CN116862340A - Early warning method, system, equipment and medium based on-transit time prediction algorithm - Google Patents

Abstract

An early warning method, system, equipment and medium based on a duration prediction algorithm relate to the technical field of computers. The method comprises the following steps: receiving transportation task data; extracting characteristic information in the transportation task data, wherein the characteristic information comprises information such as places, vehicle types, departure point longitude and latitude, destination longitude and latitude and the like; inputting the characteristic information into a pre-trained on-road duration prediction model, and outputting an on-road duration prediction result; judging whether the transportation time length is greater than the on-road time length prediction result; if yes, generating early warning information and sending the early warning information to a processor. By implementing the technical scheme provided by the application, the abnormal transportation task is determined through the prediction of the in-transit time length, and the early warning information is pushed to the processor, so that the effect of improving the timely processing efficiency of the abnormal situation is achieved.

Description

Early warning method, system, equipment and medium based on-transit time prediction algorithm

Technical Field

The application relates to the technical field of computers, in particular to an early warning method, system, equipment and medium based on a time-in-transit prediction algorithm.

Background

With the continuous development of internet technology, the penetration of the internet is contained in various industries, and convenience and high-speed development of society are brought by the internet technology under the current age background of big data. For example, there is a wide range of uses in the logistics transportation industry, and various transportation systems have been developed, and the industry is also growing.

At present, in the traditional transport task early warning system, the functions of predicting the duration of the whole transport task and the distance between destinations, designating corresponding routes according to the destination positions and the like are included, and marking the accident positions and the like when accidents occur on the transport routes.

However, in practical application, a truck executing an operation task may encounter unexpected situations and delay time during the way, so that the truck cannot arrive at a destination on time, and a traditional transportation task early warning system cannot reflect an abnormal situation to a corresponding processor in time according to the situations, so that problems such as abnormal processing delay and the like occur.

Disclosure of Invention

The application provides an early warning method, a system, equipment and a medium based on an on-transit time prediction algorithm, which have the effect of timely pushing abnormal conditions of transportation tasks and preventing abnormal processing delay.

In a first aspect, the present application provides an early warning method based on a duration-in-transit prediction algorithm, including:

receiving transportation task data;

extracting characteristic information in the transportation task data, wherein the characteristic information comprises information such as places, vehicle types, departure point longitude and latitude, destination longitude and latitude and the like;

inputting the characteristic information into a pre-trained on-road duration prediction model, and outputting an on-road duration prediction result;

judging whether the transportation time length is greater than the on-road time length prediction result;

if yes, generating early warning information and sending the early warning information to a processor.

By adopting the technical scheme, the related data of the transportation task is received in real time, the characteristic information is extracted and input into the on-road duration prediction model to obtain the on-road duration, whether the transportation vehicle can arrive on time or not is determined by the on-road duration, and the unreachable transportation task is early-warned and pushed to a processor, so that the real-time processing capability for abnormal conditions is improved, and the problem of delayed abnormal processing is avoided.

Optionally, receiving historical shipping mission data; extracting historical characteristic information in the historical transportation task data as a first model characteristic; extracting the longitude and latitude of a historical departure point and the longitude and latitude of a destination in the historical transportation task data; calling a preset path planning API, and taking the estimated travel time and the estimated travel distance obtained by taking the longitude and latitude of the historical departure point and the longitude and latitude of the destination as the second model characteristics; inputting the first model feature and the second model feature into an initial model; training an initial model by taking a preset on-road duration interval as a training standard, wherein the preset on-road duration interval is an interval range of on-road duration meeting the preset standard, so that the initial model converges to obtain the on-road duration prediction model.

By adopting the technical scheme, the characteristic information of the historical transportation task is extracted to serve as model characteristics, the path planning API is called to obtain the expected running time and the running distance and serve as model characteristics, the model characteristics are input into the initial model, and model training is carried out on the basis of GBDT to obtain the on-road duration prediction model, so that the on-road duration prediction model can be used for accurately predicting the on-road duration.

Optionally, the initial model is a GBDT algorithm model.

By adopting the technical scheme, the model training is carried out based on the GBDT algorithm, a more accurate on-road duration prediction model can be obtained through repeated model training, and the accuracy of on-road duration prediction data is improved.

Optionally, if not, after the update time is preset at intervals, updating the statistical transportation time length and judging whether the transportation time length is greater than the in-transit time length prediction result or not.

By adopting the technical scheme, the obtained on-road time length is screened, the transportation task with the transportation time length longer than the predicted on-road time length is screened, the abnormal situation of the transportation task can be determined according to the mode, and the transportation vehicle can not arrive at the destination on time, so that early warning information is generated, and the instantaneity of processing abnormal situations is improved.

Optionally, inquiring the contact information of the processor corresponding to the transportation task, and pushing the early warning information to the processor through a preset RocketMQ message middleware.

By adopting the technical scheme, the RocketMQ message middleware is introduced to push the early warning information, so that the early warning information generation and the early warning push can be decoupled from each other, the reliability of message push is ensured, and the message push capability is improved.

Optionally, judging whether the processor processes the transportation task within a preset processing time; if not, pushing the early warning information to an upper processor.

By adopting the technical scheme, after the early warning information is pushed to the processor, if the processor does not process the transportation task of the early warning within the preset processing time, the delay warning information can be automatically pushed to the upper level of the processor, so that the abnormal condition can be conveniently and timely processed, the problem of delay caused by unprocessed processor is prevented, and economic loss is avoided.

Optionally, if yes, recording the actual completion time of the transportation task and storing the actual completion time into a database.

By adopting the technical scheme, if a processor finishes processing the early-warning transportation task within the preset processing time, the actual completion time is recorded, and the completion time is stored in the database, so that a characteristic value can be provided for updating iteration of the on-road duration prediction model.

In a second aspect of the present application, an early warning system based on a duration-in-transit prediction algorithm is provided, including:

the data receiving module is used for receiving the transportation task data;

the feature extraction module is used for extracting feature information in the transportation task data, wherein the feature information comprises information such as places, vehicle types, departure point longitude and latitude, destination longitude and latitude and the like;

the duration prediction module is used for inputting the characteristic information into a pre-trained on-road duration prediction model and outputting an on-road duration prediction result;

the early warning pushing module is used for judging whether the transportation time length is greater than the on-road time length prediction result; if yes, generating early warning information and sending the early warning information to a processor.

In a third aspect of the application, an electronic device is provided.

An early warning system based on a duration-in-transit prediction algorithm comprises a memory, a processor and a program stored in the memory and capable of running on the processor, wherein the program can be loaded and executed by the processor to realize an early warning method based on the duration-in-transit prediction algorithm.

In a fourth aspect of the application, a computer readable storage medium is provided.

A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement a pre-warning method based on a duration-in-transit prediction algorithm.

In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:

1. according to the method, the relevant data of the transportation task is received in real time, the characteristic information is extracted and input into the on-road duration prediction model to obtain the on-road duration, whether the transportation vehicle can arrive on time or not is determined through the on-road duration, and the unreachable transportation task early warning is pushed to a processor.

2. The application improves the capability of pushing the early warning information by introducing the RocketMQ message middleware to process the early warning information, can realize the function of triggering the early warning upgrading when the processor processes overtime, and ensures the reliability of message pushing in different scenes.

3. According to the application, the estimated running time and the Gooder estimated running distance information are obtained by calling the path planning API, so that more accurate model characteristics can be provided for model training, and the model training efficiency is improved.

Drawings

Fig. 1 is a schematic flow chart of an early warning method based on a duration prediction algorithm according to an embodiment of the present application.

Fig. 2 is a schematic diagram of early warning processing of an early warning method based on a duration prediction algorithm according to an embodiment of the present application.

Fig. 3 is a task list query interface diagram of an early warning method based on a time-in-transit prediction algorithm according to an embodiment of the present application.

Fig. 4 is a detailed task list interface diagram of an early warning method based on a time-in-transit prediction algorithm provided by the embodiment of the application.

Fig. 5 is a task list processing interface diagram of an early warning method based on a duration in transit prediction algorithm according to an embodiment of the present application.

Fig. 6 is a schematic structural diagram of an early warning system based on a duration prediction algorithm according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of an electronic device according to the disclosure.

Reference numerals illustrate: 601. a data receiving module; 602. a feature extraction module; 603. a duration prediction module; 604. the early warning pushing module; 700. an electronic device; 701. a processor; 702. a memory; 703. a user interface; 704. a network interface; 705. a communication bus.

Detailed Description

In order that those skilled in the art will better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments.

In describing embodiments of the present application, words such as "for example" or "for example" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "such as" or "for example" in embodiments of the application should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.

In the description of embodiments of the application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

In order to facilitate understanding of the method and system provided by the embodiments of the present application, a description of the background of the embodiments of the present application is provided before the description of the embodiments of the present application.

At present, in the logistics transportation industry, the adopted traditional transportation task early warning system cannot timely react to abnormal transportation tasks through predicting the on-road time length, and the abnormal conditions are reflected to the problems of corresponding processing personnel.

The embodiment of the application discloses an early warning method based on an on-road duration prediction algorithm, which is used for predicting on-road duration by extracting characteristic information of a transportation task, obtaining early warning information according to the on-road duration and pushing the early warning information to a processor, and is mainly used for solving the problem that abnormal conditions cannot be reflected to corresponding processors in time.

Those skilled in the art will appreciate that the problems associated with the prior art are solved by the present application, and a detailed description of a technical solution according to an embodiment of the present application is provided below, wherein the detailed description is given with reference to the accompanying drawings.

Referring to fig. 1 and 2, an early warning method based on a time-in-transit prediction algorithm includes steps S10 to S40, specifically including the following steps:

s10: transport task data is received.

Specifically, a worker can create a transportation task according to information such as a destination, a departure place and the like, and the system receives data recorded in the background of the transportation task.

S20: and extracting characteristic information in the transportation task data, wherein the characteristic information comprises information such as places, vehicle types, departure point longitudes and latitudes, destination longitudes and latitudes and the like.

Specifically, the system extracts characteristic information at a specific position in the transportation task data, the characteristic information of the position is the same as the type of the characteristic information when the preset in-transit time length prediction model is trained, the transportation task data is subjected to characteristic analysis through the existing algorithm, and the characteristic information of the vehicle type, the driver, the site, the departure point longitude and latitude, the destination longitude and latitude and the like in the transportation task data is extracted.

S30: and inputting the characteristic information into a pre-trained on-road duration prediction model, and outputting an on-road duration prediction result.

Specifically, in order to calculate the estimated time of the transportation task, the extracted characteristic information such as the vehicle type, the driver, the site, the departure point longitude and latitude, the destination longitude and latitude and the like of the transportation task is input into a on-road duration prediction model which is obtained through training of the same type of data in advance, so that the on-road duration corresponding to the transportation task is obtained, and the input characteristic information is stored in a database so as to facilitate the next model updating iteration.

On the basis of the above embodiment, the on-road duration prediction model needs to be obtained through model training, and the specific steps include S01 to S04:

s01: historical shipping task data is received.

Illustratively, historical transportation mission data is received, including information of historical sites, vehicle models, drivers, and historical departure point latitude and longitude, destination latitude and longitude, and the like.

S02: and extracting historical characteristic information in the historical transportation task data as a first model characteristic.

In an exemplary embodiment, the algorithm model training process needs to input feature information of a transportation task, when the on-road time length is predicted, the historical feature information in the historical transportation task data of each task sheet is based on historical transportation task data, wherein the historical feature information in the historical transportation task data of each task sheet comprises related information such as a place, a vehicle type, a driver identity and the like, and then the historical feature information is stored in a database as a first model feature of the input training model for training.

S03: extracting the longitude and latitude of a historical departure point and the longitude and latitude of a destination in the historical transportation task data; and calling a preset path planning API, and taking the estimated running time and the estimated running distance obtained by taking the longitude and latitude of the historical departure point and the longitude and latitude of the destination as the second model characteristics.

The path planning API is an german API, after extracting the latitude and longitude data of the departure point and the latitude and longitude data of the destination in the historical transportation task data, calling the german path planning API, then entering the departure point and the latitude and longitude of the destination into the vehicle according to the format of the latitude and longitude, selecting a designated driving strategy, for example, the driving strategy is free from congestion, the path is shortest, obtaining a planning result returned by the german path planning API after entering the vehicle, reading the planning result, namely determining the estimated driving time and the estimated driving distance, and binding the estimated driving time and the estimated driving distance into a second model feature of an input training model to store the second model feature into a database for training.

S04: inputting the first model features and second model features corresponding to the first model features into an initial model; training an initial model by taking a time-in-transit time interval of the historical time-in-transit in the historical transportation task data as a training standard, so that the initial model converges to obtain the time-in-transit time prediction model, and the preset time-in-transit time interval is a time period of the historical time-in-transit.

The first model feature and the first model feature are obtained by taking the same historical task data, the information of a place, a vehicle type, a driver and the like extracted from the historical task data and the estimated running time and the estimated running distance obtained by calling a Goldpath planning API are formed into a training model feature to be input into an initial model, the initial model is a GBDT model, the algorithm is an iterative decision tree algorithm based on the GBDT algorithm, the algorithm is composed of a plurality of decision trees, the conclusions of all the trees are accumulated to be a final answer, after the training model feature is input, the model is trained according to the output standard, for example, the historical on-road time interval takes one day as a unit, for example, within 1 day, the historical on-road time interval of a task of which a task-designated transport vehicle reaches a destination in twenty four hours is 1 day, and the historical on-road time interval of the task of which the transport vehicle reaches the destination is between 1 day and 2 days is 2 days; in other embodiments, the unit of the historical in-transit time interval may be 4 hours or other time, which is not limited in this embodiment and is reasonable. And if the output result is within the historical on-road time interval of the historical task list, the output result is used as the on-road time meeting the requirements, and then a plurality of groups of historical task data training iterations are carried out, so that the initial model converges to obtain the on-road time prediction model.

S40: judging whether the transportation time length is greater than the on-road time length prediction result; if yes, generating early warning information and sending the early warning information to a processor.

Specifically, after the on-road duration prediction model is obtained and a prediction result is output, the predicted on-road duration is screened according to a standard preset transportation duration, a transportation task mark corresponding to the actual transportation duration exceeding the predicted on-road duration is generated, corresponding early warning information is generated, and the early warning information is pushed to a processor, so that the problem of delayed transportation tasks is prevented.

The specific steps include S41 to S42:

s41: if yes, generating early warning information.

For example, due to the fact that the express delivery transportation tasks are different, transportation tasks need to be screened in combination with a specific transportation service scene, for example, in a vehicle transportation scene, a transportation vehicle C is from an a transportation center to a B transportation center, after the transportation task is finished, the next transportation task of the transportation vehicle C needs to be returned from the B transportation center to the a transportation center, at this time, a staff in the a transportation center needs to determine whether the transportation vehicle C can arrive at the a transportation center on time, if the transportation vehicle C cannot arrive at the a transportation center on time, the staff in the a transportation center needs to be notified, and the specific process includes: the system compares the on-transit time output by the on-transit time prediction model with the preset transportation time corresponding to the transportation task, screens out transportation tasks with the on-transit time longer than the preset transportation time, and calls early warning information corresponding to the transportation tasks aiming at the transportation tasks of which the transportation vehicles cannot arrive at the transportation center on time, wherein the early warning information comprises common warning information and delayed warning information, the common warning information is used for timely informing a processor that the transportation vehicles cannot arrive on time, and the delayed warning information is used for being pushed to other processors when the processor does not process in time.

S42: inquiring the contact information of the processor corresponding to the transportation task, and pushing the early warning information to the processor through a preset RocketMQ message middleware.

When the transport vehicle cannot arrive at the transfer center on time, the early warning is required to be timely and stably pushed to a designated processor, after the early warning is pushed to the processor, if the processor does not timely process a transport task, the processor cannot finish generating feedback information by a task list, and then the early warning is required to be pushed to other processors.

Referring to fig. 3 and fig. 4, it should be noted that, in the present application, the early warning information is converted into a task to be handled by using a task sheet as a carrier, and is pushed to a designated handler for processing through a dockmq message middleware, which specifically includes:

in order to process different to-be-handled logics, the system converts early warning information into to-be-handled tasks, the system is realized by setting a task list, the task list is also set to be of various types according to different transportation task data, the task list comprises common warning information, delay warning information and transportation task data and can be accurately pushed through message middleware, two vehicle scene early warning modes are designed, one of the two vehicle scene early warning modes is the capability of realizing instant and reliable pushing through the RocketMQ pushing common warning information, the other of the two vehicle scene early warning modes is the capability of realizing overtime triggering early warning upgrading through the delay warning information, the RocketMQ message middleware is introduced to enable early warning information generation, early warning information pushing and processing processes to be mutually decoupled, and the waste of computing resources to detect whether early warning should overtime upgrading or not can be avoided.

S43: judging whether the processor processes the transportation task within a preset processing time; if not, pushing the early warning information to an upper processor; if yes, recording the actual completion time of the transportation task and storing the actual completion time into a database.

After the ordinary warning message and the delayed warning message are successfully pushed to the appointed handler by the RocketMQ message middleware, the system judges whether the transportation task is finished within the preset processing time, the handler does not finish the task list to generate feedback information, the preset processing time is determined by the delay time set by the delayed warning message, the delay time can be set by a worker, the system pushes the delayed warning message to the upper level of the handler after judging that the transportation task is not processed after the set delay time interval, if the processor finishes processing the transportation task within the set delay time interval, the specific time for the completion of the transportation task is recorded, and the actual completion condition of the task list is stored in a database so as to be convenient for subsequent updating iteration.

Based on the above embodiment, the logic for processing two types of alarm messages specifically includes:

for example, for a common alarm message, different processing logic is adopted according to different generation periods of the alarm message, for example, a task list to be processed is generated for the alarm message of 12 to 17 points, and a task list to be checked is generated at other times, and the processing flows of subsequent processing persons are different due to different task list types, wherein the specific processing flows comprise: if a to-be-processed task list is generated, the to-be-processed task list needs to be appointed to fill in a form by a processor, a task list state is automatically generated according to the form content system to carry out the next processing, for example, when the processor fills in the processing incapability, feedback information is obtained, and then the task list is updated to a superior processor through a message middleware. In addition, a delay alarm message is generated simultaneously when the to-be-processed list is generated, and is used for being upgraded to the upper level of the processor in time when the processor times out and does not process the to-be-processed list, if the to-be-checked task list is generated, the processor needs to check the specific content of the early warning information, and no process of time-out upgrading exists. For the delay alarm message, the time of delay can be set by the user definition according to the actual working condition, for example, the time of delay is set to 60 minutes, the upgrade operation can be automatically triggered after the task list to be processed is generated for 60 minutes, the delay alarm message is pushed to the upper level of a processor through a message middleware, and the task list can be ended after the upper level receives the upgrade task list and completes the task list processing.

Referring to fig. 5, it should be further described that the task sheet implementation scheme provided by the present application includes the following specific functions:

the application realizes the processing of the task list based on the nailing task function to be handled, constructs the message containing the title of the early warning information, url capable of jumping to the detail page of the task list, the nailing mobile phone number of the processing person and other information, and realizes the task list pushing function in a network request mode. In addition, the task sheet has a state detection function, for example, the task sheet to be processed in the present application includes three states: in the initial state, in the processing, the ending state, in addition, there is a task sheet state of an intermediate process, the task sheet state of the intermediate process includes submitted and the like, the change of the task sheet state is related to an event executed by a processor, for example, in the event that the processor executes submitted form content, the different form contents trigger different state changes, when the form contents are filled out and cannot be processed, the upgrading of the task sheet is triggered, and if a specific processing scheme is filled out, the task sheet state is changed from the processing state to the ending state.

The task list also has the function of flow tracking, and the application stores the early warning information, the task list information, the processor operation log information and the like based on the RDS database, has the flow tracking capability of the task list, and can support information such as post analysis processing rate and the like.

The following are system embodiments of the present application that may be used to perform method embodiments of the present application. For details not disclosed in the platform embodiments of the present application, reference is made to the method embodiments of the present application.

Referring to fig. 6, a system of an early warning method based on a duration prediction algorithm according to an embodiment of the present application includes: a data receiving module 601, a feature extracting module 602, a duration predicting module 603, and an early warning pushing module 604, wherein:

a data receiving module 601, configured to receive transportation task data;

the feature extraction module 602 is configured to extract feature information in the transportation task data, where the feature information includes information such as a place, a vehicle type, a departure point longitude and latitude, and a destination longitude and latitude;

the duration prediction module 603 is configured to input the feature information into a pre-trained on-road duration prediction model, and output an on-road duration prediction result;

the early warning pushing module 604 is configured to determine whether the transportation duration is longer than the on-transit duration prediction result; if yes, generating early warning information and sending the early warning information to a processor.

It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.

The application also discloses electronic equipment. Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device 700 may include: at least one processor 701, at least one network interface 704, a user interface 703, a memory 702, at least one communication bus 705.

Wherein a communication bus 705 is used to enable connected communication between these components.

The user interface 703 may include a Display screen (Display), a Camera (Camera), and the optional user interface 703 may further include a standard wired interface, and a wireless interface.

The network interface 704 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Wherein the processor 701 may include one or more processing cores. The processor 701 connects various portions of the overall server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 702, and invoking data stored in the memory 702. Alternatively, the processor 701 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 701 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface diagram, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 701 and may be implemented by a single chip.

The Memory 702 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 702 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 702 may be used to store instructions, programs, code, sets of codes, or instruction sets. The memory 702 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 702 may also optionally be at least one storage device located remotely from the processor 701. Referring to fig. 7, an operating system, a network communication module, a user interface module, and an application program of an early warning method based on a time-in-transit prediction algorithm may be included in a memory 702 as a computer storage medium.

In the electronic device 700 shown in fig. 7, the user interface 703 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 701 may be configured to invoke an application program in the memory 702 that stores an early warning method based on a time-in-transit prediction algorithm, which when executed by the one or more processors 701, causes the electronic device 700 to perform the method as described in one or more of the embodiments above. It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.

The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.

This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims (10)

1. An early warning method based on a duration prediction algorithm is characterized by comprising the following steps:

receiving transportation task data;

extracting characteristic information in the transportation task data, wherein the characteristic information comprises information such as places, vehicle types, departure point longitude and latitude, destination longitude and latitude and the like;

inputting the characteristic information into a pre-trained on-road duration prediction model, and outputting an on-road duration prediction result;

judging whether the transportation time length is greater than the on-road time length prediction result;

if yes, generating early warning information and sending the early warning information to a processor.

2. The early warning method based on the on-transit time length prediction algorithm according to claim 1, wherein the training process of the on-transit time length prediction model comprises the following steps:

receiving historical transportation task data;

extracting historical characteristic information in the historical transportation task data as a first model characteristic;

extracting the longitude and latitude of a historical departure point and the longitude and latitude of a destination in the historical transportation task data;

calling a preset path planning API, and taking the estimated travel time and the estimated travel distance obtained by taking the longitude and latitude of the historical departure point and the longitude and latitude of the destination as the second model characteristics;

inputting the first model features and second model features corresponding to the first model features into an initial model;

training an initial model by taking a time-in-transit time interval of the historical time-in-transit in the historical transportation task data as a training standard, so that the initial model converges to obtain the time-in-transit time prediction model, and the preset time-in-transit time interval is a time period of the historical time-in-transit.

3. The early warning method based on the on-transit time prediction algorithm according to claim 2, wherein the early warning method is characterized in that: the initial model is a GBDT algorithm model.

4. The early warning method based on the on-transit time prediction algorithm according to claim 1, wherein after determining whether the transportation time is longer than the on-transit time prediction result, the method comprises:

if not, after the updating time is preset at intervals, updating the statistical transportation time length and judging whether the transportation time length is greater than the on-road time length prediction result or not.

5. The early warning method based on the on-transit time prediction algorithm according to claim 1, wherein the sending to the processor comprises:

inquiring the contact information of the processor corresponding to the transportation task, and pushing the early warning information to the processor through a preset RocketMQ message middleware.

6. The early warning method based on the on-transit time prediction algorithm according to claim 5, wherein after pushing the task sheet to a processor, the method further comprises:

judging whether the processor processes the transportation task within a preset processing time;

if not, pushing the early warning information to an upper processor.

7. The early warning method based on the on-transit time prediction algorithm according to claim 1, wherein the determining whether the processor processes the task sheet within a preset processing time further comprises:

if yes, recording the actual completion time of the transportation task and storing the actual completion time into a database.

8. A system for early warning based on a duration-in-transit prediction algorithm, the system comprising:

a data receiving module (601) for receiving transportation task data;

the feature extraction module (602) is used for extracting feature information in the transportation task data, wherein the feature information comprises information such as places, vehicle types, departure point longitude and latitude, destination longitude and latitude and the like;

the duration prediction module (603) is used for inputting the characteristic information into a pre-trained on-road duration prediction model and outputting an on-road duration prediction result;

the early warning pushing module (604) is used for judging whether the transportation time length is greater than the on-road time length prediction result; if yes, generating early warning information and sending the early warning information to a processor.

9. An electronic device comprising a processor (701), a memory (702), a user interface (703) and a network interface (704), the memory (702) being configured to store instructions, the user interface (703) and the network interface (704) being configured to communicate with other devices, the processor (701) being configured to execute the instructions stored in the memory (702) to cause the electronic device (700) to perform the method of early warning based on the on-transit time prediction algorithm according to any one of claims 1 to 7.

10. A computer readable storage medium storing instructions which, when executed, perform the pre-warning method steps of any one of claims 1-7 based on a time-in-transit prediction algorithm.