CN111507541A - Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment - Google Patents

Abstract

The invention provides a goods quantity prediction model construction method, a goods quantity measurement device and electronic equipment, wherein the method comprises the following steps: acquiring identification information of a plurality of areas and historical cargo quantity information corresponding to the areas; and inputting the identification information and the historical cargo quantity information as training samples into a prediction model to be trained, and training the prediction model to be trained to obtain a trained prediction model. When the model is trained, the adopted training samples are identification information of a plurality of regions and historical cargo quantity information corresponding to the regions, the trained prediction model can predict the cargo quantity information of a plurality of places, the complexity of constructing the prediction model can be effectively reduced, the number of samples can be effectively increased, the recognition accuracy of the prediction model is improved, and the problems that the independent prediction model is independently established for one place or region and the model prediction accuracy cannot be improved under the condition that the historical cargo quantity data is limited in the prior art can be effectively solved.

Description

Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment

Technical Field

The invention relates to the technical field of logistics, in particular to a goods quantity prediction model construction method, a goods quantity measurement device and electronic equipment.

Background

In the existing logistics field, particularly in the field of truck freight, the problem that other freight orders cannot be found at a discharge place (such as a certain city) in a short time after a vehicle completes an order task at the discharge place often occurs; in response to this problem, the carrier either chooses to wait at that location until a shipment order can be taken; or choose to drive off the site to another site to take over the shipping order. Either way, it will bring about an increase in transportation costs, and even make the admitter unable to gain income, even loss. In addition, the occurrence of the condition simultaneously causes the reduction of the transportation efficiency and is not beneficial to the healthy development of the freight market.

At present, the problem is solved in a way that firstly, an independent prediction model is established for one place by using artificial intelligence, and during prediction, a corresponding prediction model needs to be selected according to a specific place for prediction; thus, a large number of prediction models need to be established due to the large number of sites; in addition, there are some locations where data is insufficient, and an effective prediction model cannot be built, or the accuracy of the output result of the built prediction model is low due to insufficient data.

Therefore, how to improve the accuracy of the cargo quantity prediction is an urgent technical problem to be solved.

Disclosure of Invention

The invention provides a cargo quantity prediction model construction method, a cargo quantity measurement device and electronic equipment, and aims to solve the problem of how to improve the accuracy of cargo quantity prediction in the prior art.

According to a first aspect, the invention provides a method for constructing a cargo capacity prediction model, comprising the following steps: acquiring identification information of a plurality of areas and historical cargo quantity information corresponding to the areas; and inputting the identification information and the historical cargo quantity information as training samples into a prediction model to be trained, and training the prediction model to be trained to obtain a trained prediction model.

Optionally, the acquiring the identification information of the plurality of areas and the historical cargo volume information corresponding to the areas includes: and establishing an identification code for representing the area based on a preset rule as identification information.

Optionally, the establishing of the code for characterizing the region identifier based on the preset rule includes: acquiring the number N of areas; and establishing N-dimensional vector codes in one-to-one correspondence with the regions based on the number N of the regions as identification codes of the regions.

Optionally, the establishing, as the identification information, an identification code for characterizing the region based on a preset rule further includes: and utilizing the area incidence relation to perform embedded expression on the identification codes established based on the preset rule and used for representing the areas to obtain data as identification information. .

Optionally, the area association relationship is a relationship between areas created when the same user or a certain user group generates a behavior related to freight transportation.

Optionally, the obtaining the identification information of the plurality of areas includes: and acquiring the area name and/or a standard code corresponding to the area as the identification information of the area.

According to a second aspect, an embodiment of the present invention provides a cargo quantity prediction model building apparatus, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a plurality of areas and historical cargo quantity information corresponding to the areas; and the training module is used for inputting the identification information and the historical cargo quantity information into a prediction model to be trained as training samples, and training the prediction model to be trained to obtain a trained prediction model.

Optionally, the cargo quantity prediction model building device further includes: and the identification information processing module is used for establishing an identification code for representing the area based on a preset rule as identification information.

Optionally, the identification information processing module includes: a first acquisition unit configured to acquire a number N of regions; and the first identification information establishing unit is used for establishing N-dimensional vector codes which are in one-to-one correspondence with the regions on the basis of the number N of the regions as identification codes.

Optionally, the identification information processing module further includes: and the first identification information processing unit is used for carrying out embedded expression on the identification codes established based on the preset rule and used for representing the areas by utilizing the area incidence relation to obtain data as identification information.

Optionally, the area association relationship is a relationship between areas created when the same user or a certain user group generates a behavior related to freight transportation.

Optionally, the identification information processing module further includes: and the second identification information processing unit is used for taking the area name and/or the standard code corresponding to the area as the identification information of the area.

According to a third aspect, an embodiment of the present invention provides a cargo quantity prediction method, including: acquiring identification information of an area to be predicted and historical cargo quantity information corresponding to the area to be predicted; and inputting the identification information and the historical cargo quantity information into a prediction model to obtain the predicted cargo quantity of the area to be measured, wherein the prediction model is constructed by adopting the cargo quantity prediction model construction method of any one of the first aspect.

According to a fourth aspect, an embodiment of the present invention provides a cargo amount prediction apparatus, including: the second acquisition module is used for acquiring identification information of the area to be predicted and historical cargo quantity information corresponding to the area to be predicted; and the prediction module is used for inputting the identification information and the historical cargo quantity information into a prediction model to obtain the predicted cargo quantity of the area to be measured, and the prediction model is constructed by adopting the cargo quantity prediction model construction method of any one of the first aspect.

According to a fifth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing the computer to execute the cargo prediction model building method according to any one of the above first aspects or the cargo prediction method according to the above third aspect.

According to a sixth aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the cargo quantity prediction model building method according to any one of the first aspect or the cargo quantity prediction method according to the third aspect.

When the goods quantity is predicted, an artificial intelligence prediction model is adopted for prediction, and during model training, training samples are identification information of a plurality of areas and historical goods quantity information corresponding to the areas, so that the trained prediction model can predict the goods quantity information of a plurality of places, a plurality of prediction models do not need to be built aiming at different places, the complexity of building the prediction model can be effectively reduced, in addition, the sample quantity can be effectively increased by training the same model by adopting the historical goods quantity information of a plurality of areas and a plurality of areas, the recognition precision of the prediction model is improved, and the problems that the independent prediction model is separately built aiming at one place or area in the prior art, and the model prediction precision cannot be improved under the condition of limited historical goods quantity data can be effectively solved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for building a cargo quantity prediction model according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a cargo quantity forecasting method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a cargo quantity prediction model building apparatus according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of a cargo quantity forecasting apparatus according to an embodiment of the present invention;

fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

The embodiment of the invention provides a method for constructing a cargo quantity prediction model, which can comprise the following steps of:

s11, obtaining identification information of a plurality of areas and historical cargo quantity information corresponding to the areas. As an exemplary embodiment, the area is a range for acquiring the cargo volume data, for example, may be a certain location, and may be, for example, an address of a discharge location or a loading location, or may be a range within a certain radius centering on the certain location, and may be, for example, an address of a discharge location or a loading location centering on the certain location, and a range within a radius of 30KM as an area, or may be divided into areas by an administrative area where the certain location is located, and may be, for example, a city, an administrative district, a county, or the like where the address of the discharge location or the address of the loading location is located. It should be noted that the address referred to in this embodiment includes the exemplary listed areas, and may also include other customized areas or areas with wider or narrower ranges.

The historical cargo volume information referred to as corresponding to a region may historically yield cargo traffic information for that region. In this embodiment, a city may be taken as an area for explanation: the historical cargo quantity information may be the cargo quantity information of a certain city in a historical preset time period as the historical cargo quantity information of the area, for example, the cargo quantity information of a certain city taken out of the city generated on a certain historical day of the area may be the historical cargo quantity information of the area, the cargo quantity information of a certain city taken out of the city generated on a certain historical day of the city may be the historical cargo quantity information of the area, or the cargo quantity information of a certain city taken out of the city generated on a certain historical time period of the city may be the historical cargo quantity information of the area; in addition, the cargo amount information may also be the cargo amount information carried into the area, or may be the sum of the cargo amount information carried into and out of the area. It should be understood by those skilled in the art that the amount information referred to in the present embodiment is within the scope of the present embodiment as long as the data reflecting the amount of goods, such as the amount of orders, the weight of the goods, the number of the goods, etc., can be obtained.

Note that the plurality of regions means two or more regions.

In the embodiment, the prediction model to be trained may include one or a combination of at least any two of L asso model, Xgboost model, L ightgbm model and Prophet model, and it should be understood by those skilled in the art that the prediction model in the embodiment may also be other models.

It should be noted that, when the identification information and the historical cargo quantity information are used as training samples to train the model to be trained, the cargo quantity information of a certain area in a certain time period in the history can be used as the training samples of the model to be trained. The same model to be trained is trained simultaneously based on the cargo capacity information of a plurality of regions in a certain historical time period, so that the trained prediction model has a multi-region cargo capacity prediction function. As an alternative embodiment, the historical cargo quantity information and the identification information may be combined to form data in a specific format as a training sample. Therefore, in the cargo quantity prediction, the cargo quantities of different areas can be predicted in one prediction model.

When the goods quantity is predicted, an artificial intelligence prediction model is adopted for prediction, and training samples are identification information of a plurality of areas and historical goods quantity information corresponding to the areas when the model is trained, so that the trained prediction model can predict the goods quantity information of a plurality of places, a plurality of prediction models do not need to be built aiming at different places, the complexity of building the prediction model can be effectively reduced, in addition, the sample quantity can be effectively increased by training the same model by adopting the identification information of the plurality of areas and the historical goods quantity information of the plurality of areas, the recognition precision of the prediction model is improved, and the problems that an independent prediction model is independently built aiming at one place or area in the prior art, and the model prediction precision cannot be improved under the condition of limited historical goods quantity data can be effectively solved.

As an exemplary embodiment, the identification information of the region may be prepared before training the prediction model, for example, an identification code established for characterizing the region based on a preset rule is used as the identification information, which is not specifically limited in this embodiment. The identification information of the regions may also respectively establish identification information for distinguishing the regions based on a preset rule, specifically, the regions are described by taking cities as examples, for example, historical freight data of 10 cities, such as shenzhen city, huizhou city, kunshan city, suzhou city, nanjing city, elchun city, spring city, zhangyang city and harrisun city, are input, except for the historical freight volume information of the 10 cities, the identification information of the 10 cities needs to be input, where the identification information may be names of the cities (names of the regions), or area codes corresponding to the cities (standard codes corresponding to the regions), or numbers for distinguishing the 10 cities by themselves, and the like, for distinguishing each region.

Exemplarily, establishing the identification code for characterizing the region based on the preset rule may be performed by the following means, specifically, obtaining the number N of the regions; and establishing N-dimensional vector codes which correspond to the regions one by one on the basis of the number N of the regions as identification codes of the regions. Taking 10 cities as an example in the above embodiment, the vector code may be 10-dimensional vector codes, each corresponding to one region, for example:

shenzhen city {1,0,0,0,0,0,0,0, 0}

Huizhou city {0,1,0,0,0,0,0,0,0,0}

Kunshan city {0,0,1,0,0,0,0,0,0,0}

Suzhou city {0,0,0,1,0,0,0,0, 0}

Nanjing city {0,0,0,0,1,0,0,0,0,0}

Islands {0,0,0,0,0,1,0,0,0,0}

Spring city {0,0,0,0,0,0,1,0,0,0}

Zhangye City {0,0,0,0,0,0,0,1,0,0}

Luoyang city {0,0,0,0,0,0,0,0,1,0}

Harbin City {0,0,0,0,0,0,0,0,0,1 }. To improve the accuracy of the prediction model, regions may be associated to make the results output by the prediction model more accurate. For example, the area association relationship is used to perform embedded expression on the identification code established based on the preset rule and used for representing the area to obtain data as the identification information. As an alternative embodiment, the areas may be associated based on the behavior data, and the area association relationship is, for example, a relationship between areas established when the same user or a certain user group generates a behavior related to freight transportation.

Specifically, behavior data related to freight transportation of the same user or a certain specific user group can be acquired; identifying a plurality of regions contained in the behavioral data; and associating a plurality of areas contained in the behavior data to obtain an area association relation. The regions are correlated based on the behavior data, so that the input data can be more converged before being predicted, and the model prediction accuracy is improved.

The association of the regions based on the region association relationship obtained from the behavior data may be a sequence relationship between regions established when the same user or a certain group of users consults, browses, places orders, carries, and the like, in relation to freight. For example, in the process of browsing the freight orders, each user may search for an order that the user needs, in the action process, an area in which the user wants to take over the order is limited, and in the process of browsing the freight orders twice in the front and back of the user, the two freight orders may include two different area information, but the two area information may be the area in which the user wants to take over the freight orders, so that the action of the user establishes an association between the two different areas. Besides, the user can also establish the association relationship between the areas in the process of ordering, transporting and other actions.

As an exemplary embodiment, in order to prevent the input information of model training from being too sparse and poor in training effect due to too many regions, in this embodiment, the input information may be embedded and represented by using a region association relationship, so as to reduce the sparsity of training samples, improve the training effect of the model, and further improve the prediction accuracy of the model. In this embodiment, the identification information may be N-dimensional vector codes or may be information in other forms, for example: the name of the city, or the area code or custom code corresponding to the city. In this embodiment, the identification information may be N-dimensional vector codes as an example for explanation:

by using the region association relations, N-dimensional vector codes of N regions can be embedded and expressed. The process of the embedded representation may use the existing method, and is not limited in this application.

For example, the identification information after embedded representation by using the area association relationship may be:

shenzhen city { -0.77,0.31, -0.12}

Huizhou city { -0.76,0.33, -0.13}

Kunshan city { -0.61,0.39,0.17}

Suzhou city { -0.61,0.41,0.15}

Nanjing City { -0.62,0.43,0.15}

Islands' 0.16,0.17,0.68}

Spring city {0.22,0.78, -0.11}

Zhangye City {0.21,0.77, -0.12}

Luoyang city {0.51, -0.51, -0.52}

Harbin City {0.15,0.15,0.65 }.

After the embedded representation is completed, for example, the embedded vector coding is used for replacing a plurality of N vector codes as the identification information of the region, and the identification information of the region can be embodied in a lower dimension, so that the problems that the input information is too sparse, the training effect is poor, and the accuracy of the output result of the prediction model is not high can be prevented.

An embodiment of the present invention provides a method for predicting a cargo volume, as shown in fig. 2, the method may include the following steps:

and S21, acquiring identification information of the area to be predicted and historical cargo quantity information corresponding to the area to be predicted. In the present embodiment, the acquired identification information of the region should coincide with the identification information of the region used when the model is built. The specific method for acquiring the identification information of the area may refer to the description in the above embodiments. The historical cargo quantity information also needs to be the same as the historical preset interval period used in the modeling, and in particular, the description of the historical cargo quantity information can be summarized by referring to the above embodiment.

And S22, inputting the historical cargo quantity information of the area to be predicted and the area to be predicted into a prediction model to obtain the predicted cargo quantity of the area to be predicted. Specifically, the prediction model may be constructed by using the method for constructing the cargo capacity prediction model in the above embodiment.

After the prediction model is built, identification information of an area and specific historical data can be input into the prediction model, and the needed goods amount can be calculated by using the prediction model. In addition, the identification information of the inputted area should be identical to the identification information of the area used when the model is built, and the historical cargo amount information also needs to be identical to the historical preset interval period used when the model is built.

For example, the following can be illustrated by taking the example of predicting the cargo capacity of a certain city, such as Shenzhen city: when the prediction model is built, the identification information of Shenzhen city is { -0.77,0.31, -0.12}, and when the cargo capacity of Shenzhen city is predicted, the identification information of the region input into the prediction model should also be { -0.77,0.31, -0.12}, but {1,0,0,0,0,0,0,0,0,0}, or a region code and the like cannot be input into the prediction model. If the forecasting model is established, historical cargo quantity information of the time T is used as input, and the cargo quantity information of the time T is used as output to be trained, namely, the cargo quantity data of the third day, the fourth day and the fifth day before the time T are used as input. Then historical inventory information for T-3, T-4, T-5 may also be required as input in the prediction. For example, the time is 2/5/2020, and it is desired to predict the data of the volume of Shenzhen city in 2/6/2020, then the data of the volume of Shenzhen city in three days, i.e. 2/1/2020, 2/2020, and 2/3/2020, need to be input at this time.

When the goods quantity is predicted, an artificial intelligence prediction model is adopted for prediction, and during model training, training samples are identification information of a plurality of areas and historical goods quantity information corresponding to the areas, so that the trained prediction model can predict the goods quantity information of a plurality of places, a plurality of prediction models do not need to be built aiming at different places, the complexity of building the prediction model can be effectively reduced, in addition, the number of samples can be effectively increased by training the same model by adopting the historical goods quantity information of the plurality of areas and the plurality of areas, the recognition precision of the prediction model is improved, and the problems that the independent prediction model is separately built aiming at one place or area and the model prediction precision cannot be improved under the condition that the goods quantity data is limited in the prior art can be effectively solved.

An embodiment of the present invention provides a device for building a cargo quantity prediction model, as shown in fig. 3, including: a first obtaining module 31, configured to obtain identification information of a plurality of areas and historical cargo amount information corresponding to the areas; and the training module 32 is configured to input the identification information and the historical cargo quantity information as training samples into the prediction model to be trained, and train the prediction model to be trained to obtain a trained prediction model.

Optionally, the cargo quantity prediction model building device further includes: and the identification information processing module is used for establishing an identification code for representing the area based on a preset rule as identification information.

Optionally, the identification information processing module includes: a first acquisition unit configured to acquire a number N of regions; a first identification information establishing unit configured to establish, as identification information, N-dimensional vector codes that are one-to-one corresponding to the regions based on the number N of the regions.

Optionally, the identification information processing module includes: the second acquisition unit is used for acquiring behavior data related to freight of the same user or a certain specific user group; a region identification unit configured to identify a plurality of regions included in the behavior data; and the association unit is used for associating the plurality of areas contained in the behavior data to obtain the area association relation.

Optionally, the identification information processing module further includes: and the first identification information processing unit is used for carrying out embedded expression on the identification codes established based on the preset rule and used for representing the areas by utilizing the area incidence relation to obtain data as identification information.

Optionally, the identification information establishing module further includes: and the second identification information processing unit is used for taking the area name and/or the standard code corresponding to the area as the identification information of the area.

Optionally, the first obtaining module includes: and the third acquisition unit is used for acquiring the shipment information and/or the incoming cargo amount information of the preset time period of the region.

An embodiment of the present invention provides a cargo quantity prediction apparatus, as shown in fig. 4, including: a second obtaining module 41, configured to obtain identification information of the area to be predicted and historical cargo quantity information corresponding to the area to be predicted; the prediction module 42 is configured to input the identification information of the area to be predicted and the historical cargo quantity information of the area to be predicted into the prediction model to obtain the predicted cargo quantity of the area to be predicted, where the prediction model is constructed by using the cargo quantity prediction model construction method described in the foregoing embodiment.

An embodiment of the present invention provides an electronic device, as shown in fig. 5, the electronic device includes one or more processors 51 and a memory 52, and one processor 53 is taken as an example in fig. 5.

The controller may further include: an input device 53 and an output device 54.

The processor 51, the memory 52, the input device 53 and the output device 54 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.

The processor 51 may be a Central Processing Unit (CPU). The processor 51 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 52 is a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the control method in the embodiment of the present application. The processor 51 executes various functional applications of the server and data processing, i.e., a cargo quantity prediction model construction method or a cargo quantity prediction method of the above-described method embodiments, by executing non-transitory software programs, instructions, and modules stored in the memory 52.

The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing device operated by the server, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, which may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 53 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing device of the server. The output device 54 may include a display device such as a display screen.

One or more modules are stored in the memory 52 and, when executed by the one or more processors 51, perform the method as shown in fig. 1 or 2.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the motor control methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random Access Memory (RAM), a flash memory (FlashMemory), a hard disk (hard disk drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.

Finally, the principle and the implementation of the present invention are explained by applying the specific embodiments in the present invention, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (11)

1. A method for constructing a cargo quantity prediction model is characterized by comprising the following steps:

acquiring identification information of a plurality of areas and historical cargo quantity information corresponding to the areas;

and inputting the identification information and the historical cargo quantity information as training samples into a prediction model to be trained, and training the prediction model to be trained to obtain a trained prediction model.

2. The method of constructing a cargo quantity prediction model according to claim 1, wherein the obtaining identification information of a plurality of areas and historical cargo quantity information corresponding to the areas comprises:

and establishing an identification code for representing the area based on a preset rule as identification information.

3. The method of claim 2, wherein the establishing a code for characterizing the region identifier based on the predetermined rule comprises:

acquiring the number N of areas;

and establishing N-dimensional vector codes which are in one-to-one correspondence with the regions on the basis of the number N of the regions as identification codes.

4. The cargo quantity prediction model construction method according to claim 2 or 3, wherein the establishing an identification code for characterizing a region based on a preset rule as identification information further comprises:

and utilizing the area incidence relation to perform embedded expression on the identification codes established based on the preset rule and used for representing the areas to obtain data as identification information.

5. The method according to claim 4, wherein the regional association is a relationship between regions that is established when the same user or a specific user group generates a behavior related to freight transportation.

6. The method of constructing a cargo quantity prediction model according to claim 2, wherein the obtaining identification information of a plurality of areas comprises:

and acquiring the area name and/or a standard code corresponding to the area as the identification information of the area.

7. A cargo quantity prediction model construction device is characterized by comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a plurality of areas and historical cargo quantity information corresponding to the areas;

and the training module is used for inputting the identification information and the historical cargo quantity information into a prediction model to be trained as training samples, and training the prediction model to be trained to obtain a trained prediction model.

8. A method for predicting a quantity of goods, comprising:

acquiring identification information of an area to be predicted and historical cargo quantity information corresponding to the area to be predicted;

inputting the identification information and the historical cargo quantity information into a prediction model to obtain the predicted cargo quantity of the area to be measured, wherein the prediction model is constructed by adopting the cargo quantity prediction model construction method of any one of claims 1 to 6.

9. A cargo quantity prediction apparatus, comprising:

the second acquisition module is used for acquiring identification information of the area to be predicted and historical cargo quantity information corresponding to the area to be predicted;

and the prediction module is used for inputting the identification information and the historical cargo quantity information into a prediction model to obtain the predicted cargo quantity of the area to be measured, and the prediction model is constructed by adopting the cargo quantity prediction model construction method of any one of claims 1 to 6.

10. A computer-readable storage medium storing computer instructions for causing a computer to execute the cargo quantity prediction model building method according to any one of claims 1 to 6 or the cargo quantity prediction method according to claim 8.

11. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of building a cargo prediction model according to any one of claims 1-6 or the method of predicting cargo according to claim 8 when executing the program.

Images