CN113052513B - Method for constructing address classification model, address classification method and related equipment - Google Patents
Method for constructing address classification model, address classification method and related equipment Download PDFInfo
- Publication number
- CN113052513B CN113052513B CN202110521974.4A CN202110521974A CN113052513B CN 113052513 B CN113052513 B CN 113052513B CN 202110521974 A CN202110521974 A CN 202110521974A CN 113052513 B CN113052513 B CN 113052513B
- Authority
- CN
- China
- Prior art keywords
- dispatch
- address
- map
- sub
- classification model
- 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.)
- Active
Links
- 238000013145 classification model Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000000638 solvent extraction Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000008932 jinhong Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Biodiversity & Conservation Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method for constructing an address classification model, an address classification method and related equipment, wherein the method for constructing the address classification model comprises the following steps: dividing the region to be classified into a plurality of sub-map regions to obtain map category data; dividing the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data; and training an address classification model based on the map category data and the dispatch address category data, wherein the address classification model is used for predicting the dispatch category to which the address to be classified belongs. The invention optimizes the address classification model, so that the address classification can be accurately performed for the address position or the building without history dispatch records, thereby improving the logistics timeliness and improving the logistics experience of users.
Description
Technical Field
The present invention relates to the field of computer applications, and in particular, to a method for constructing an address classification model, an address classification method, and related devices.
Background
Under the logistics scene, after a user generates a logistics order, a logistics platform or other platforms with logistics scenes such as an e-commerce platform need to infer each circulation link which needs to be passed from a delivery place to a receiving place according to address information filled by the user so as to perform express circulation. This series of flow information is identified primarily by means of three-segment codes printed on the flow sheet. However, the three-segment code needs to infer the node dispatching the address according to the detailed address filled by the user. The common reasoning model relies on a large number of dispatch records of the area to learn, for example, in the past 10 days, packages with golden rainbow bridge international centers in addresses are dispatched by ancient north nodes, and the reasoning model can learn the mapping relation between the golden rainbow bridge international centers and the ancient north nodes according to the packages.
However, for the address location or building where there is no dispatch record in the historical logistics data, the common reasoning model has difficulty in learning the corresponding dispatch node. For example, [ Chang Fang International Square ] does not appear in the history dispatch records, and the inference model is difficult to construct the mapping relation between [ Chang Fang International Square ] and any node. The current mode will lead to writing the address position that does not have history dispatch record or the commodity circulation order of building, can't confirm the dispatch node in the reasoning model to can't confirm the three-section code, also can't print the three-section code on commodity circulation face list, from this, when carrying out commodity circulation parcel letter sorting, need the manual judgment letter sorting, reduced commodity circulation ageing, influence user experience.
Therefore, how to optimize the address classification model, so that the address classification can be accurately performed for the address position or the building without history dispatch records, thereby improving logistics timeliness and increasing user logistics experience, and the method is a technical problem to be solved in the field.
Disclosure of Invention
In order to overcome the defects of the related art, the invention provides a method for constructing an address classification model, an address classification method and related equipment, and further optimizes the address classification model, so that the address classification can be accurately performed for address positions or buildings without history dispatch records, thereby improving logistics timeliness and improving user logistics experience.
According to one aspect of the present invention, there is provided a method of constructing an address classification model, comprising:
dividing the region to be classified into a plurality of sub-map regions to obtain map category data;
dividing the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data;
and training an address classification model based on the map category data and the dispatch address category data, wherein the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
In some embodiments of the invention, the address classification model comprises:
the address data vectorization layer is configured to carry out text vectorization processing on the address information input into the address classification model;
and the address classification layer is configured to classify the address information subjected to the text vectorization processing so as to output the belonging dispatch category.
In some embodiments of the present invention, the address data vectorization layer employs textCNN and the address classification layer employs softmax.
In some embodiments of the invention, the dispatch categories are based on dispatcher/dispatch node partitioning.
In some embodiments of the invention, the sub-map area is partitioned based on dispatch/dispatch nodes.
In some embodiments of the invention, the sub-map areas are divided by a set regular shape.
In some embodiments of the present invention, the dividing the region to be classified into a plurality of sub-map regions to obtain map category data includes:
determining the number of the sub-map areas according to the number of the dispatch personnel/dispatch nodes;
dividing the region to be classified into a plurality of quasi-sub map regions in a rectangular shape according to the determined quantity;
the quasi-sub-map areas are adjusted to determine sub-map areas based at least on the historical dispatch volumes of each quasi-sub-map area, the historical dispatch capabilities of each dispatcher/dispatch node.
In some embodiments of the present invention, the adjusting the quasi-sub map areas based at least on the historical dispatch volume for each quasi-sub map area, the historical dispatch capacity for each dispatcher/dispatch node, to determine sub map areas includes:
calculating the ratio of the historical dispatch quantity in the set time period of each quasi-sub map area to the historical dispatch capacity of the dispatch person/dispatch node corresponding to the quasi-sub map area;
for each quasi-sub map area, judging whether the difference between the ratio of the quasi-sub map area and the ratio of the adjacent quasi-sub map area is larger than a set threshold value;
If yes, the area of the current quasi-self map area is reduced, and the area of the adjacent quasi-sub map area is increased.
According to still another aspect of the present invention, there is also provided an address classification method, including:
inputting an address to be classified into an address classification model, the address classification model being constructed via the method of constructing an address classification model as described above;
and predicting the dispatch category to which the address to be classified belongs according to the output of the address classification model.
According to still another aspect of the present invention, there is also provided an apparatus for constructing an address classification model, including:
the first dividing module is configured to divide the region to be classified into a plurality of sub-map regions so as to obtain map category data;
the second dividing module is configured to divide the historical dispatch addresses of the region to be classified into a plurality of dispatch categories so as to obtain dispatch address category data;
the training module is configured to train an address classification model based on the map category data and the dispatch address category data, wherein the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
According to still another aspect of the present invention, there is also provided an address classifying apparatus including:
an input module configured to input an address to be classified into an address classification model, the address classification model being constructed via a method of constructing an address classification model as described above;
And the prediction module is configured to predict the dispatch type to which the address to be classified belongs according to the output of the address classification model.
According to still another aspect of the present invention, there is also provided an electronic apparatus including: a processor; a storage medium having stored thereon a computer program which, when executed by the processor, performs the steps as described above.
According to a further aspect of the present invention there is also provided a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps as described above.
Compared with the prior art, the invention has the advantages that:
the invention takes the map category data based on the map and the dispatch address category data based on the historical dispatch address as training samples for training the address classification model, so that the address classification model can learn not only the mapping relation between the historical dispatch address and the dispatch category, but also the mapping relation between the sub map area in the map category data and the dispatch category according to the map category data and the dispatch address category data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
FIG. 1 illustrates a flow chart of a method of building an address classification model according to an embodiment of the invention.
Fig. 2 illustrates a flowchart of dividing an area to be classified into a plurality of sub-map areas to obtain map category data according to an embodiment of the present invention.
FIG. 3 illustrates a flow chart for adjusting quasi-sub-map regions to determine sub-map regions based at least on historical dispatch volumes for each quasi-sub-map region, historical dispatch capabilities for each dispatcher/dispatch node, in accordance with an embodiment of the present invention.
Fig. 4 shows a flow chart of an address classification method according to an embodiment of the invention.
Fig. 5 shows a block diagram of an apparatus for constructing an address classification model according to an embodiment of the present invention.
Fig. 6 shows a block diagram of an address classification apparatus according to an embodiment of the invention.
Fig. 7 schematically illustrates a computer-readable storage medium according to an exemplary embodiment of the present invention.
Fig. 8 schematically illustrates an electronic device according to an exemplary embodiment of the invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only and not necessarily all steps are included. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
In various embodiments of the present invention, the method for constructing an address classification model provided by the present invention may be applied to a logistics platform, an electronic commerce platform, or any platform where a third party needs to implement address classification, but the application scenario of the present invention is not limited thereto, and is not described herein.
FIG. 1 illustrates a flow chart of a method of building an address classification model according to an embodiment of the invention. The method for constructing the address classification model comprises the following steps:
Step S110: the region to be classified is divided into a plurality of sub-map regions to obtain map category data.
Specifically, the region to be classified may be a city, a county, a village, or the like. In some variations, the region to be classified may be set as required, for example, a plurality of adjacent villages may be used as one region to be classified; a plurality of adjacent counties may be used as one region to be classified, which is not limited by the present invention.
Specifically, step S110 may divide the above-described region to be classified into a plurality of sub-map regions based on map data provided by each map provider.
Specifically, the map category data may include address data and a sub-map area to which the address data belongs. In a preferred embodiment, the address data may include address information and the latitude and longitude of the address. The address information may be complete address information or address information of a set field (e.g., a point of interest, a road name, a building, a community, etc.), which the present invention is not limited to.
Specifically, in step S110, the division of the area may be implemented by executing a GeoHash algorithm on the longitude and latitude in the address data, which is not limited by the present invention. The GeoHash algorithm is a way of spatial indexing, whose basic principle is to understand the earth as a two-dimensional plane, recursively decompose the plane into smaller sub-blocks, each having the same code over a range of longitudes and latitudes. The space index is established in a GeoHash mode, so that the efficiency of carrying out longitude and latitude retrieval on the space interest point data can be improved. Taking Shanghai city as an example of the region to be classified, step S110 may divide all address data of Shanghai city into a plurality of sub-map regions (such as 1000, 5000, 10000, 20000, etc.), and addresses in each sub-map region are longitude and latitude coordinates adjacent to each other.
Specifically, in some embodiments, when the sub-map region division is performed in step S110, the number of sub-map regions may be set in advance, thereby facilitating the division of the regions. In this embodiment, the number of sub-map areas set in advance may be, for example, the number of dispatch operators for the area to be classified. Thus, it is equivalent to enabling one dispatcher to complete the division of one sub-map area. In other embodiments, the number of sub-map areas set in advance may be, for example, the number of dispatch nodes of the area to be classified. Therefore, the method is equivalent to enabling one dispatch node to complete the division of one sub-map area. In still other embodiments, the number of pre-set sub-map regions may be greater than the number of dispatch nodes/dispatch operators for the region to be classified, for example. Therefore, the mapping relation between the dispatch personnel/dispatch nodes and the sub map area can be more refined according to the subsequent study of the address classification model.
Specifically, in some embodiments, when the sub-map region division is performed in step S110, the shape of the sub-map region may be set in advance, thereby facilitating the division of the region. In this embodiment, the shape of the sub-map area set in advance is a regular shape, and the dividing efficiency of the sub-map area can be improved compared with other irregular shapes. Further, in this embodiment, the shape of the sub-map area that can be set in advance is a regular shape, and meanwhile, the number of sub-map areas that are set in advance is far greater than the number of dispatch nodes/dispatch operators in the area to be classified, so that not only can the efficiency of area division be improved, but also the shape formed by the sub-map areas that can be mapped by the dispatch nodes/dispatch operators is more flexible, so as to adapt to various road conditions and logistics dispatch conditions. The present invention is not limited thereto, and other irregular shapes, or adjustments of the shape of the region during the dividing process, are within the scope of the present invention.
Step S120: and dividing the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data.
Specifically, in step S120, the dispatch category may be divided based on dispatch personnel/dispatch nodes. In an embodiment based on dispatch personnel division, the codes/identifiers of the dispatch personnel can be used as dispatch categories, so that each historical dispatch address can be divided into the dispatch categories in which the codes/identifiers of the dispatch personnel performing the dispatch of the logistic package are located. In a specific implementation, when there are multiple dispatch members that execute the logistics including dispatch in the logistics data of the historical dispatch address, the code/identifier of the dispatch member with the largest dispatch number in the last set period (one week/two weeks/one month) may be used as the dispatch class where the historical dispatch address is located. The partitioning of dispatch categories based on dispatch nodes may be implemented in a similar manner, and will not be described in detail herein.
In one embodiment, a certain logistics provider has 3000 dispatch operators in the Shanghai, each of which is responsible for a respective area, whereby the historical dispatch addresses of all Shanghai users can be divided into 3000 dispatch categories. Each dispatch category is a dispatch area of a dispatcher, and each historical dispatch address in the dispatch area of the same dispatcher is close to each other.
Step S130: and training an address classification model based on the map category data and the dispatch address category data, wherein the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
In particular, the address classification model may include an address data vectorization layer and an address classification layer. The address classification layer may be concatenated after the address data vectorization layer. The address data vectorization layer is configured to perform text vectorization processing on address information input into the address classification model. The address data vectorization layer may adopt textCNN (text convolutional neural network) to perform text vectorization processing. textCNN is a variant of CNN (convolutional neural network) that is mainly used for picture classification, while textCNN is mainly used for text classification, which can vectorize text into a k-dimensional vector, thereby representing words in sentences. Specifically, the address data vectorization layer is configured to implement sharing of map category data and delivery address category data. The address classification layer is configured to classify the address information subjected to the text vectorization processing to output the belonging dispatch category. The address classification layer may employ softmax. Softmax can be used in a multi-classification process that maps the output of multiple neurons into (0, 1) intervals as probabilities for that classification, thereby achieving multiple classifications. Further, the address classification layer achieves separation of map category data and dispatch address category data. Therefore, the address data vectorization layer can share address information of two sources, so that the model has stronger generalization capability.
In the method for constructing the address classification model, the map type data based on the map and the dispatch address type data based on the historical dispatch addresses are used as training samples for training the address classification model, so that the address classification model can learn the mapping relation between the historical dispatch addresses and the dispatch types, and can learn the mapping relation between the sub-map areas in the map type data and the dispatch types according to the map type data and the dispatch address type data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
Referring now to fig. 2, fig. 2 illustrates a flow chart of dividing an area to be classified into a plurality of sub-map areas to obtain map category data according to an embodiment of the present invention. Fig. 2 shows the following steps in total:
step S111: and determining the number of the sub map areas according to the number of the dispatch personnel/dispatch nodes.
In some embodiments, the number of sub-map areas set in advance may be, for example, the number of dispatch operators for the area to be classified. Thus, it is equivalent to enabling one dispatcher to complete the division of one sub-map area. In other embodiments, the number of sub-map areas set in advance may be, for example, the number of dispatch nodes of the area to be classified. Therefore, the method is equivalent to enabling one dispatch node to complete the division of one sub-map area. In still other embodiments, the number of pre-set sub-map regions may be greater than the number of dispatch nodes/dispatch operators for the region to be classified, for example. Therefore, the mapping relation between the dispatch personnel/dispatch nodes and the sub map area can be more refined according to the subsequent study of the address classification model.
Step S112: and dividing the region to be classified into a plurality of quasi-sub map regions in a rectangular shape according to the determined quantity.
In this embodiment, the shape of the sub-map area set in advance is rectangular, and the dividing efficiency of the sub-map area can be improved compared with other irregular shapes. Further, the preliminary quasi-sub map area is obtained by the average division in step S112, thereby further improving the execution efficiency of step S112.
Step S113: the quasi-sub-map areas are adjusted to determine sub-map areas based at least on the historical dispatch volumes of each quasi-sub-map area, the historical dispatch capabilities of each dispatcher/dispatch node.
Specifically, considering that the dispatch capacity of the dispatcher/dispatch nodes is far beyond the historical dispatch capacity of the corresponding sub-map areas, and the dispatch capacity of the dispatcher/dispatch nodes is far beyond the historical dispatch capacity and the unbalanced throughput of the corresponding sub-map areas, which are directly divided according to the rectangular shape, the dispatch capacity of the dispatcher/dispatch nodes may be caused. Therefore, the adjustment of the quasi-sub map area is realized through the step S113, so that the historical dispatch capacity of the dispatch nodes and the historical dispatch capacity of the sub map area can be matched, and the capacity balance of each area is realized.
Specifically, the implementation of step S113 may refer to fig. 3, and fig. 3 shows a flowchart of adjusting the quasi-sub-map areas to determine sub-map areas based on at least the historical dispatch amount of each quasi-sub-map area and the historical dispatch capability of each dispatcher/dispatch node according to an embodiment of the present invention. Fig. 3 shows the following steps in total:
step S1131: and calculating the ratio of the historical dispatch quantity in the set time period of each quasi-sub map area to the historical dispatch capacity of the dispatch person/dispatch node corresponding to the quasi-sub map area.
Specifically, the set period of time may be, for example, the last day, the last week, the last two weeks, or the like, and the present invention is not limited thereto. The historical dispatch volume may be, for example, a daily dispatch volume. The historical dispatch capability may be the average dispatch volume of the dispatcher/dispatch node over a set period of time.
Step S1132: for each quasi-sub map region, it is determined whether the difference between the ratio and the ratio of the adjacent quasi-sub map region is greater than a set threshold.
Specifically, step S1132 determines whether the capacities of the adjacent quasi-sub map areas are balanced according to the ratio. The set threshold may be set as needed, and the present invention is not limited thereto.
If the determination in step S1132 is yes, step S1133 is executed: the area of the current quasi-self map region is reduced, and the area of the adjacent quasi-sub map region is increased.
When step S1132 determines that the capacity of the adjacent quasi-sub map area is not balanced, the capacity of the sender/sender node is not equal to the historical sending capacity of the current quasi-sub map area, and the sending capacity of the sender/sender node exceeds the historical sending capacity of the adjacent quasi-sub map area, so that the capacity of the adjacent map area is balanced by increasing or decreasing the area, that is, adjusting and distributing the quasi-sub map area.
Fig. 3 is a schematic illustration of one implementation of step S113, which is not limited by this, and other implementations of adjusting the quasi-sub-map regions based on the historical dispatch volumes of the quasi-sub-map regions and the historical dispatch capabilities of the dispatcher/dispatch nodes to determine the sub-map regions are also within the scope of the present invention. For example, in other embodiments, it may be determined whether a ratio of a historical dispatch capacity of a dispatcher/dispatch node corresponding to each quasi-sub map area to a historical dispatch capacity of the dispatcher/dispatch node corresponding to the quasi-sub map area is less than or equal to 1 and greater than 0.9 (where 1 and 0.9 may be set as needed, the invention is not limited thereto), and if so, the quasi-sub map area is taken as a sub map area; if not, judging whether the ratio of the historical dispatch capacity of the dispatch personnel/dispatch nodes corresponding to the adjacent quasi-sub map areas in the set time period is smaller than or equal to 0.9 when the ratio of the current quasi-sub map areas is larger than 1, if so, reducing the area of the current quasi-sub map areas and increasing the area of the adjacent quasi-sub map areas (the adjusted area size can be determined according to the difference value between the calculated ratio and 1/0.9); when the ratio of the current quasi-sub map area is less than or equal to 0.9, judging whether the ratio of the historical dispatch capacity of the dispatch member/dispatch node corresponding to the quasi-sub map area to the historical dispatch capacity of the dispatch member/dispatch node corresponding to the quasi-sub map area is greater than 0.9, if so, increasing the area of the current quasi-sub map area and reducing the area of the adjacent quasi-sub map area (the adjusted area can be determined according to the difference between the calculated ratio and 1/0.9). Further, the sub-map areas may be obtained by adjusting the sub-map areas with each other, which is not limited by the present invention. Therefore, the historical dispatch capacity of the dispatch staff/dispatch nodes in the quasi-sub map area is slightly larger than the historical dispatch amount in the set time period of the quasi-sub map area, so that the dispatch amount of the quasi-sub map area can be throughput, and meanwhile, the capacity margin can be provided to cope with the increase of the special dispatch amount.
The above are merely a plurality of specific implementations of the method for constructing an address classification model according to the present invention, and each implementation may be implemented independently or in combination, which is not limited thereto. Further, the flow chart of the present invention is merely illustrative, and the execution order of steps is not limited thereto, and the splitting, merging, sequential exchange, and other synchronous or asynchronous execution of steps are all within the scope of the present invention.
Referring now to fig. 4, fig. 4 is a flow chart illustrating a method of address classification according to an embodiment of the invention. The address classification method comprises the following steps:
step S210: the address to be classified is input into an address classification model, which is constructed via the method of constructing an address classification model as described above.
Step S220: and predicting the dispatch category to which the address to be classified belongs according to the output of the address classification model.
The obtained dispatch category can be used for calculating three-section codes, realizing time-effect prediction, realizing automatic sorting and the like, and the invention is not limited by the method.
In the address classification method provided by the invention, the address classification model can be used as a training sample for training the address classification model based on the map type data of the map and the dispatch address type data based on the historical dispatch address, so that the address classification model can learn the mapping relation between the historical dispatch address and the dispatch type and can learn the mapping relation between the sub-map area in the map type data and the dispatch type according to the map type data and the dispatch address type data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
In a specific embodiment of the present application, in combination with the method for constructing an address classification model and the address classification method of fig. 1 and fig. 4, the present invention may be implemented as follows:
first, map category data is prepared. And cutting the map data of the whole Shanghai to obtain a plurality of rectangular frames, wherein each sub-rectangular frame is a sub-map area. For example, in the division of map data, the "long house international square" and the "golden iridescent bridge international center" are divided into one sub map area.
Thereafter, the dispatch address category data is prepared. The dispatch record of dispatcher 001 [ golden rainbow bridge international center ] [ roqueen mountain cell ], both of which are classified into the same dispatch category. However, the record of the order is less, and the record of the order is not in any order sender.
Then, an address classification model based on the neural network is constructed. The sharing of text vectorization of the dispatch address category data and the map category data is realized through the address data vectorization layer of the address classification model, so that vectors of [ the long house international square ] and [ the golden siphon bridge international center ] can be learned to be similar in the address data vectorization layer, and the same dispatch category is corresponding to the address data vectorization layer; meanwhile, vectors of the 'Jinhong bridge International center' and the 'Louis mountain district' are similar, and correspond to the same dispatch category and form a mapping with a dispatcher 001. Thus, the whole network can map the long house international square with the dispatcher 001, so that the dispatcher of the long house international square can be predicted correctly.
The above is merely a specific implementation manner of the method for constructing an address classification model and the address classification method according to the present invention, and the present invention is not limited thereto. Furthermore, the order of execution of the steps is not limited, and any way of splitting, merging, order exchange, and other synchronous or asynchronous execution of the steps is within the scope of the present invention.
Referring now to fig. 5, fig. 5 is a block diagram illustrating an apparatus for constructing an address classification model according to an embodiment of the present invention. The apparatus 300 for constructing an address classification model includes a first partitioning module 310, a second partitioning module 320, and a training module 330.
The first dividing module 310 is configured to divide the region to be classified into a plurality of sub-map regions to obtain map category data;
the second dividing module 320 is configured to divide the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data;
the training module 330 is configured to train an address classification model based on the map category data and the dispatch address category data, wherein the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
In the device for constructing the address classification model according to the exemplary embodiment of the present invention, the map type data based on the map and the dispatch address type data based on the history dispatch address are used as training samples for training the address classification model, so that the address classification model can learn not only the mapping relationship between the history dispatch address and the dispatch type, but also the mapping relationship between the sub-map area in the map type data and the dispatch type according to the map type data and the dispatch address type data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
Fig. 5 is a schematic illustration only, and the apparatus 300 for constructing an address classification model provided by the present invention is not inconsistent with the present invention, and the splitting, merging and adding of the modules are all within the protection scope of the present invention. The device 300 for constructing an address classification model according to the present invention may be implemented by software, hardware, firmware, plug-in and any combination thereof, which is not limited to this embodiment.
Referring now to fig. 6, fig. 6 shows a block diagram of an address classification apparatus according to an embodiment of the invention. The address classification apparatus 400 includes an input module 410 and a prediction module 420.
The input module 410 is configured to input an address to be classified into an address classification model, which is constructed via the method of constructing an address classification model as described above;
the prediction module 420 is configured to predict a dispatch category to which an address to be classified belongs according to an output of the address classification model.
In the address classification device according to the exemplary embodiment of the present invention, the map category data based on the map and the dispatch address category data based on the history dispatch address are used as training samples for training the address classification model, so that the address classification model can learn not only the mapping relationship between the history dispatch address and the dispatch category, but also the mapping relationship between the sub-map area in the map category data and the dispatch category according to the map category data and the dispatch address category data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
Fig. 6 is a schematic illustration only, and the address classification device 400 provided by the present invention is not limited by the present invention, and the splitting, combining and adding of the modules are all within the protection scope of the present invention. The address classifying apparatus 400 provided by the present invention may be implemented by software, hardware, firmware, plug-in and any combination thereof, which is not limited to the present invention.
In an exemplary embodiment of the invention, a computer-readable storage medium is also provided, on which a computer program is stored, which program, when being executed by, for example, a processor, may implement the steps of the method of building an address classification model and/or the address classification method described in any of the embodiments above. In some possible embodiments, the aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the above description of the method of building an address classification model and/or address classification method section, when said program product is run on the terminal device.
Referring to fig. 7, a program product 700 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the tenant computing device, partially on the tenant device, as a stand-alone software package, partially on the tenant computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the tenant computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected through the internet using an internet service provider).
In an exemplary embodiment of the invention, an electronic device is also provided, which may include a processor, and a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the steps of the method of building an address classification model and/or the address classification method described in any of the embodiments above via execution of the executable instructions.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 500 according to this embodiment of the invention is described below with reference to fig. 8. The electronic device 500 shown in fig. 8 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 8, the electronic device 500 is embodied in the form of a general purpose computing device. The components of electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one memory unit 520, a bus 530 connecting the different system components (including the memory unit 520 and the processing unit 510), a display unit 540, etc.
Wherein the storage unit stores program code that is executable by the processing unit 510 such that the processing unit 510 performs the steps according to various exemplary embodiments of the present invention described in the above description of the method of constructing an address classification model and/or address classification method section. For example, the processing unit 510 may perform the steps shown in any one or more of fig. 1-4.
The memory unit 520 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 5201 and/or cache memory unit 5202, and may further include Read Only Memory (ROM) 5203.
The storage unit 520 may also include a program/utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 530 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 500 may also communicate with one or more external devices 600 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a tenant to interact with the electronic device 500, and/or any device (e.g., router, modem, etc.) that enables the electronic device 500 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 550. Also, electronic device 500 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 560. The network adapter 560 may communicate with other modules of the electronic device 500 via the bus 530. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 500, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiment of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, or a network device, etc.) to perform the above-described method for constructing an address classification model and/or the address classification method according to the embodiment of the present invention.
Compared with the prior art, the invention has the advantages that:
the invention takes the map category data based on the map and the dispatch address category data based on the historical dispatch address as training samples for training the address classification model, so that the address classification model can learn not only the mapping relation between the historical dispatch address and the dispatch category, but also the mapping relation between the sub map area in the map category data and the dispatch category according to the map category data and the dispatch address category data. Whether the address to be classified belongs to the historical dispatch address or not, the dispatch category to which the address to be classified belongs can be predicted through the address classification model, so that the logistics timeliness is improved, and meanwhile, the logistics experience of users is improved.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
Claims (11)
1. A method of constructing an address classification model, comprising:
dividing the region to be classified into a plurality of sub-map regions to obtain map category data, including: determining the number of the sub-map areas according to the number of the dispatch personnel/dispatch nodes; dividing the region to be classified into a plurality of quasi-sub map regions in a rectangular shape according to the determined quantity; adjusting the quasi-sub map areas at least based on the historical dispatch amount of each quasi-sub map area and the historical dispatch capacity of each dispatcher/dispatch node to determine sub map areas;
dividing the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data, wherein the dispatch categories are divided based on dispatch staff/dispatch nodes;
And training an address classification model based on the map category data and the dispatch address category data, so that the address classification model learns the mapping relation between the historical dispatch address and the dispatch category and the mapping relation between the sub map area and the dispatch category, and the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
2. The method of constructing an address classification model of claim 1, wherein the address classification model comprises:
the address data vectorization layer is configured to carry out text vectorization processing on the address information input into the address classification model;
and the address classification layer is configured to classify the address information subjected to the text vectorization processing so as to output the belonging dispatch category.
3. The method of building an address classification model of claim 2, wherein the address data vectorization layer employs textCNN and the address classification layer employs softmax.
4. The method of building an address classification model of claim 1, wherein the sub-map area is partitioned based on dispatch personnel/dispatch nodes.
5. The method of constructing an address classification model of claim 1, wherein the sub-map areas are divided by a set regular shape.
6. The method of building an address classification model according to claim 1, wherein said adjusting the quasi-sub-map region to determine sub-map regions based at least on historical dispatch volumes for each quasi-sub-map region, historical dispatch capabilities for each dispatcher/dispatch node comprises:
calculating the ratio of the historical dispatch quantity in the set time period of each quasi-sub map area to the historical dispatch capacity of the dispatch person/dispatch node corresponding to the quasi-sub map area;
for each quasi-sub map area, judging whether the difference between the ratio of the quasi-sub map area and the ratio of the adjacent quasi-sub map area is larger than a set threshold value;
if yes, the area of the current quasi-self map area is reduced, and the area of the adjacent quasi-sub map area is increased.
7. An address classification method, comprising:
inputting an address to be classified into an address classification model constructed via the method of constructing an address classification model as claimed in any one of claims 1 to 6;
and predicting the dispatch category to which the address to be classified belongs according to the output of the address classification model.
8. An apparatus for constructing an address classification model, comprising:
the first division module is configured to divide the region to be classified into a plurality of sub-map regions to obtain map category data, and comprises: determining the number of the sub-map areas according to the number of the dispatch personnel/dispatch nodes; dividing the region to be classified into a plurality of quasi-sub map regions in a rectangular shape according to the determined quantity; adjusting the quasi-sub map areas at least based on the historical dispatch amount of each quasi-sub map area and the historical dispatch capacity of each dispatcher/dispatch node to determine sub map areas;
The second division module is configured to divide the historical dispatch addresses of the region to be classified into a plurality of dispatch categories to obtain dispatch address category data, and the dispatch categories are divided based on dispatch staff/dispatch nodes;
the training module is configured to train an address classification model based on the map category data and the dispatch address category data, so that the address classification model learns the mapping relation between the historical dispatch address and the dispatch category and the mapping relation between the sub map area and the dispatch category, and the address classification model is used for predicting the dispatch category to which the address to be classified belongs.
9. An address classification apparatus, comprising:
an input module configured to input an address to be classified into an address classification model constructed via the method of constructing an address classification model as claimed in any one of claims 1 to 6;
and the prediction module is configured to predict the dispatch type to which the address to be classified belongs according to the output of the address classification model.
10. An electronic device, the electronic device comprising:
a processor;
a memory having stored thereon a computer program which, when executed by the processor, performs:
A method of constructing an address classification model as claimed in any one of claims 1 to 6; and/or
The address classification method of claim 7.
11. A storage medium having a computer program stored thereon, the computer program when executed by a processor performing:
a method of constructing an address classification model as claimed in any one of claims 1 to 6; and/or
The address classification method of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110521974.4A CN113052513B (en) | 2021-05-13 | 2021-05-13 | Method for constructing address classification model, address classification method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110521974.4A CN113052513B (en) | 2021-05-13 | 2021-05-13 | Method for constructing address classification model, address classification method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052513A CN113052513A (en) | 2021-06-29 |
| CN113052513B true CN113052513B (en) | 2024-03-26 |
Family
ID=76518701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110521974.4A Active CN113052513B (en) | 2021-05-13 | 2021-05-13 | Method for constructing address classification model, address classification method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052513B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255565A (en) * | 2017-07-14 | 2019-01-22 | 菜鸟智能物流控股有限公司 | Address attribution identification and logistics task distribution method and device |
| CN110069626A (en) * | 2017-11-09 | 2019-07-30 | 菜鸟智能物流控股有限公司 | Target address recognition method, classification model training method and device |
| CN110751446A (en) * | 2019-10-25 | 2020-02-04 | 上海德启信息科技有限公司 | Distribution area dividing method and device, electronic equipment and readable storage medium |
| CN112465035A (en) * | 2020-11-30 | 2021-03-09 | 上海寻梦信息技术有限公司 | Logistics distribution task allocation method, system, equipment and storage medium |
| CN112488195A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Party delivery identification method, device, equipment and storage medium |
| CN112488200A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Logistics address feature extraction method, system, equipment and storage medium |
-
2021
- 2021-05-13 CN CN202110521974.4A patent/CN113052513B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255565A (en) * | 2017-07-14 | 2019-01-22 | 菜鸟智能物流控股有限公司 | Address attribution identification and logistics task distribution method and device |
| CN110069626A (en) * | 2017-11-09 | 2019-07-30 | 菜鸟智能物流控股有限公司 | Target address recognition method, classification model training method and device |
| CN110751446A (en) * | 2019-10-25 | 2020-02-04 | 上海德启信息科技有限公司 | Distribution area dividing method and device, electronic equipment and readable storage medium |
| CN112465035A (en) * | 2020-11-30 | 2021-03-09 | 上海寻梦信息技术有限公司 | Logistics distribution task allocation method, system, equipment and storage medium |
| CN112488195A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Party delivery identification method, device, equipment and storage medium |
| CN112488200A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Logistics address feature extraction method, system, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘树春.《深度实践OCR 基于深度学习的文字识别》.机械工业出版社,2020,第301-303页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052513A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133645B (en) | Method, equipment and storage medium for predicting order cancelling behavior of passenger | |
| CN113239198B (en) | Subway passenger flow prediction method and device and computer storage medium | |
| CN112328909B (en) | Information recommendation method and device, computer equipment and medium | |
| CN111522838A (en) | Address similarity calculation method and related device | |
| CN114912433A (en) | Text level multi-label classification method and device, electronic equipment and storage medium | |
| CN115130711A (en) | Data processing method and device, computer and readable storage medium | |
| CN111967808B (en) | Method, device, electronic equipment and storage medium for determining commodity circulation object receiving mode | |
| CN110990651B (en) | Address data processing method and device, electronic equipment and computer readable medium | |
| CN111800289A (en) | Communication network fault analysis method and device | |
| CN113204698B (en) | News subject term generation method, device, equipment and medium | |
| CN107729944B (en) | Identification method and device of popular pictures, server and storage medium | |
| CN113052513B (en) | Method for constructing address classification model, address classification method and related equipment | |
| WO2023236588A1 (en) | User classification method and apparatus based on deviation smoothing optimization for customer groups | |
| CN116346863A (en) | Vehicle-mounted network data processing method, device, equipment and medium based on federal learning | |
| US10824777B2 (en) | Employing natural language processing to facilitate geospatial analysis | |
| CN113591881B (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN115563522A (en) | Traffic data clustering method, device, equipment and medium | |
| CN113626605B (en) | Information classification method, device, electronic equipment and readable storage medium | |
| CN112488195B (en) | Method, device, equipment and storage medium for identifying dispatch of dispatcher | |
| CN114638308A (en) | Method and device for acquiring object relationship, electronic equipment and storage medium | |
| WO2021121206A1 (en) | Method for determining responsibility for service accident and system | |
| CN112835922A (en) | Address division classification method, system, device and storage medium | |
| CN112488624A (en) | Logistics routing information calculation method, device, equipment and storage medium | |
| CN113011672B (en) | Logistics aging prediction method and device, electronic equipment and storage medium | |
| CN113537671A (en) | Sorting timeliness prediction method and device, storage medium and electronic equipment |
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 |