaining the classification standard of the appointed department and setting multiple normalization linear functions by adopting a preset linear classifier according to the classification standard
(ii) a Wherein,
and is and
，
a constant associated with the classification criteria is represented,
representing an offset, t being a positive integer, w representing a weight vector having the same dimensions as the target order,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
the Euclidean distance calculation module is used for calculating the Euclidean distance between each normalized linear function and each target order, extracting the maximum Euclidean distance and the minimum Euclidean distance of each normalized linear function, and subtracting the minimum Euclidean distance from the maximum Euclidean distance to be used as the information distance of the corresponding normalized linear function;
a transformation parameter calculation module for calculating a transformation parameter according to a formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function of (2);
a conversion parameter judgment module for judging the conversion parameter
Whether the current is within a preset range;
and the data order classification module is used for classifying the data orders in the order data packet based on each normalized linear function and sending the classification result to the designated department if the data orders are in a preset range.
Further, the order management apparatus based on data analysis further includes:
the adjusting module is used for adjusting the weight vector in the normalized linear function if the weight vector is not in a preset range until the transformation parameter is in the preset range to obtain a target linear function corresponding to each normalized linear function;
and the classification module is used for classifying the data orders in the order data packet based on each target linear function and sending the classification result to the designated department.
Further, the data order mapping module includes:
an information value calculating operator module for calculating the value of the information value according to a formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic is shown, n is the number of the data orders, the dimension characteristic is one of the multi-dimension characteristics,
a value corresponding to the ith dimension characteristic of the jth data order is shown,
and
respectively representing the minimum value and the maximum value of the ith dimension characteristic in the order data packet;
the input submodule is used for inputting the information value of the dimension characteristic and the information of the designated department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
and the mapping submodule is used for carrying out space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
Further, the order management apparatus based on data analysis further includes:
the data order judging module is used for judging whether the order data packet has data orders belonging to the same template;
and the folding module is used for folding the data orders belonging to the same template if the data orders belong to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
Further, the order management apparatus based on data analysis further includes:
the time limit characteristic value acquisition module is used for acquiring the time limit characteristic value of each data order;
the sorting module is used for sorting the data orders in each classification category based on the time limit characteristic value of each data order;
and the ex-warehouse module is used for issuing tasks to all the working posts according to the sequenced data orders so as to sequentially ex-warehouse the products on all the data orders.
The invention has the beneficial effects that: the data order classification of the appointed department is realized by acquiring the order data packet to be classified of the appointed department, performing feature extraction on the order data packet, performing space mapping to obtain a target order corresponding to each data order, and setting a plurality of normalized linear functions for classification by using a target order setting linear classifier, so that secondary classification of the data order is not needed, the processing efficiency of the data order is improved, and the ex-warehouse efficiency of the commodity is improved.
Drawings
FIG. 1 is a flow chart of a method and apparatus for order management based on data analysis according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a two-dimensional data space mapping according to an embodiment of the invention;
FIG. 3 is a block diagram illustrating the structure of an order management method and apparatus based on data analysis according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is changed accordingly, and the connection may be a direct connection or an indirect connection.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In addition, the descriptions related to "first", "second", etc. in the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, the present invention provides an order management method based on data analysis, including:
s1: acquiring order data packets to be classified based on an order data packet acquisition instruction of a designated department; wherein the order data packet comprises a plurality of data orders;
s2: performing feature extraction on each data order to obtain a multi-dimensional feature representation of each data order;
s3: selecting a corresponding kernel function according to a preset selection method to perform space mapping on each data order to obtain a corresponding target order after each data order is mapped;
s4: obtaining a classification standard of a designated department, and setting a plurality of normalization linear functions by adopting a preset linear classifier according to the classification standard
(ii) a Wherein,
and is and
，
a constant associated with the classification criteria is represented,
represents an offset, t is a positive integer, w represents a weight having the same dimension as the target orderThe weight vector is a vector of the number of vectors,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
s5: calculating the Euclidean distance between each normalized linear function and each target order, extracting the maximum Euclidean distance and the minimum Euclidean distance of each normalized linear function, and subtracting the minimum Euclidean distance from the maximum Euclidean distance to be used as the information distance of the corresponding normalized linear function;
s6: according to the formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function of (2);
s7: judging the transformation parameters
Whether the current is within a preset range;
s8: and if the data order is in the preset range, classifying the data order in the order data packet based on each normalized linear function, and sending a classification result to the designated department.
As described in the above step S1, the order data packet to be classified is obtained based on the instruction for obtaining the order data packet by the designated department; wherein the order data packet includes a plurality of data orders. The instruction for obtaining the order data packet may be sent by a specific department or sent by other departments, for example, the data distribution center may package the corresponding data order and then send the packaged data order to the corresponding specific department, it should be noted that the data order in the order data packet may be a large-class data order, for example, a household appliance class, or a data order including multiple classes, which may be determined according to the stock of the specific department. The data order is an order which is issued by each customer on the corresponding APP.
As described in step S2, performing feature extraction on each data order to obtain a multidimensional feature representation of each data order, where the feature extraction may be to extract data in the data order through a preset natural language processing model, the extracted feature category may be a category, a quantity, an address, and the like of a commodity in the data order, and it should be noted that each extracted feature needs to be converted into a corresponding vector or numerical representation, and the latter is preferred in this application, so as to obtain the multidimensional feature representation of each data order.
As described in step S3, the corresponding kernel function is selected according to a preset selection method to perform spatial mapping on each data order, so as to obtain a corresponding target order after mapping each data order. The method for selecting kernel functions can be any selection method, detailed description of kernel function selection is provided later in the application, and is not repeated herein, common kernel functions include linear kernel functions, polynomial kernel functions, Gauss radial basis kernel functions and the like, referring to fig. 2, the application performs detailed description on the role of kernel functions in a two-dimensional space, the left diagram in fig. 2 is a multidimensional data order which is not changed by kernel functions, fig. 3 is multidimensional data representation of a target order which is changed by kernel functions, it can be seen that data in the left diagram cannot be classified by a linear classifier, the right diagram which is changed by kernel functions can be easily classified by kernel functions, certainly, if a data order has three-dimensional or more dimensional features, the data order can still be linearly classified, linear classification here refers to classification of the data by a hyperplane, and certainly, one or more hyperplanes to be classified may be provided, this can be set appropriately according to the needs of the designated department. In fig. 2, Φ represents a kernel function, X represents a point therein, X represents a left graph, and F represents a right graph.
As described in the above step S4, the classification criteria of the designated department are obtained, and a plurality of normalized linear functions are set by using a preset linear classifier according to the classification criteria
Wherein, the linear classifier is to separate the positive and negative samples by a "hyperplane", such as: classifying the positive and negative samples on the two-dimensional plane by using a straight line; classifying positive and negative samples in a three-dimensional space by using a plane; the positive and negative samples in the N-dimensional space are classified by a hyperplane. Common linear classifiers are: LR, bayesian classification, single-layer perceptron, linear regression, SVM (linear kernel), etc. That is, if N is the space, the obtained normalized linear function is a hyperplane.
As described in step S5, the euclidean distance between each normalized linear function and each target order is calculated, the maximum euclidean distance and the minimum euclidean distance of each normalized linear function are extracted, and the minimum euclidean distance subtracted from the maximum euclidean distance is used as the information distance of the corresponding normalized linear function. The euclidean distance is calculated to obtain the normalized linear function, i.e. the distance of the hyperplane, for each target order value, and certainly, if the normalized linear function is not well set, i.e. many data are classified into the same category, or many target orders appear on the normalized linear function, the normalized linear function needs to be reset to achieve a good classified normalized linear function.
As stated in the above step S6, according to the formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function needs to be noted that the calculated transformation parameter is not a fixed value, that is, different l and k are assigned each time, the obtained results can be the same or different, in addition, l and k are different positive integers, and both need to be greater than 1, and it needs to be noted that one transformation parameter is a transformation parameter
The change condition of each target order can be reflected, and the closer the corresponding casual function parameter of every two adjacent normalized linear functions is to 1, the better the classification effect of the normalized linear functions is, and otherwise, the worse the effect is.
As described in the above steps S7-S8, the transformation parameters are determined
Whether the current is within a preset range; and if the data order is in the preset range, classifying the data order in the order data packet based on each normalized linear function, and sending a classification result to the designated department. Certainly, the transformation parameters of the order data packet cannot be always constant at a certain value, so a range can be preset, the range can be preset, then whether each transformation parameter is in the preset range or not is judged, if yes, the normalization linear functions classify the data orders in the order data packet, and classification results are sent to the appointed department, the classification mode is that target orders between every two normalization linear functions or data orders are set to be a class, and targets before the first normalization linear function and targets after the last normalization linear function are ordered to be a classThe single data is set to be of one category, so that data order classification for a specified department is realized, secondary classification of the data order is not needed, the processing efficiency of the data order is improved, and the delivery efficiency of the commodity is improved.
In one embodiment, the determining the transformation parameter
After the step S7, whether the current time is within the preset range, the method further includes:
s801: if the conversion parameters are not in the preset range, adjusting the weight vectors in the normalized linear functions until the conversion parameters are in the preset range to obtain target linear functions corresponding to the normalized linear functions;
s802: and classifying the data orders in the order data packet based on each target linear function, and sending classification results to the designated department.
As described in the foregoing steps S801 to S802, when the preset range is no longer within the preset range, the normalized linear function may be considered to be unreasonable in setting, and therefore, the weight vector therein needs to be adjusted, and the adjustment mode should be adjusted according to the standard of the designated department until all the transformation parameters are within the preset range, so as to obtain the target linear functions corresponding to the normalized linear functions, classify the data orders in the order data packets based on the target linear functions, and send the classification results to the designated department. The classification method is the same as the classification method by the normalized linear function, and is not described herein again.
In an embodiment, the step S3 of selecting a corresponding kernel function according to a preset selection method to perform spatial mapping on each data order to obtain a target order corresponding to each data order after mapping includes:
s301: according to the formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic representing the jth data order, n represents the number of the data orders, the dimension characteristic is one of the multi-dimension characteristics,
a value corresponding to the ith dimension characteristic of the jth data order is shown,
and
respectively representing the minimum value and the maximum value of the ith dimension characteristic in the order data packet;
s302: inputting the information value of the dimension characteristic and the information of the appointed department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
s303: and performing space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
As described in steps S301-S303 above, the mapping of the data order is realized by formula
Calculating the information value of each dimension characteristic in the order data packet, when the information value is larger, indicating that the difference degree of the dimension characteristic is correspondingly larger, then inputting the information value of the dimension characteristic and the information of the specified department into a preset kernel function acquisition model, wherein the preset kernel function acquisition model is a neural network model, and extracting the relation between each kernel function and each information value from the neural network model, so as to select the most appropriate kernel function for mapping, and it needs to be noted that if the data order can be directly subjected to linear classification, the mapping can be directly performed, namely, the variation of the kernel function is 1.
In an embodiment, before the step S2 of performing feature extraction on each data order to obtain a multidimensional feature representation of each data order, the method further includes:
s101: judging whether the order data packet has a data order belonging to the same template;
s102: if so, folding the data orders belonging to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
As described in steps S101-S102, some data orders exist in the order data, which are only different in receiving address, but have close receiving addresses, so that it is possible to perform a folding process on the order data, that is, one of the data orders is used as a representative in the order data packet, and other data orders belonging to the same template are deleted from the order data packet, thereby reducing subsequent calculation amount and making the processing of the data orders more efficient.
In an embodiment, after the step S8 of classifying the data orders in the order data packet based on each normalized linear function and sending the classification result to the designated department if the data orders are within the preset range, the method further includes:
s901: acquiring a time limit characteristic value of each data order;
s902: sorting the data orders in each classification category based on the time limit characteristic value of each data order;
s903: and issuing tasks to all the working posts according to the sequenced data orders so as to sequentially deliver the products on all the data orders.
As described in the foregoing steps S901 to S903, the arrangement of each data order in the delivery time is realized, that is, the time limit characteristic values of each data order are obtained, then the data orders are sorted, the data orders with a relatively tight time limit are sorted in front, and then the data orders are sent to each work post through a designated department, and the products on each data order are delivered out of the warehouse in sequence, so that the ordered processing of each data order is realized, and the background data processing is more efficient.
Referring to fig. 3, the present invention further provides an order management apparatus based on data analysis, including:
a data order obtaining module 10, configured to obtain an order data packet to be classified based on an instruction for obtaining the order data packet by a specified department; wherein the order data packet comprises a plurality of data orders;
a feature extraction module 20, configured to perform feature extraction on each data order to obtain a multidimensional feature representation of each data order;
the data order mapping module 30 is configured to select a corresponding kernel function according to a preset selection method to perform spatial mapping on each data order, so as to obtain a corresponding target order after each data order is mapped;
a function setting module 40, configured to obtain a classification standard of a designated department, and set multiple normalized linear functions according to the classification standard by using a preset linear classifier
(ii) a Wherein,
and is and
，
a constant associated with the classification criteria is represented,
representing an offset, t being a positive integer, w representing a weight vector having the same dimensions as the target order,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
the Euclidean distance calculation module 50 is configured to calculate Euclidean distances between each normalized linear function and each target order, extract a maximum Euclidean distance and a minimum Euclidean distance of each normalized linear function, and subtract the minimum Euclidean distance from the maximum Euclidean distance as an information distance of the corresponding normalized linear function;
a transformation parameter calculation module 60 for calculating a transformation parameter according to a formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the n-th information distance,
the representation is based on
The preset calculation function of (2);
a transformation parameter judgment module 70 for judging the transformation parameters
Whether the current is within a preset range;
and the data order classification module 80 is configured to classify the data orders in the order data packets based on each normalized linear function and send the classification results to the designated department if the data orders are within a preset range.
In one embodiment, the order management apparatus based on data analysis further includes:
the adjusting module is used for adjusting the weight vector in the normalized linear function if the weight vector is not in a preset range until the transformation parameter is in the preset range to obtain a target linear function corresponding to each normalized linear function;
and the classification module is used for classifying the data orders in the order data packet based on each target linear function and sending the classification result to the designated department.
In one embodiment, the data order mapping module 30 includes:
an information value calculating operator module for calculating the value of the information value according to a formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic is shown, n is the number of the data orders, the dimension characteristic is one of the multi-dimension characteristics,
a value corresponding to the ith dimension characteristic of the jth data order is shown,
and
respectively representing the minimum value and the maximum value of the ith dimension characteristic in the order data packet;
the input submodule is used for inputting the information value of the dimension characteristic and the information of the designated department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
and the mapping submodule is used for carrying out space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
In one embodiment, the order management apparatus based on data analysis further includes:
the data order judging module is used for judging whether the order data packet has data orders belonging to the same template;
and the folding module is used for folding the data orders belonging to the same template if the data orders belong to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
In one embodiment, the order management apparatus based on data analysis further includes:
the time limit characteristic value acquisition module is used for acquiring the time limit characteristic value of each data order;
the sorting module is used for sorting the data orders in each classification category based on the time limit characteristic value of each data order;
and the ex-warehouse module is used for issuing tasks to all the working posts according to the sequenced data orders so as to sequentially ex-warehouse the products on all the data orders.
The invention has the beneficial effects that: the data order classification of the appointed department is realized by acquiring the order data packet to be classified of the appointed department, performing feature extraction on the order data packet, performing space mapping to obtain a target order corresponding to each data order, and setting a plurality of normalized linear functions for classification by using a target order setting linear classifier, so that secondary classification of the data order is not needed, the processing efficiency of the data order is improved, and the ex-warehouse efficiency of the commodity is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. An order management method based on data analysis is characterized by comprising the following steps:
obtaining order data packets to be classified based on an instruction of obtaining the order data packets by a specified department; wherein the order data packet comprises a plurality of data orders;
performing feature extraction on each data order to obtain a multi-dimensional feature representation of each data order;
selecting a corresponding kernel function according to a preset selection method to perform space mapping on each data order to obtain a corresponding target order after each data order is mapped;
obtaining a classification standard of a designated department, and setting a plurality of normalization linear functions by adopting a preset linear classifier according to the classification standard
(ii) a Wherein,
and is and
，
a constant associated with the classification criteria is represented,
representing an offset, t being a positive integer, w representing a weight vector having the same dimensions as the target order,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
calculating the Euclidean distance between each normalized linear function and each target order, extracting the maximum Euclidean distance and the minimum Euclidean distance of each normalized linear function, and subtracting the minimum Euclidean distance from the maximum Euclidean distance to be used as the information distance of the corresponding normalized linear function;
according to the formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function of (2);
judging the transformation parameters
Whether the current is within a preset range;
and if the data order is in the preset range, classifying the data order in the order data packet based on each normalized linear function, and sending a classification result to the designated department.
2. The data analysis-based order management method of claim 1, wherein said determining said transformation parameter
After the step of determining whether the current time is within the preset range, the method further comprises the following steps:
if the conversion parameters are not in the preset range, adjusting the weight vectors in the normalized linear functions until the conversion parameters are in the preset range to obtain target linear functions corresponding to the normalized linear functions;
and classifying the data orders in the order data packet based on each target linear function, and sending classification results to the designated department.
3. The data analysis-based order management method according to claim 1, wherein the step of selecting a corresponding kernel function according to a preset selection method to perform spatial mapping on each data order to obtain a corresponding target order after mapping of each data order comprises:
according to the formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic is shown, n is shownA number of data orders, the dimensional feature being one of the multi-dimensional features,
a value corresponding to the ith dimension characteristic of the jth data order is shown,
and
respectively representing the minimum value and the maximum value of the ith dimensional characteristic in the order data packet;
inputting the information value of the dimension characteristic and the information of the designated department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
and performing space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
4. The data analysis-based order management method of claim 1, wherein before the step of performing feature extraction on each of the data orders to obtain the multidimensional feature representation of each of the data orders, the method further comprises:
judging whether the order data packet has a data order belonging to the same template;
if so, folding the data orders belonging to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
5. The data analysis-based order management method according to claim 1, wherein after the step of classifying the data orders in the order data packet based on each normalized linear function and sending the classification result to the designated department if the data orders are within a preset range, the method further comprises:
acquiring a time limit characteristic value of each data order;
sorting the data orders in each classification category based on the time limit characteristic value of each data order;
and issuing tasks to all the working posts according to the sequenced data orders so as to sequentially deliver the products on all the data orders.
6. An order management apparatus based on data analysis, comprising:
the data order acquisition module is used for acquiring order data packets to be classified based on an instruction of acquiring the order data packets by a specified department; wherein the order data packet comprises a plurality of data orders;
the characteristic extraction module is used for extracting the characteristics of each data order to obtain the multidimensional characteristic representation of each data order;
the data order mapping module is used for selecting a corresponding kernel function according to a preset selection method to perform space mapping on each data order to obtain a corresponding target order after each data order is mapped;
a function setting module for obtaining the classification standard of the appointed department and setting multiple normalization linear functions by adopting a preset linear classifier according to the classification standard
(ii) a Wherein,
and is and
，
indicating correlation with classification criteriaThe constant number is a constant number,
representing an offset, t being a positive integer, w representing a weight vector having the same dimensions as the target order,
expressing a normalized linear function, wherein x represents a target order and W is a preset parameter;
the Euclidean distance calculation module is used for calculating the Euclidean distance between each normalized linear function and each target order, extracting the maximum Euclidean distance and the minimum Euclidean distance of each normalized linear function, and subtracting the minimum Euclidean distance from the maximum Euclidean distance to be used as the information distance of the corresponding normalized linear function;
a transformation parameter calculation module for calculating a transformation parameter based on a formula
Transformation parameters for calculating information distance of pairwise adjacent normalized linear functions
(ii) a Wherein,
which represents the nth information distance,
the representation is based on
The preset calculation function of (2);
a conversion parameter judgment module for judging the conversion parameter
Whether the current is within a preset range;
and the data order classification module is used for classifying the data orders in the order data packet based on each normalized linear function and sending the classification result to the designated department if the data orders are in a preset range.
7. The data analysis-based order management apparatus according to claim 6, further comprising:
the adjusting module is used for adjusting the weight vector in the normalized linear function if the weight vector is not in a preset range until the transformation parameter is in the preset range to obtain a target linear function corresponding to each normalized linear function;
and the classification module is used for classifying the data orders in the order data packet based on each target linear function and sending the classification result to the designated department.
8. The data analysis-based order management apparatus of claim 6, wherein the data order mapping module comprises:
an information value calculating operator module for calculating the value of the information value according to a formula
Calculating the information value of each dimension characteristic in the order data packet, wherein
Wherein
information value representing the ith dimension characteristic when
When, define
，
Representing the intermediate value corresponding to the ith dimension characteristic of the jth data order,
a standard value corresponding to the ith dimension characteristic is shown, n is the number of the data orders, the dimension characteristic is one of the multi-dimension characteristics,
a value corresponding to the ith dimension characteristic of the jth data order is shown,
and
respectively representing the minimum value and the maximum value of the ith dimensional characteristic in the order data packet;
the input submodule is used for inputting the information value of the dimension characteristic and the information of the designated department into a preset kernel function acquisition model to obtain a corresponding kernel function; the kernel function acquisition model is trained according to information of a plurality of designated departments and corresponding dimension characteristic information values;
and the mapping submodule is used for carrying out space mapping on each data order according to the corresponding kernel function to obtain a corresponding target order after each data order is mapped.
9. The data analysis-based order management apparatus according to claim 6, further comprising:
the data order judging module is used for judging whether the order data packet has data orders belonging to the same template;
and the folding module is used for folding the data orders belonging to the same template if the data orders belong to the same template, selecting one of the data orders as a representative in the order data packet, and deleting other data orders belonging to the same template from the order data packet.
10. The data analysis-based order management apparatus according to claim 6, further comprising:
the time limit characteristic value acquisition module is used for acquiring the time limit characteristic value of each data order;
the sorting module is used for sorting the data orders in each classification category based on the time limit characteristic value of each data order;
and the ex-warehouse module is used for issuing tasks to all the working posts according to the sequenced data orders so as to sequentially ex-warehouse the products on all the data orders.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210814718.9A CN114897588B (en) | 2022-07-12 | 2022-07-12 | Order management method and device based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210814718.9A CN114897588B (en) | 2022-07-12 | 2022-07-12 | Order management method and device based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114897588A true CN114897588A (en) | 2022-08-12 |
| CN114897588B CN114897588B (en) | 2022-09-23 |
Family
ID=82729854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210814718.9A Active CN114897588B (en) | 2022-07-12 | 2022-07-12 | Order management method and device based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114897588B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468255A (en) * | 2023-06-15 | 2023-07-21 | 国网信通亿力科技有限责任公司 | Configurable main data management system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050060295A1 (en) * | 2003-09-12 | 2005-03-17 | Sensory Networks, Inc. | Statistical classification of high-speed network data through content inspection |
| US20090046951A1 (en) * | 2007-07-16 | 2009-02-19 | Nikos Paragios | System and Method for Dense Image Registration Using Markov Random Fields and Efficient Linear Programming |
| CN108446691A (en) * | 2018-06-09 | 2018-08-24 | 西北农林科技大学 | A kind of face identification method based on SVM linear discriminants |
-
2022
- 2022-07-12 CN CN202210814718.9A patent/CN114897588B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050060295A1 (en) * | 2003-09-12 | 2005-03-17 | Sensory Networks, Inc. | Statistical classification of high-speed network data through content inspection |
| US20090046951A1 (en) * | 2007-07-16 | 2009-02-19 | Nikos Paragios | System and Method for Dense Image Registration Using Markov Random Fields and Efficient Linear Programming |
| CN108446691A (en) * | 2018-06-09 | 2018-08-24 | 西北农林科技大学 | A kind of face identification method based on SVM linear discriminants |
Non-Patent Citations (3)
| Title |
|---|
| AMIT EFRAIM: "《The Universal Manifold Embedding for Estimating Rigid Transformations of Point Clouds》", 《IEEE》 * |
| 杨庆等: "基于测地线距离的核主元分析在齿轮泵故障识别中应用", 《上海交通大学学报》 * |
| 许建华等: "经典线性算法的非线性核形式", 《控制与决策》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468255A (en) * | 2023-06-15 | 2023-07-21 | 国网信通亿力科技有限责任公司 | Configurable main data management system |
| CN116468255B (en) * | 2023-06-15 | 2023-09-08 | 国网信通亿力科技有限责任公司 | Configurable main data management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114897588B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| NL1042116B1 (en) | Association rule mining method based on vector operations | |
| CN114897588B (en) | Order management method and device based on data analysis | |
| CN115426205B (en) | Encrypted data generation method and device based on differential privacy | |
| CN111126426A (en) | Feature selection method and device, computer equipment and storage medium | |
| CN114419378B (en) | Image classification method and device, electronic equipment and medium | |
| CN112926616A (en) | Image matching method and device, electronic equipment and computer-readable storage medium | |
| CN112364163A (en) | Log caching method and device and computer equipment | |
| Al-Sahaf et al. | A multitree genetic programming representation for automatically evolving texture image descriptors | |
| Molovtsev et al. | Classification algorithms analysis in the forest fire detection problem | |
| CN112634057A (en) | Fund similarity calculation method, platform, device and readable storage medium | |
| CN113759917A (en) | Wisdom commodity circulation letter sorting system based on cloud calculates | |
| CN103902706A (en) | Method for classifying and predicting big data on basis of SVM (support vector machine) | |
| CN112035664A (en) | Medicine classification method and device and computer equipment | |
| US20200380288A1 (en) | Proposal region filter for digital image processing | |
| CN110598772A (en) | Operation data detection method and device, computer equipment and storage medium | |
| CN114692785B (en) | Behavior classification method, device, equipment and storage medium | |
| Bogalinski et al. | Evaluation of strip nesting algorithms: an experimentation system for the practical users | |
| CN112989022B (en) | Intelligent virtual text selection method and device and computer equipment | |
| Fröhlich et al. | Efficient Gaussian process classification using random decision forests | |
| CN113642623A (en) | Complex support vector machine classification method based on unitary space multi-feature fusion | |
| CN112163926A (en) | Clothing chest size matching method, device, equipment and storage medium | |
| Kwenda et al. | Forest image classification based on deep learning and XGBoost algorithm | |
| CN107563399A (en) | The characteristic weighing Spectral Clustering and system of a kind of knowledge based entropy | |
| KR20210063775A (en) | Device for predicting price of asset use of convolution neural network | |
| Baruque et al. | WeVoS scale invariant map |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |