CN111754050A - Method and apparatus for predicting delivery image of delivery object - Google Patents
Method and apparatus for predicting delivery image of delivery object Download PDFInfo
- Publication number
- CN111754050A CN111754050A CN202010677070.6A CN202010677070A CN111754050A CN 111754050 A CN111754050 A CN 111754050A CN 202010677070 A CN202010677070 A CN 202010677070A CN 111754050 A CN111754050 A CN 111754050A
- Authority
- CN
- China
- Prior art keywords
- delivery
- information
- state
- distribution
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 92
- 238000012549 training Methods 0.000 claims abstract description 56
- 230000010354 integration Effects 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013475 authorization Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000005070 sampling Methods 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- 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
- G06Q10/0833—Tracking
-
- 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
- G06Q10/0838—Historical data
-
- 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
Abstract
The embodiment of the invention discloses a method and a device for predicting a distribution portrait of a distribution object, wherein the method comprises the following steps: collecting delivery order information and track information of each first delivery object in the first delivery object set, and carrying out delivery state marking processing on the track information according to the delivery order information to obtain sample data; training the state multi-classification label model according to the sample data to obtain a trained state multi-classification label model; for any second delivery object in the second delivery object set, collecting track information of the second delivery object, and inputting the track information of the second delivery object into the trained state multi-classification label model to obtain track information after state marking processing; and obtaining a distribution image of the second distribution object according to the track information subjected to the state marking processing. And determining a distribution image of the second distribution object based on the track information after the marking processing of the distribution state, wherein the limitation that the distribution image needs to obtain distribution order information of a distribution platform is avoided.
Description
Technical Field
The embodiment of the invention relates to the technical field of Internet, in particular to a method and a device for predicting a distribution portrait of a distribution object.
Background
With the deep development of O2O, logistics distribution systems develop rapidly, and daily orders exceed ten million quantity levels. For a large number of orders, it is important to improve the order delivery quality and delivery rate.
In the prior art, when an order is distributed, the order is generally distributed based on characteristics of a distribution object, such as order taking capability, a distribution area and the like, so that order information, order data and the like of the order are matched with the distribution object to the greatest extent, and distribution efficiency is improved. Data such as receipt ability and delivery area of the delivery target can be obtained by representing the delivery target. For example, order information distributed to the distribution object by the distribution platform is obtained, the distribution image is carried out on the distribution object by counting the order information, and data such as the order taking capability and the distribution area of the distribution object are obtained. However, when the distribution object can receive orders distributed by multiple distribution platforms, different distribution platforms cannot acquire the order information of other distribution platforms, and only according to the order information of each distribution platform, the real image of the distribution object cannot be acquired, which results in the loss of distribution efficiency when distributing the orders.
Therefore, there is a need for a method for predicting a delivery image of a delivery object without being limited by order information of a delivery platform, so as to obtain a true image of the delivery object.
Disclosure of Invention
In view of the above, embodiments of the present invention are provided to provide a method and an apparatus for predicting delivery images of delivery objects, which overcome or at least partially solve the above problems.
According to an aspect of an embodiment of the present invention, there is provided a method for predicting a delivery profile of a delivery object, including:
collecting delivery order information and track information of each first delivery object in the first delivery object set, and carrying out delivery state marking processing on the track information according to the delivery order information to obtain sample data;
training the state multi-classification label model according to the sample data to obtain a trained state multi-classification label model;
for any second delivery object in the second delivery object set, collecting track information of the second delivery object, and inputting the track information of the second delivery object into the trained state multi-classification label model to obtain track information after the delivery state marking processing;
and obtaining a distribution image of the second distribution object according to the track information after the marking treatment of the distribution state.
Optionally, each first delivery object in the first delivery object set and each second delivery object in the second delivery object set have different role attribute information; the role attribute information is set according to the delivery platform information to which the delivery object belongs.
Optionally, after collecting the delivery order information and the trajectory information of each first delivery object in the first delivery object set, and/or after collecting the trajectory information of the second delivery object, the method further includes:
carrying out track integration processing on the track information;
the track integration processing includes: carrying out resampling and/or filtering processing to remove interference information; carrying out grid conversion processing to obtain a plurality of grid space information of continuous time points; and carrying out coarse-grained processing on the plurality of grid space information of the continuous time points to obtain a grid track sequence of the continuous time points.
Optionally, the delivery order information includes order statuses at different time points; the order state comprises an order waiting state, an order receiving state, an order taking state, a distribution process state and/or an order sending completion state; the track information comprises a grid track sequence of continuous time points;
marking the delivery state of the track information according to the delivery order information, and obtaining sample data further comprises:
and carrying out delivery state marking processing on the grid track sequence contained in the track information according to the same time point in the track information of the first delivery object and the delivery order information of the first delivery object to obtain the grid track sequence for marking each order state.
Optionally, training the state multi-class label model according to the sample data, and obtaining the trained state multi-class label model further includes:
analyzing the track information by using a bag-of-words model, and determining a continuous vector relation of the track information;
and inputting the track information and the continuous vector relationship of the track information into the state multi-class label model for training, and adjusting the training parameters of the state multi-class label model according to the track information subjected to the marking treatment of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-class label model.
Optionally, the delivery order information further includes order state influence factors at different time points;
inputting the track information and the continuous vector relationship of the track information into a state multi-classification label model for training, adjusting the training parameters of the state multi-classification label model according to the track information subjected to the marking processing of the delivery state and the continuous vector relationship of the track information, and obtaining the trained state multi-classification label model further comprises the following steps:
and inputting order state influence factors, track information and continuous vector relations of the track information at different time points into the state multi-classification label model for training, and adjusting training parameters of the state multi-classification label model according to the track information subjected to marking processing in the delivery state and the continuous vector relations of the track information to obtain the trained state multi-classification label model.
Optionally, the obtaining of the delivery image of the second delivery object according to the track information after the marking process of the delivery state further includes:
extracting the order taking state and the order sending completion state marked in the track information after the marking processing of the distribution state;
matching the order state according to the order taking state and the order sending completion state to obtain at least one piece of estimated order information matched with the track information; the estimated order information comprises estimated order time, an order taking area and/or an order sending area;
obtaining a distribution image of a second distribution object according to the estimated order information; the delivery image of the second delivery object comprises the order taking capability, the order taking area, the order sending area, the area activity and/or the preference degree of the delivery platform of the second delivery object.
Optionally, the method further comprises:
and according to the matching degree of the distribution image of the second distribution object and the order information of each distribution platform, carrying out order distribution on the second distribution object.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for predicting a delivery image of a delivery target, including:
the first collecting module is suitable for collecting the distribution order information and the track information of each first distribution object in the first distribution object set, and carrying out distribution state marking processing on the track information according to the distribution order information to obtain sample data;
the training module is suitable for training the state multi-class label model according to the sample data to obtain a trained state multi-class label model;
the second collecting module is suitable for collecting track information of any second delivery object in the second delivery object set, inputting the track information of the second delivery object into the trained state multi-classification label model and obtaining the track information after the delivery state marking treatment;
and the drawing module is suitable for marking the processed track information according to the distribution state to obtain a distribution drawing of the second distribution object.
Optionally, each first delivery object in the first delivery object set and each second delivery object in the second delivery object set have different role attribute information; the role attribute information is set according to the delivery platform information to which the delivery object belongs.
Optionally, the apparatus further comprises:
the track integration module is suitable for carrying out track integration processing on the track information; the track integration processing includes: resampling and/or filtering the track information to remove interference information; carrying out grid conversion processing to obtain a plurality of grid space information of continuous time points; and carrying out coarse-grained processing on the plurality of grid space information of the continuous time points to obtain a grid track sequence of the continuous time points.
Optionally, the delivery order information includes order statuses at different time points; the order state comprises an order waiting state, an order receiving state, an order taking state, a distribution process state and/or an order sending completion state; the track information comprises a grid track sequence of continuous time points;
the first collection module is further adapted to:
and carrying out delivery state marking processing on the grid track sequence contained in the track information according to the same time point in the track information of the first delivery object and the delivery order information of the first delivery object to obtain the grid track sequence for marking each order state.
Optionally, the training module is further adapted to:
analyzing the track information by using a bag-of-words model, and determining a continuous vector relation of the track information;
and inputting the track information and the continuous vector relationship of the track information into the state multi-class label model for training, and adjusting the training parameters of the state multi-class label model according to the track information subjected to the marking treatment of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-class label model.
Optionally, the delivery order information further includes order state influence factors at different time points;
the training module is further adapted to:
and inputting order state influence factors, track information and continuous vector relations of the track information at different time points into the state multi-classification label model for training, and adjusting training parameters of the state multi-classification label model according to the track information subjected to marking processing in the delivery state and the continuous vector relations of the track information to obtain the trained state multi-classification label model.
Optionally, the portrait module is further adapted to:
extracting the order taking state and the order sending completion state marked in the track information after the marking processing of the distribution state;
matching the order state according to the order taking state and the order sending completion state to obtain at least one piece of estimated order information matched with the track information; the estimated order information comprises estimated order time, an order taking area and/or an order sending area;
obtaining a distribution image of a second distribution object according to the estimated order information; the delivery image of the second delivery object comprises the order taking capability, the order taking area, the order sending area, the area activity and/or the preference degree of the delivery platform of the second delivery object.
Optionally, the apparatus further comprises:
and the distribution module is suitable for distributing orders for the second distribution objects according to the matching degree of the distribution images of the second distribution objects and the order information of each distribution platform.
According to still another aspect of an embodiment of the present invention, there is provided a computing device including: the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the prediction method of the distribution image of the distribution object.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform an operation corresponding to the method for predicting a distribution image of a distribution object as described above.
According to the method and the device for predicting the distribution images of the distribution objects, which are provided by the embodiment of the invention, the distribution order information and the track information of each first distribution object in the first distribution object set are collected, and the distribution state marking processing is carried out on the track information according to the distribution order information to obtain sample data; training the state multi-classification label model according to the sample data to obtain a trained state multi-classification label model; for any second delivery object in the second delivery object set, collecting track information of the second delivery object, and inputting the track information of the second delivery object into the trained state multi-classification label model to obtain track information after state marking processing; and obtaining a distribution image of the second distribution object according to the track information subjected to the state marking processing. And carrying out delivery state marking processing on the track information by using the obtainable delivery order information and track information of the first delivery object, so that the track information and the delivery order information establish an incidence relation. And training sample data obtained based on the marking processing of the distribution state, finishing the marking processing of the distribution state of the track information of the second distribution object, and determining the corresponding distribution state through the track information, so that the distribution portrait of the second distribution object can be obtained based on the track information after the marking processing of the distribution state, and the limitation that the distribution portrait needs to obtain the distribution order information of the distribution platform is avoided.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the embodiments of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for predicting a delivery profile of a delivery object according to an embodiment of the invention;
FIG. 2 is a flow chart illustrating a method for predicting a delivery profile of a delivery object according to another embodiment of the present invention;
FIG. 3 is a block diagram showing a configuration of an apparatus for predicting delivery of a delivery image by a delivery object according to an embodiment of the present invention;
FIG. 4 shows a schematic structural diagram of a computing device according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 is a flowchart illustrating a method for predicting a delivery profile of a delivery object according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S101, collecting distribution order information and track information of each first distribution object in the first distribution object set, and carrying out distribution state marking processing on the track information according to the distribution order information to obtain sample data.
In this embodiment, each first delivery object of the first delivery object set is a delivery object dedicated to a single delivery platform, and based on the single delivery platform, all delivery order information of each first delivery object in the first delivery object set may be collected, so as to ensure integrity of the collected delivery order information. The trajectory information of the first delivery object may be collected based on the delivery platform, or the trajectory information of the first delivery object may be obtained based on the position information by collecting the position information periodically uploaded by the delivery device and the delivery apparatus carried by the first delivery object on the premise of the authorization permission of the first delivery object.
The delivery order information includes order statuses at different time points, such as various order statuses of waiting for an order, receiving an order, waiting for taking an order, in the delivery process, completing the delivery, and the like. The track information comprises position information of different time points, and the track information of the same time point is subjected to delivery state marking processing according to the delivery order information and the time points in the track information. And marking the position information of the time point as the order taking state according to the time point corresponding to the order taking state, thereby obtaining sample data which can be used for model training. The track information is used as input data of sample data, and the track information (including marking order states) after the marking processing of the distribution state is used as output data of the sample data, so that training is facilitated.
And S102, training the state multi-class label model according to the sample data to obtain the trained state multi-class label model.
And inputting the obtained sample data into a state multi-classification label model for training. The state multi-classification marking model is used for classifying and marking the track information into a plurality of order states.
The track information can present characteristics such as needing to stay at a certain position, the same position information appears for multiple times in preset unit time and the like according to distribution practice, the track information has continuous characteristics such as position continuity, time continuity and the like, based on the characteristics, the track information can be converted into natural language, such as continuous natural language words, the track information is analyzed by utilizing a bag-of-words model, and the characteristics of each position point in the track information are determined. Specifically, the bag-of-words model is used for analyzing the frequency of occurrence of the same position information in the track information, the stay time of the position information and the like, determining the characteristics of the position points, and combining the continuous characteristics of the track information, the continuous vector relationship of the track information can be determined. And inputting the track information and the continuous vector relationship of the track information into the state multi-classification label model for training, and adjusting the training parameters of the state multi-classification label model according to the track information subjected to the marking treatment of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-classification label model.
Further, in the actual distribution process, the distribution state marking process of the track information of the distribution object and the order state is also influenced by the outside. The delivery order information also comprises order state influence factors at different time points, such as weather, holidays, time periods of delivery and the like which influence the update of the delivery order state. In order to guarantee the accuracy of the state multi-class label model training, order state influence factors, track information and continuous vector relations of the track information at different time points are input into the state multi-class label model for training, training parameters of the state multi-class label model are adjusted according to the track information after the delivery state marking processing and the continuous vector relations of the track information, and the trained state multi-class label model is obtained.
Step S103, collecting track information of any second delivery object in the second delivery object set, inputting the track information of the second delivery object into the trained state multi-classification label model, and obtaining the track information after the marking processing of the delivery state.
In this embodiment, each first delivery object in the first delivery object set and each second delivery object in the second delivery object set have different role attribute information. The role attribute information is set according to the delivery platform information to which the delivery object belongs. The role attribute information of the first distribution object in the first distribution object set is a distribution object which belongs to a single distribution platform exclusively; the role attribute information of each second delivery object in the second delivery object set is a delivery object belonging to a plurality of different delivery platforms at the same time, and each delivery platform can only collect delivery order information allocated to the second delivery object by the delivery platform, and cannot acquire the delivery order information of all the delivery platforms of the second delivery object.
The role attribute information of the first delivery object and the second delivery object may be set according to application information installed in the delivery equipment used by the delivery objects, and when only application information specifying a delivery platform or a single delivery platform is installed in the delivery equipment used by the delivery objects, the first delivery object is identified; when the distribution equipment used by the distribution object is provided with the application information of a plurality of different distribution platforms, the distribution equipment is a second distribution object; the obtaining of the application information installed in the distribution device may determine the number, name, and the like of the application information of the installed distribution platform by scanning whether the distribution device is installed with the application information of the distribution platform through a legal interface (e.g., UrlScheme of the IOS) provided by an IOS platform, an android platform, and the like used by a terminal of the distribution device. And determining the role attribute information of the delivery object according to the determined application information of the installed delivery platform. Alternatively, the determination may be made according to the basic information of the delivery object, and if the basic information of the delivery object indicates that the delivery object belongs to a plurality of different delivery platforms at the same time, the delivery object is determined to be the second delivery object. The setting of the specific role attribute information may be set according to the implementation, and is not limited herein.
After the second delivery objects are determined, trajectory information of the second delivery objects may be collected by a delivery device, such as the second delivery objects, for any second delivery object in the second delivery object set. And inputting the track information of the second delivery object into the trained state multi-classification marking model to obtain the track information after the delivery state marking treatment.
And step S104, obtaining a distribution image of a second distribution object according to the track information after the marking processing of the distribution state.
According to the track information after the marking processing of the distribution state, the order number can be determined according to each order state. For example, according to the order taking state and the order sending completion state in the order states, it can be determined that an order is sent to completion. By matching the order taking state and the order sending completion state, the estimated order information of the second delivery object can be obtained, so that the daily delivery of the second delivery object can be drawn according to the estimated order information, and the delivery drawing of the second delivery object can be determined, such as the order taking capability of the delivery order of the second delivery object, the daily order taking range and the order sending range of the delivery order of the second delivery object.
The estimated order information of the second distribution object is obtained based on the track information after the marking processing of the distribution state, and then the distribution portrait of the second distribution object can be obtained without depending on the distribution order information of the second distribution object, so that the problems that the second distribution object cannot obtain all the distribution order information, the distribution portrait is inaccurate and the like are solved.
According to the method for predicting the distribution image of the distribution object, provided by the embodiment of the invention, the distribution order information and the track information of each first distribution object in the first distribution object set are collected, and the distribution state marking processing is carried out on the track information according to the distribution order information to obtain sample data; training the state multi-classification label model according to the sample data to obtain a trained state multi-classification label model; for any second delivery object in the second delivery object set, collecting track information of the second delivery object, and inputting the track information of the second delivery object into the trained state multi-classification label model to obtain track information after state marking processing; and obtaining a distribution image of the second distribution object according to the track information subjected to the state marking processing. And carrying out delivery state marking processing on the track information by using the obtainable delivery order information and track information of the first delivery object, so that the track information and the delivery order information establish an incidence relation. And training sample data obtained based on the marking processing of the distribution state, finishing the marking processing of the distribution state of the track information of the second distribution object, and determining the corresponding distribution state through the track information, so that the distribution portrait of the second distribution object can be obtained based on the track information after the marking processing of the distribution state, and the limitation that the distribution portrait needs to obtain the distribution order information of the distribution platform is avoided.
Fig. 2 is a flowchart illustrating a method for predicting a delivery profile of a delivery object according to another embodiment of the present invention, as shown in fig. 2, the method includes the steps of:
step S201, collecting delivery order information and trajectory information of each first delivery object in the first delivery object set, and performing trajectory integration processing on the trajectory information.
After the track information of the first delivery object is collected, because the position information contained in the track information generally mainly comprises GPS information, the problems of uneven GPS sampling, overlarge noise, GPS offset and the like often exist, the GPS coordinate position is too discrete, the delivery state marking processing is not facilitated directly according to the track information, and the track information needs to be subjected to track integration processing so as to be more standardized and be used as sample data for model training.
Specifically, the track integration processing includes: for example, the track information is first resampled and/or filtered to eliminate the interference information in the track information, so that the track information is more suitable for the actual distribution process. And then, carrying out grid conversion processing on the track information, for example, based on but not limited to algorithms such as geohash, S2 and the like, converting the track information into a plurality of grid space information of continuous time points, and carrying out coarse-grained processing on the plurality of grid space information of the continuous time points to obtain a grid track sequence of the continuous time points, so that model training based on the grid track sequence is facilitated. When the grid space information is subjected to coarse graining treatment, proper granularity needs to be selected for coarse graining treatment according to actual conditions, so that the problems of accurate training and the like caused by over-fine granularity or over-coarse granularity are avoided. After the track information is subjected to the track integration processing, the obtained grid track sequence may be a sequence of grid space information at predetermined time intervals. If the distribution object stays at a certain position for a long time, the same grid space information exists in the obtained grid track sequence at different time points.
Here, in order to train more accurately, it is necessary to collect a large amount of trajectory information of each first delivery object, where the trajectory information includes real-time trajectory information and historical trajectory information, so as to train.
And S202, carrying out delivery state marking processing on the track information according to the delivery order information to obtain sample data.
And after the track information is subjected to track integration processing, the track information comprises a grid track sequence of continuous time points. And carrying out delivery state marking processing on the grid track sequence contained in the track information according to the same time point in the track information of the first delivery object and the delivery order information of the first delivery object to obtain the grid track sequence for marking each order state. A plurality of different grid space information corresponding to the same order state may exist in the network track sequence, such as corresponding to a waiting order state, or corresponding to a state in the distribution process; the same grid space information at different time points may correspond to the same order state in the network track sequence, for example, waiting for order taking, the order needs to be made at the same position, the distribution object stays at the position, and the same grid space information at a plurality of different time points corresponds to the order waiting state.
Based on the track information after the track integration processing, the marking processing of the delivery state is more conveniently carried out according to the time point correspondence, the standard of sample data is guaranteed, and the training of the state multi-classification marking model is more favorably carried out.
And step S203, training the state multi-class label model according to the sample data to obtain the trained state multi-class label model.
And analyzing the track information after track integration processing by using a bag-of-words model, determining the characteristics of the grid track sequence of continuous time points, and determining the continuous vector relation of the track information.
And taking the track information after the track integration processing as sample input data, and training the state multi-class label model by combining the continuous vector relation of the track information, wherein the specific training process refers to the description of the step 102 and is not repeated herein.
Step S204 is to collect trajectory information of the second delivery objects for any second delivery object in the second delivery object set, and perform trajectory integration processing on the trajectory information.
The embodiment is suitable for the first delivery object which is exclusively owned by the single delivery platform and the second delivery object which is part of the single delivery platform, so that the track information of the second delivery object can be conveniently collected under the condition that the second delivery object is authorized. The track information includes all track information of the second delivery object in the working process, and includes track information corresponding to the delivery order information of the second delivery object on the delivery platform, and track information corresponding to the delivery order information of the second delivery object on other part-of-the-job delivery platforms. In the present embodiment, the second delivery object may be not limited to the above-described configuration, and when the second delivery object is authorized, even if the second delivery object does not function as the delivery platform, the trajectory information or the historical trajectory information of the second delivery object may be collected according to the second delivery object authorization, and the delivery image of the second delivery object may be determined based on the trajectory information or the historical trajectory information, so that the order may be directly distributed according to the delivery image of the second delivery object when the second delivery object operates as the delivery platform in the following period.
The collected trajectory information of the second delivery objects may be subjected to trajectory integration processing to make the trajectory information more standard. The process of performing the track integration processing on the track information of the second delivery object may refer to the process of performing the track integration processing on the track information of the first delivery object in step S201, and is not described herein again.
When the trajectory information of the second delivery object is collected, the real-time trajectory information of the second delivery object may be collected, or the historical trajectory information of the second delivery object may be collected, so that the delivery figure of the second delivery object can be obtained more accurately by collecting a large amount of historical trajectory information.
Step S205, inputting the track information of the second delivery object into the trained state multi-classification label model to obtain the track information after the delivery state marking processing.
The track information is related to the distribution order information, the distribution order information has an overlapped area, and the track information of the distribution objects has specific characteristics when the distribution order information is completed, so that the track information of the second distribution object after marking treatment of the distribution state can be obtained according to the trained state multi-classification marking model, the corresponding relation between the track information of the second distribution object and the order state is determined, and the estimated order information of the second distribution object can be obtained through reverse deduction.
Step S206, according to the track information after the marking processing of the distribution state, a distribution image of the second distribution object is obtained.
And extracting the order taking state and the order sending completion state marked in the track information after the marking processing of the distribution state, wherein the order taking state indicates the starting execution of the distribution order information, and the order sending completion state indicates the completion of the execution of the distribution order information. The order state matching process can be performed by extracting the order taking state and the order sending completion state, and the order taking state and the order sending completion state, which differ by a preset time (e.g., 30 minutes) at time points, can be one-to-one matched by using a matching algorithm (e.g., a keyword matching algorithm such as an order state, a time point, and the like, which is not limited herein), so as to obtain at least one piece of estimated order information matched with the track information. The estimated order information comprises estimated order time, order taking area, order sending area and other information. And taking a set of grid space information of the track information corresponding to the order state, namely a taking order area, and sending a set of grid space information of the track information corresponding to the order completion state, namely a sending order area. And according to the time point corresponding to the order taking state, the estimated order time can be roughly determined. When the order taking state and the order delivery completion state are matched, whether the order taking state and the order delivery completion state are the same as the order taking state and the order delivery completion state of the distribution order information or not can be not considered, and the estimated order information can be obtained only through one-to-one matching of the order taking state and the order delivery completion state.
The delivery image of the second delivery object can be obtained according to the estimated order information. The delivery image of the second delivery object comprises the list carrying capacity, the list taking area, the list sending area, the area activity, the preference degree of the delivery platform and the like of the second delivery object. The order taking capability, that is, the number of orders that can be simultaneously received by the second distribution object, can be obtained by counting the number of estimated order information in unit time. The waybill capability may be calculated by taking a time period as a unit, or may be calculated by taking a day as a unit, and is not limited herein. The order taking region and the order sending region of each piece of estimated order information are counted, so that the order taking region and the order sending region of the second distribution object which are more active can be obtained. By counting the respective estimated quantity of the order information in the order taking area and the order sending area, the area activeness (represented by the estimated quantity of the order information) of the second distribution object in each area of the order taking area and the order sending area can be obtained. Furthermore, the distribution order information of the second distribution object on the current distribution platform can be collected, the distribution order information is compared with the estimated order information, and the estimated order information which does not belong to the current distribution platform can be screened out, so that the order quantity of the second distribution object receiving other distribution platforms can be determined, and the preference degree of the second distribution object on the distribution platform can be calculated.
Step S207, according to the matching degree of the distribution image of the second distribution object and the order information of each distribution platform, order distribution is carried out on the second distribution object.
According to the determined distribution image of the second distribution object, the order distribution of the second distribution object by each distribution platform can be facilitated. Specifically, the order taking region, the order sending region and the like can be determined according to the current order information of the distribution platform, matching is performed according to the order taking region, the order sending region, the region activity degree and the like in the distribution image of the second distribution object, and when the matching degree is higher than a preset threshold value, order distribution is performed on the second distribution object; or, when the order receiving quantity of the second delivery objects on the current delivery platform is far smaller than the order taking capacity of the second delivery objects, the order distribution can be performed on the second delivery objects according to the comparison between the order receiving quantity of the second delivery objects on the current delivery platform and the order taking capacity of the second delivery objects.
In an alternative embodiment, the first delivery object is a delivery object specific to the delivery platform a, such as a monopoly rider hired by the takeaway platform to complete the instant delivery work, and the second delivery object is a delivery object belonging to the delivery platform a and other delivery platforms, such as b and c, such as a crowd-sourced rider receiving a plurality of takeaway platform tasks (the instant delivery task pushed by the takeaway platform is completed through a crowd-sourced application of the takeaway platform). For the distribution platform a, all the distribution order information allocated to the first distribution object can be conveniently acquired, and the distribution portrait of the first distribution object can be completely obtained based on all the distribution order information. For the second delivery object, the delivery platform a can only acquire the delivery order information of the second delivery object on the delivery platform, cannot acquire all the delivery order information of the second delivery object, and cannot acquire a complete delivery image of the second delivery object only based on the delivery order information of the delivery platform a. In the embodiment, the delivery state marking processing is performed on the track information of the first delivery object to obtain sample data to train the state multi-classification marking model, so that when the delivery order information of the second delivery object cannot be completely obtained, the delivery order state corresponding to the track information can be obtained through the track information, the estimated order information of the second delivery object is further obtained, and the delivery portrait of the second delivery object is obtained based on the estimated order information.
According to the method for predicting the distribution object distribution portrait provided by the embodiment of the invention, the track information is subjected to track integration processing, and the track information of a grid track sequence containing continuous time points is obtained by adopting a grid space information mode, so that the track information is more standard, and the model training is more facilitated. And obtaining the track information of the second delivery object after the delivery state marking treatment by using the trained state multi-classification marking model, analyzing the track information, and obtaining the estimated order information, so that the delivery image of the second delivery object can be obtained, and on one hand, the distribution image is not influenced by the fact that all order information cannot be obtained, on the other hand, the order distribution can be carried out on the second delivery object based on the delivery image, and order receiving preference and the like of the second delivery object are determined.
Fig. 3 is a block diagram showing a configuration of an apparatus for predicting delivery images of delivery objects according to an embodiment of the present invention, as shown in fig. 3, the apparatus including:
the first collecting module 310 is adapted to collect the delivery order information and the track information of each first delivery object in the first delivery object set, and perform delivery state marking processing on the track information according to the delivery order information to obtain sample data.
The training module 320 is adapted to train the state multi-class label model according to the sample data to obtain a trained state multi-class label model.
The second collecting module 330 is adapted to collect trajectory information of any second delivery object in the second delivery object set, and input the trajectory information of the second delivery object into the trained state multi-class label model to obtain the trajectory information after the delivery state marking process.
The image module 340 is adapted to obtain a distribution image of the second distribution object according to the track information after the marking process of the distribution status.
Optionally, the apparatus further comprises: a trajectory integration module 350.
A track integration module 350, adapted to perform track integration processing on the track information; the track integration processing includes: resampling and/or filtering the track information to remove interference information; carrying out grid conversion processing to obtain a plurality of grid space information of continuous time points; and carrying out coarse-grained processing on the plurality of grid space information of the continuous time points to obtain a grid track sequence of the continuous time points.
Optionally, the first collecting module 310 is further adapted to: and carrying out delivery state marking processing on the grid track sequence contained in the track information according to the same time point in the track information of the first delivery object and the delivery order information of the first delivery object to obtain the grid track sequence for marking each order state.
Optionally, the training module 320 is further adapted to: analyzing the track information by using a bag-of-words model, and determining a continuous vector relation of the track information; and inputting the track information and the continuous vector relationship of the track information into the state multi-class label model for training, and adjusting the training parameters of the state multi-class label model according to the track information subjected to the marking treatment of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-class label model.
Optionally, the training module 320 is further adapted to: and inputting order state influence factors, track information and continuous vector relations of the track information at different time points into the state multi-classification label model for training, and adjusting training parameters of the state multi-classification label model according to the track information subjected to marking processing in the delivery state and the continuous vector relations of the track information to obtain the trained state multi-classification label model.
Optionally, portrait module 340 is further adapted to: extracting the order taking state and the order sending completion state marked in the track information after the marking processing of the distribution state; matching the order state according to the order taking state and the order sending completion state to obtain at least one piece of estimated order information matched with the track information; the estimated order information comprises estimated order time, an order taking area and an order sending area; obtaining a distribution image of a second distribution object according to the estimated order information; the delivery image of the second delivery object comprises the list carrying capacity, the list taking area, the activity of the list sending area and/or the preference degree of the delivery platform of the second delivery object.
Optionally, the apparatus further comprises: an assignment module 360.
The distribution module 360 is adapted to distribute the order for the second distribution object according to the matching degree between the distribution image of the second distribution object and the order information of each distribution platform.
The descriptions of the modules refer to the corresponding descriptions in the method embodiments, and are not repeated herein.
According to the prediction device for the distribution image of the distribution object, which is provided by the embodiment of the invention, the distribution state marking processing is carried out on the track information by using the available distribution order information and track information of the first distribution object, so that the track information and the distribution order information establish an association relation. And training sample data obtained based on the marking processing of the distribution state, finishing the marking processing of the distribution state of the track information of the second distribution object, and determining the corresponding distribution state through the track information, so that the distribution portrait of the second distribution object can be obtained based on the track information after the marking processing of the distribution state, and the limitation that the distribution portrait needs to obtain the distribution order information of the distribution platform is avoided.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the executable instruction can execute the method for predicting the distribution image of the distribution object in any method embodiment.
Fig. 4 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein:
the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408.
A communication interface 404 for communicating with network elements of other devices, such as clients or other servers.
The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the embodiment of the method for predicting the distribution image of the distribution object.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU, or an application specific Integrated circuit asic, or one or more Integrated circuits configured to implement an embodiment of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Specifically, the program 410 may be used to cause the processor 402 to execute a method of predicting a delivery target delivery image in any of the above-described method embodiments. The specific implementation of each step in the program 410 may refer to the corresponding steps and corresponding descriptions in the units in the foregoing embodiment for predicting the distribution image of the distribution object, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of embodiments of the present invention as described herein, and any descriptions of specific languages are provided above to disclose preferred embodiments of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of an embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of and form different embodiments of the invention. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present invention. Embodiments of the invention may also be implemented as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing embodiments of the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the embodiments of the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method for predicting a delivery profile of a delivery object, comprising:
collecting distribution order information and track information of each first distribution object in a first distribution object set, and carrying out distribution state marking processing on the track information according to the distribution order information to obtain sample data;
training the state multi-classification label model according to the sample data to obtain a trained state multi-classification label model;
for any second delivery object in a second delivery object set, collecting track information of the second delivery object, and inputting the track information of the second delivery object into a trained state multi-classification label model to obtain track information after marking treatment of delivery states;
and obtaining a distribution image of a second distribution object according to the track information after the marking treatment of the distribution state.
2. The method of claim 1, wherein each first delivery object in the first set of delivery objects has different role attribute information than each second delivery object in the second set of delivery objects; the role attribute information is set according to the delivery platform information to which the delivery object belongs.
3. The method of claim 1, wherein after the collecting delivery order information and trajectory information of each first delivery object in the first set of delivery objects, and/or after the collecting trajectory information of the second delivery object, the method further comprises:
carrying out track integration processing on the track information;
the trajectory integration process includes: carrying out resampling and/or filtering processing to remove interference information; carrying out grid conversion processing to obtain a plurality of grid space information of continuous time points; and carrying out coarse-grained processing on the plurality of grid space information of the continuous time points to obtain a grid track sequence of the continuous time points.
4. The method of any of claims 1-3, wherein the delivery order information includes order status at different points in time; the order state comprises an order waiting state, an order receiving state, an order taking state, a distribution process state and/or an order sending completion state; the track information comprises a grid track sequence of continuous time points;
the marking process of the delivery state is carried out on the track information according to the delivery order information, and obtaining sample data further comprises:
and carrying out delivery state marking processing on the grid track sequence contained in the track information according to the same time point in the track information of the first delivery object and the delivery order information of the first delivery object to obtain the grid track sequence for marking each order state.
5. The method according to any one of claims 1-4, wherein said training a state multi-class label model according to said sample data, obtaining a trained state multi-class label model further comprises:
analyzing the track information by using a bag-of-words model, and determining a continuous vector relation of the track information;
and inputting the track information and the continuous vector relationship of the track information into the state multi-class label model for training, and adjusting the training parameters of the state multi-class label model according to the track information subjected to the marking treatment of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-class label model.
6. The method of claim 5 wherein the delivery order information further comprises order status impact factors at different points in time;
the inputting the track information and the continuous vector relationship of the track information into the state multi-classification label model for training, and adjusting the training parameters of the state multi-classification label model according to the track information after the marking processing of the delivery state and the continuous vector relationship of the track information to obtain the trained state multi-classification label model further comprises:
and inputting order state influence factors, track information and continuous vector relations of the track information at different time points into the state multi-classification label model for training, and adjusting training parameters of the state multi-classification label model according to the track information subjected to marking processing in the delivery state and the continuous vector relations of the track information to obtain the trained state multi-classification label model.
7. The method according to any one of claims 1 to 6, wherein the obtaining of the delivery image of the second delivery object according to the track information after the delivery state marking process further comprises:
extracting the order taking state and the order sending completion state marked in the track information after the marking processing of the distribution state;
matching the order state according to the order taking state and the order sending completion state to obtain at least one piece of estimated order information matched with the track information; the estimated order information comprises estimated order time, an order taking area and/or an order sending area;
obtaining a distribution image of a second distribution object according to the estimated order information; the delivery image of the second delivery object comprises the order taking capability, the order taking area, the order sending area, the area activity and/or the preference degree of the delivery platform of the second delivery object.
8. An apparatus for predicting a delivery image of a delivery object, comprising:
the first collecting module is suitable for collecting distribution order information and track information of each first distribution object in a first distribution object set, and carrying out distribution state marking processing on the track information according to the distribution order information to obtain sample data;
the training module is suitable for training the state multi-class label model according to the sample data to obtain a trained state multi-class label model;
the second collecting module is suitable for collecting track information of a second delivery object aiming at any second delivery object in a second delivery object set, and inputting the track information of the second delivery object into the trained state multi-classification label model to obtain track information after the delivery state marking treatment;
and the drawing module is suitable for obtaining a distribution drawing of the second distribution object according to the track information subjected to marking processing in the distribution state.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction for causing the processor to perform operations corresponding to the method for predicting a delivery image of a delivery object as claimed in any one of claims 1 to 7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of predicting a delivery profile of a delivery object as recited in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010677070.6A CN111754050A (en) | 2020-07-14 | 2020-07-14 | Method and apparatus for predicting delivery image of delivery object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010677070.6A CN111754050A (en) | 2020-07-14 | 2020-07-14 | Method and apparatus for predicting delivery image of delivery object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754050A true CN111754050A (en) | 2020-10-09 |
Family
ID=72710268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010677070.6A Pending CN111754050A (en) | 2020-07-14 | 2020-07-14 | Method and apparatus for predicting delivery image of delivery object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754050A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115222109A (en) * | 2022-06-28 | 2022-10-21 | 浙江口碑网络技术有限公司 | Information processing method, device, medium, and apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005124614A1 (en) * | 2004-06-22 | 2005-12-29 | Kikuchi Sheet Industry Co., Ltd. | Order receiving system, terminal device, server device, transmission target retrieving device, advertisement, advertising medium, mobile unit, order receiving method, transmission target retrieving method, and information processing method |
| CN105160880A (en) * | 2015-09-24 | 2015-12-16 | 滴滴（中国）科技有限公司 | Method and device for estimating vehicle passenger state |
| CN107818431A (en) * | 2016-09-14 | 2018-03-20 | 北京京东尚科信息技术有限公司 | A kind of method and system that order track data is provided |
| CN109685429A (en) * | 2018-12-27 | 2019-04-26 | 拉扎斯网络科技（上海）有限公司 | Distribution capacity determines method, apparatus, electronic equipment and storage medium |
| CN110363453A (en) * | 2018-03-26 | 2019-10-22 | 北京京东振世信息技术有限公司 | Distribution information method for visualizing and device |
| US20190362422A1 (en) * | 2018-05-24 | 2019-11-28 | Royal Bank Of Canada | Systems and methods for quantitative order routing |
-
2020
- 2020-07-14 CN CN202010677070.6A patent/CN111754050A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005124614A1 (en) * | 2004-06-22 | 2005-12-29 | Kikuchi Sheet Industry Co., Ltd. | Order receiving system, terminal device, server device, transmission target retrieving device, advertisement, advertising medium, mobile unit, order receiving method, transmission target retrieving method, and information processing method |
| CN105160880A (en) * | 2015-09-24 | 2015-12-16 | 滴滴（中国）科技有限公司 | Method and device for estimating vehicle passenger state |
| CN107818431A (en) * | 2016-09-14 | 2018-03-20 | 北京京东尚科信息技术有限公司 | A kind of method and system that order track data is provided |
| CN110363453A (en) * | 2018-03-26 | 2019-10-22 | 北京京东振世信息技术有限公司 | Distribution information method for visualizing and device |
| US20190362422A1 (en) * | 2018-05-24 | 2019-11-28 | Royal Bank Of Canada | Systems and methods for quantitative order routing |
| CN109685429A (en) * | 2018-12-27 | 2019-04-26 | 拉扎斯网络科技（上海）有限公司 | Distribution capacity determines method, apparatus, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115222109A (en) * | 2022-06-28 | 2022-10-21 | 浙江口碑网络技术有限公司 | Information processing method, device, medium, and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111966729B (en) | Vehicle track data processing method, device, equipment and storage medium | |
| CN110765615B (en) | Logistics simulation method, device and equipment | |
| CN110806954A (en) | Method, device and equipment for evaluating cloud host resources and storage medium | |
| CN112633842B (en) | Task pushing method, device and system | |
| CN108806302A (en) | A kind of vehicle dispatching method and device | |
| CN111833594B (en) | Traffic flow prediction method, traffic flow prediction device, electronic device, and storage medium | |
| CN111724037B (en) | Method and device for allocating operation resources, computer equipment and readable storage medium | |
| CN109308538B (en) | Method and device for predicting transaction conversion rate | |
| CN111507762A (en) | Urban taxi demand prediction method based on multi-task co-prediction neural network | |
| CN113642938A (en) | Intelligent production management method and system | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN111369137A (en) | Distribution method, distribution device, server and storage medium of distribution tasks | |
| CN110378529B (en) | Data generation method and device, readable storage medium and electronic equipment | |
| CN113379168B (en) | Time series prediction processing method, device and equipment | |
| CN111754050A (en) | Method and apparatus for predicting delivery image of delivery object | |
| CN110543699A (en) | shared vehicle travel data simulation and shared vehicle scheduling method, device and equipment | |
| CN110826196B (en) | Industrial equipment operation data processing method and device | |
| CN110516872B (en) | Information processing method and device, storage medium and electronic equipment | |
| CN112036695A (en) | Weather information prediction method and device, readable storage medium and electronic equipment | |
| CN116668321A (en) | Network traffic prediction method, device, equipment and storage medium | |
| CN109360137B (en) | Vehicle accident assessment method, computer readable storage medium and server | |
| CN108537447A (en) | Mission effectiveness computational methods, device and the electronic equipment of satellite | |
| CN114143734A (en) | Data processing method and device for 5G Internet of things network card flow acquisition | |
| CN113238911A (en) | Alarm processing method and device | |
| CN111027823A (en) | Browser-based work order automatic forwarding method and device |
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 |