CN114239944A

CN114239944A - Real crowd quantity prediction method and device

Info

Publication number: CN114239944A
Application number: CN202111500624.6A
Authority: CN
Inventors: 陶闯; 邱卫根; 赵康宁; 王昊奋
Original assignee: Shanghai Weizhi Zhuoxin Information Technology Co ltd
Current assignee: Shanghai Weizhi Zhuoxin Information Technology Co ltd
Priority date: 2021-12-09
Filing date: 2021-12-09
Publication date: 2022-03-25

Abstract

The invention discloses a method and a device for predicting the number of real people, wherein the method comprises the following steps: determining the number of communication terminals of an area to be predicted in a target time period; inputting the number of the communication terminals into a trained regression network prediction model to predict the number of real people in the target time period of the area to be predicted; the regression network prediction model is obtained by training a training data set of a training region comprising a plurality of region population numbers and communication terminal numbers known in a training time period. Therefore, the method and the device can predict the number of the real crowds in the region by combining the regression network model according to the number of the communication terminals in the region, thereby predicting the number of the real crowds in the region with high efficiency and low cost, and subsequently facilitating further data analysis operation by using the number of the crowds in the region.

Description

Real crowd quantity prediction method and device

Technical Field

The invention relates to the technical field of data prediction, in particular to a method and a device for predicting the number of real people.

Background

When analyzing the regional characteristics of a specific region, such as the regional pedestrian volume, commercial attractiveness or crowd portrayal, the real crowd quantity of the specific region needs to be acquired as the basis of data analysis, but because the data collection difficulty of the crowd quantity is high and the cost is huge, the prior art does not directly count the real crowd quantity, and estimates the real crowd quantity by manually counting the crowd quantity in a specific time period or replaces the real crowd quantity by some related parameters such as communication data. However, the existing technical thought can not always ensure that the number of people estimated finally or obtained by substitution is real enough, and further the subsequent regional feature analysis work can not be performed on the basis of accurate data. Therefore, the defects of the prior art are found to be urgently solved.

Disclosure of Invention

The technical problem to be solved by the present invention is to provide a method and a device for predicting the number of real people, which can predict the number of real people in an area with high efficiency and low cost, and subsequently facilitate further data analysis operation by using the number of people in the area.

In order to solve the above technical problem, a first aspect of the present invention discloses a method for predicting a number of real people, including:

determining the number of communication terminals of an area to be predicted in a target time period;

inputting the number of the communication terminals into a trained regression network prediction model to predict the number of real people in the target time period of the area to be predicted; the regression network prediction model is obtained by training a training data set of a training region comprising a plurality of region population numbers and communication terminal numbers known in a training time period.

As an optional implementation manner, in the first aspect of the present invention, the number of communication terminals includes at least one of a number of terminals based on software dimension perception, a number of terminals based on operating system dimension perception, a number of terminals based on operator dimension perception, and a number of terminals based on brand dimension perception; and/or the number of the regional population is determined according to the call detail record of at least one operator in the training time period in the training region; and/or the number of the regional population is determined according to the sum of call detail records of a plurality of operators in the training time period in the training region; and/or the number of the regional population is determined according to the call detail record of the target operator in the training time period of the training region and the proportion parameter corresponding to the target operator; the proportion parameter is used for indicating the proportion of the call detail record of the target operator to the sum of the call detail records of all operators.

As an optional implementation manner, in the first aspect of the present invention, the determining the number of communication terminals of the area to be predicted in the target time period includes:

acquiring device communication information perceived by perception devices in the region to be predicted within a target time period;

and determining the number of the communication terminals of the area to be predicted in the target time period according to the equipment communication information.

As an optional implementation manner, in the first aspect of the present invention, after determining the number of communication terminals in the area to be predicted, the method further includes:

determining the region characteristic parameters of the region to be predicted;

the inputting the number of the communication terminals into a trained regression network prediction model to predict the number of the real people in the target time period of the area to be predicted comprises the following steps:

inputting the number of the communication terminals and the region characteristic parameters into a trained regression network prediction model to predict the number of real people of the region to be predicted in a target time period;

the regression network prediction model is obtained by training a training data set of a training region comprising a plurality of region population numbers, region characteristic parameters and communication terminal numbers known in a training time period.

As an optional implementation manner, in the first aspect of the present invention, the regional characteristic parameter includes at least one of a regional physical characteristic, a regional administrative level characteristic, a regional peripheral facility characteristic, and a regional peripheral competitive product characteristic.

As an optional implementation manner, in the first aspect of the present invention, the determining the region characteristic parameter of the region to be predicted includes:

determining a plurality of target facilities around the position of the area to be predicted;

determining a distance parameter between the position of the area to be predicted and any one target facility;

determining the distance parameters corresponding to all the target facilities as the regional peripheral facility characteristics of the region to be predicted;

and/or the presence of a gas in the gas,

determining a plurality of competitive goods shops around the position of the area to be predicted;

determining a distance parameter between the position of the area to be predicted and any bidding shop;

and determining the distance parameters corresponding to all the competitive product shops as the regional peripheral competitive product characteristics of the region to be predicted.

As an alternative implementation, in the first aspect of the present invention, the regression network prediction model is trained according to the following steps:

determining a training data set; the training data set comprises a plurality of training areas with known area crowd number and communication terminal number in a training time period;

inputting the training data set into a crowd prediction training model for training until convergence so as to obtain the trained regression network prediction model; the crowd prediction training model comprises the regression network prediction model and a corresponding parameter optimization layer.

As an alternative embodiment, in the first aspect of the present invention, the regression network prediction model includes at least one of a linear regression network model, a polynomial regression network model, a ridge regression algorithm model, a LightGBM regression model, a multi-layer perceptron network model, and a convolutional neural network model.

The second aspect of the embodiment of the present invention discloses a device for predicting the number of real people, including:

the determining module is used for determining the number of the communication terminals of the area to be predicted in the target time period;

the prediction module is used for inputting the number of the communication terminals into a trained regression network prediction model so as to predict and obtain the number of real people of the area to be predicted in the target time period; the regression network prediction model is obtained by training a training data set of a training region comprising a plurality of region population numbers and communication terminal numbers known in a training time period.

As an optional implementation manner, in the second aspect of the present invention, the number of communication terminals includes at least one of a number of terminals based on software dimension perception, a number of terminals based on operating system dimension perception, a number of terminals based on operator dimension perception, and a number of terminals based on brand dimension perception; and/or the number of the regional population is determined according to the call detail record of at least one operator in the training time period in the training region; and/or the number of the regional population is determined according to the sum of call detail records of a plurality of operators in the training time period in the training region; and/or the number of the regional population is determined according to the call detail record of the target operator in the training time period of the training region and the proportion parameter corresponding to the target operator; the proportion parameter is used for indicating the proportion of the call detail record of the target operator to the sum of the call detail records of all operators.

As an optional implementation manner, in the second aspect of the present invention, a specific manner of determining, by the determining module, the number of communication terminals of the area to be predicted in the target time period includes:

As an optional implementation manner, in the second aspect of the present invention, the determining module is further configured to determine a region feature parameter of the region to be predicted;

the prediction module inputs the number of the communication terminals into a trained regression network prediction model to predict the number of the real people in the target time period of the area to be predicted, and the prediction module comprises the following specific modes:

As an optional embodiment, in the second aspect of the present invention, the regional characteristic parameter includes at least one of a regional physical characteristic, a regional administrative level characteristic, a regional peripheral facility characteristic, and a regional peripheral auction characteristic.

As an optional implementation manner, in the second aspect of the present invention, a specific manner of determining the region characteristic parameter of the region to be predicted by the determining module includes:

and/or the presence of a gas in the gas,

As an optional implementation manner, in the second aspect of the present invention, the apparatus further includes a training module, where the training module is configured to perform the following steps to train the regression network prediction model:

As an alternative embodiment, in the second aspect of the present invention, the regression network prediction model includes at least one of a linear regression network model, a polynomial regression network model, a ridge regression algorithm model, a LightGBM regression model, a multi-layer perceptron network model, and a convolutional neural network model.

The third aspect of the present invention discloses another real crowd quantity prediction apparatus, including:

a memory storing executable program code;

a processor coupled with the memory;

the processor calls the executable program code stored in the memory to execute part or all of the steps of the real population quantity prediction method disclosed by the first aspect of the invention.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

the embodiment of the invention discloses a method and a device for predicting the number of real people, wherein the method comprises the following steps: determining the number of communication terminals of an area to be predicted in a target time period; inputting the number of the communication terminals into a trained regression network prediction model to predict the number of real people in the target time period of the area to be predicted; the regression network prediction model is obtained by training a training data set of a training region comprising a plurality of region population numbers and communication terminal numbers known in a training time period. Therefore, the embodiment of the invention can predict the number of the real crowd in the region by combining the regression network model according to the number of the communication terminals in the region, thereby predicting the number of the real crowd in the region with high efficiency and low cost, and subsequently facilitating the further data analysis operation by using the number of the crowd in the region.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for predicting a real population quantity according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of an apparatus for predicting a real population quantity according to an embodiment of the present invention.

Fig. 3 is a schematic structural diagram of another device for predicting a number of real people according to an embodiment of the present invention.

Detailed Description

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

The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or apparatus that comprises a list of steps or elements is not limited to those listed but may alternatively include other steps or elements not listed or inherent to such process, method, product, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

The invention discloses a method and a device for predicting the number of real crowds, which can predict the number of the real crowds in a region by combining a regression network model according to the number of communication terminals in the region, thereby efficiently predicting the number of the real crowds in the region at low cost and facilitating further data analysis operation by using the number of the crowds in the region subsequently. The following are detailed below.

Example one

Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a method for predicting a real population according to an embodiment of the present invention. The real population quantity prediction method described in fig. 1 is applied to a prediction chip, a prediction terminal, or a prediction server (where the prediction server may be a local server or a cloud server) of a population quantity prediction system. As shown in fig. 1, the real population quantity prediction method may include the following operations:

101. and determining the number of the communication terminals of the area to be predicted in the target time period.

Alternatively, the communication terminal may be a mobile terminal such as a mobile phone or a tablet or a notebook computer, or a fixed terminal such as a desktop computer or a server. Optionally, the number of communication terminals may include at least one of a number of terminals based on software dimension awareness, a number of terminals based on operating system dimension awareness, a number of terminals based on operator dimension awareness, and a number of terminals based on brand dimension awareness.

Optionally, the number of terminals based on software dimension sensing may be a fixed number of terminals or a mobile number of terminals using different mobile phone software applications, including but not limited to: hundred-degree video, internet music, Tencent video, WeChat and other software applications. Optionally, the number of terminals perceived based on the operating system dimension may include the number of fixed terminals or the number of mobile terminals using different operating systems, including but not limited to: ios, android, Hongmon systems, and the like. Alternatively, the operator dimension-aware based terminal numbers may include fixed terminal numbers or mobile terminal numbers using different communication operators, including but not limited to: operators of China Mobile, China Unicom, China telecom, etc. Alternatively, the perceived number of terminals based on brand dimensionality may include a fixed number of terminals or a number of mobile terminals using different brands, including but not limited to: apple, Huashi, glorious, charm, Samsung, millet, oppo, vivo, Yijia, hammer and other brands.

102. And inputting the number of the communication terminals into the trained regression network prediction model to predict the number of the real people in the target time period of the region to be predicted.

Optionally, the regression network prediction model is obtained by training a training data set including a plurality of training regions known as the number of regional crowds and the number of communication terminals in a training time period. Alternatively, the training regions in the training data set may be representative regions selected, including but not limited to: typical residential areas, typical commercial areas, typical industrial areas, typical educational areas, typical transportation hub areas, and the like.

Optionally, the number of population in the training area in the training data set may be data information of demographic data of an operator or a big data organization in the training area for a training time period.

Optionally, the number of regional groups of the training region in the training data set may be determined from call detail records of at least one operator of the training region during the training time period. Specifically, Call Detail Records (CDRs), also called mobile phone Call position data, are a basic data for calculating revenue of communication operators. The data records the code and time of the base station connected when the mobile phone use event (such as call receiving and making, short message sending or network use) occurs. In particular, call detail records of multiple operators in a particular area can be generally considered to be relatively close to the actual population.

Optionally, the number of regional groups is determined according to a sum of call detail records of multiple operators in the training time period in the training region, for example, the number of regional groups may be obtained by purchasing and adding call detail records of multiple operators in the training time period in the training region.

Optionally, the number of regional groups may be determined according to the call detail records of the target operator in the training time period in the training region and a proportion parameter corresponding to the target operator, and specifically, the proportion parameter is used to indicate a proportion of the call detail records of the target operator in a sum of the call detail records of all the operators. Alternatively, the number of regional population may be equal to the product of the call detail record of the target operator of the training region during the training period and the duty ratio parameter. Alternatively, the percentage parameter may be obtained by counting the proportion of call detail records of the target operator in a plurality of regions to the sum of call detail records of all operators in a historical period of time.

Optionally, the target operator may include a plurality of target operators, and at this time, the call detail records of the plurality of target operators in the training time period in the training area may be multiplied by the proportion parameter corresponding to each target operator to obtain the crowd number in the plurality of reference areas. Alternatively, the number of regional populations may be calculated from the number of reference regional populations, for example, by calculating a weighted average of the number of reference regional populations. Optionally, the weighted average may be calculated after removing the larger offset value of the population in the plurality of reference regions to obtain the population in the region, wherein the larger offset value may be determined according to the difference between the population in each reference region and the average of the population in the plurality of reference regions.

Therefore, the embodiment of the invention can predict the number of the real crowd in the region by combining the regression network model according to the number of the communication terminals in the region, thereby predicting the number of the real crowd in the region with high efficiency and low cost, and subsequently facilitating further data analysis operation by using the number of the crowd in the region.

As an optional implementation manner, in step 101, determining the number of communication terminals of the area to be predicted in the target time period includes:

acquiring device communication information perceived by perception devices in a region to be predicted within a target time period;

Optionally, the sensing device may include at least one of a wireless AP, a bluetooth device, a wireless probe device, and other internet of things devices having a device sensing function. Optionally, the device communication information may include at least one of software information, operating system information, communication operator information, and device brand information of the device, so as to be used for counting the number of communication terminals with different sensing dimensions in the following step.

Therefore, by implementing the optional implementation mode, the number of the communication terminals of the to-be-predicted area in the target time period can be determined according to the device communication information sensed by the sensing device in the to-be-predicted area in the target time period, so that the number of the communication terminals of the to-be-predicted area in the target time period can be accurately determined, and the number of the real people in the area can be estimated efficiently and at low cost subsequently based on the number of the communication terminals.

As an optional implementation manner, after the step 101, the method further includes:

and determining the regional characteristic parameters of the region to be predicted.

Optionally, the regional characteristic parameters may include at least one of regional physical characteristics, regional administrative level characteristics, regional perimeter facility characteristics, and regional perimeter auction characteristics. Alternatively, the zone physical characteristics may include the area of the zone and/or the shape of the zone. Alternatively, the regional administrative level features may be administrative level features of a region, such as the administrative level of the city in which the region is located, which may be used to characterize the city level of the region, and further may be used to characterize the demographic characteristics of the region.

Optionally, the regional perimeter facility characteristics may include a number of regional perimeter facilities and/or a distance parameter between a regional perimeter facility and a regional location. Alternatively, the peripheral facilities may be POI (point of interest) or AOI (area of interest), which may be of types including but not limited to: sports leisure, catering, living services, science and education culture, shopping, transportation, national government, lodging, enterprise business, health care/healthcare, public facilities, and the like.

Optionally, the regional perimeter auction feature may include a number of regional perimeter auction stores and/or a distance parameter between a regional perimeter auction store and a regional location. Alternatively, the distance parameter may include at least one of a direct distance, an average distance, a maximum distance, and a minimum distance.

Specifically, in the step 102, inputting the number of the communication terminals into the trained regression network prediction model to predict and obtain the number of the real people in the target time period of the area to be predicted, includes:

and inputting the number of the communication terminals and the regional characteristic parameters into a trained regression network prediction model so as to predict the number of the real people in the target time period of the region to be predicted.

Optionally, the regression network prediction model is obtained by training a training data set including a plurality of training regions known in the number of regional crowds, the number of regional characteristic parameters, and the number of communication terminals in a training time period.

Therefore, by implementing the optional implementation mode, the regional characteristic parameters of the region to be predicted can be determined, the real crowd number of the region to be predicted in the target time period can be more accurately predicted by combining the regional characteristic parameters, and the real crowd number of the region can be estimated efficiently and at low cost subsequently based on the regional characteristic parameters.

As an optional implementation manner, in the step, determining the region characteristic parameter of the region to be predicted includes:

determining a distance parameter between the position of the area to be predicted and any target facility;

and determining the distance parameters corresponding to all the target facilities as the peripheral facility characteristics of the region to be predicted.

In one particular embodiment, the area to be predicted may be a store or facility. Optionally, the target facility corresponding to the area to be predicted may be a commercial facility within a first distance range of the location of the area to be predicted, such as a shopping mall or an office building, a large market for clothing, general merchandise, building materials, and decorative materials, or a comprehensive shopping mall, or other large commercial facilities such as catering, entertainment, leisure facilities, commercial squares, and commercial streets, which are marked and closely related to the lives of people.

Optionally, the distance parameter between the location of the area to be predicted and any target facility may include one or both of a straight-line distance and a walking distance. Optionally, the linear distance between the location of the area to be predicted and any target facility may be determined by calculating a distance between a connection line between the location of the area to be predicted and the location of any target facility. Optionally, the walkable distance between the location of the area to be predicted and any target facility may be determined by:

determining a walking path between the position of the area to be predicted and the position of any target facility between the area map models according to a preset area map model;

the length of the walking path is determined so as to determine the walkable distance between the position of the area to be predicted and any target facility.

Optionally, at least one of the average value, the total value, the maximum value, and the minimum value of the distance parameters corresponding to all the target facilities may be determined as the regional peripheral facility feature of the region to be predicted.

Therefore, by the optional implementation mode, the distance parameters corresponding to all the target facilities can be determined as the characteristics of the facilities around the region to be predicted, so that the characteristics of the facilities around the region can be reasonably determined, and the estimation of the number of the real people in the region based on the characteristics can be realized efficiently and at low cost.

determining a distance parameter between the position of the area to be predicted and any competitive product shop;

and determining the distance parameters corresponding to all the competitive product shops as the competitive product characteristics around the area to be predicted.

In one particular embodiment, the area to be predicted may be a store or facility. Optionally, the competitive product shop corresponding to the area to be predicted may be a competitive product shop around the position of the area to be predicted, where the competitive product shop may be a peripheral shop where the service field intersects with the service field corresponding to the area to be predicted, or a peripheral shop where the commodity parameter of the commodity on the shelf intersects with the commodity parameter of the preset commodity on the shelf corresponding to the area to be predicted. Optionally, the determination manner of the competitive store may include:

acquiring all shops in a second distance range of the position of the area to be predicted;

determining a shop parameter corresponding to any shop;

determining shop parameters corresponding to the area to be predicted; the store parameters comprise commodity parameters of a service field set and/or commodities on shelves;

calculating the similarity between the shop parameters corresponding to the area to be predicted and the shop parameters corresponding to any shop;

and determining the shops with the similarity between the shop parameters corresponding to the areas to be predicted higher than a preset similarity threshold value as competitive shops.

Optionally, the distance parameter between the position of the area to be predicted and any competitive store may include one or both of a straight line distance and a walking distance. Optionally, the straight-line distance between the position of the area to be predicted and any competitive product shop can be determined by calculating the distance of a connecting line between the position of the area to be predicted and the position of any competitive product shop. Optionally, the walkable distance between the position of the area to be predicted and any competitive store can be determined by the following method:

determining a walking path between the position of the area to be predicted and the position of any competition store between the area map models according to a preset area map model;

and determining the length of the walking path so as to determine the walking distance between the position of the area to be predicted and any competitive store.

Optionally, at least one of the average value, the total value, the maximum value and the minimum value of the distance parameters corresponding to all the competitive product shops may be determined as the regional peripheral competitive product characteristics of the region to be predicted.

Therefore, through the optional implementation mode, the distance parameters corresponding to all the competitive product shops can be determined as the regional peripheral competitive product characteristics of the region to be predicted, so that the regional peripheral competitive product characteristics are reasonably determined, and the method is favorable for estimating the number of the real crowd in the region based on the regional peripheral competitive product characteristics in a follow-up manner with high efficiency and low cost.

As an alternative embodiment, the regression network prediction model is trained according to the following steps:

determining a training data set;

and inputting the training data set into the crowd prediction training model for training until convergence so as to obtain a trained regression network prediction model.

Optionally, the training data set comprises a plurality of training regions for which the number of regional groups and the number of communication terminals are known during a training time period. Preferably, the training data set includes a plurality of training regions in which the number of regional crowds, the number of regional characteristic parameters, and the number of communication terminals in a training time period are known, so as to train a network model capable of predicting the number of real crowds according to the regional characteristic parameters and the number of communication terminals.

Optionally, the crowd prediction training model includes a regression network prediction model and a corresponding parameter optimization layer. Optionally, the parameter optimization layer may include a loss function calculation layer and a gradient descent optimization layer, where the loss function calculation layer is configured to calculate a difference between a result of predicting the number of people in the regression network prediction model and a label of the number of people in the region of the training data, and the gradient descent optimization layer is configured to optimize the model parameters of the regression network prediction model by using a gradient descent method, so that a result of calculating the loss function value in the loss function calculation layer is minimized to obtain the trained regression network prediction model.

Alternatively, the regression network prediction model may include at least one of a linear regression network model, a polynomial regression network model, a ridge regression algorithm model, a LightGBM regression model, a multi-layered perceptron network model, and a convolutional neural network model. The linear regression network model or the polynomial regression network model may be used to perform linear operation/polynomial operation on the area characteristic parameters and the number of communication terminals to obtain the regression network model. A convolutional neural network model (CNN) may be used when the amount of data is large, and a one-dimensional convolutional neural network may be used.

Therefore, by implementing the optional implementation mode, the trained regression network prediction model can be obtained by inputting the training data set into the crowd prediction training model for training until convergence, so that the network model for predicting the number of the real crowd can be obtained by training, and the method is favorable for realizing the estimation of the number of the real crowd in the region with high efficiency and low cost based on the network model.

Example two

Referring to fig. 2, fig. 2 is a schematic structural diagram of a device for predicting a real population quantity according to an embodiment of the present invention. The real crowd quantity prediction apparatus described in fig. 2 is applied to a prediction chip, a prediction terminal, or a prediction server (where the prediction server may be a local server or a cloud server) of a crowd quantity prediction system. As shown in fig. 2, the real population amount prediction means may include:

a determining module 201, configured to determine the number of communication terminals in the target time period in the area to be predicted.

The prediction module 202 is configured to input the number of the communication terminals into the trained regression network prediction model to predict the number of the real people in the target time period in the region to be predicted.

As an optional implementation manner, the determining module 201 determines the number of communication terminals of the area to be predicted in the target time period, including:

As an optional implementation, the determining module 201 is further configured to determine a region feature parameter of the region to be predicted.

The predicting module 202 inputs the number of the communication terminals into the trained regression network prediction model to predict the number of the real people in the target time period of the area to be predicted, and the specific method includes:

As an optional implementation manner, the specific manner of determining the region characteristic parameter of the region to be predicted by the determining module 201 includes:

determining a shop parameter corresponding to any shop;

As an optional implementation manner, the apparatus further includes a training module, and the training module is configured to perform the following steps to train and obtain the regression network prediction model:

determining a training data set;

EXAMPLE III

Referring to fig. 3, fig. 3 is a schematic diagram illustrating another real crowd prediction apparatus according to an embodiment of the present invention. The real population quantity prediction apparatus described in fig. 3 is applied to a prediction chip, a prediction terminal, or a prediction server (where the prediction server may be a local server or a cloud server) of a population quantity prediction system. As shown in fig. 3, the real population amount prediction means may include:

a memory 301 storing executable program code;

a processor 302 coupled to the memory 301;

the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the real population prediction method described in the first embodiment or the second embodiment.

Example four

The embodiment of the invention discloses a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the real crowd quantity prediction method described in the first embodiment or the second embodiment.

EXAMPLE five

An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the method for predicting the number of real people described in the first embodiment or the second embodiment.

While certain embodiments of the present disclosure have been described above, other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily have to be in the particular order shown or in sequential order to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus, device, and non-volatile computer-readable storage medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and in relation to the description, reference may be made to some portions of the description of the method embodiments.

The apparatus, the device, the nonvolatile computer readable storage medium, and the method provided in the embodiments of the present specification correspond to each other, and therefore, the apparatus, the device, and the nonvolatile computer storage medium also have similar advantageous technical effects to the corresponding method.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Finally, it should be noted that: the method and the device for predicting the number of real people disclosed in the embodiments of the present invention are only the preferred embodiments of the present invention, and are only used for illustrating the technical solutions of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting a real population amount, the method comprising:

2. The method according to claim 1, wherein the number of communication terminals comprises at least one of a number of terminals based on software dimension perception, a number of terminals based on operating system dimension perception, a number of terminals based on operator dimension perception, and a number of terminals based on brand dimension perception; and/or the number of the regional population is determined according to the call detail record of at least one operator in the training time period in the training region; and/or the number of the regional population is determined according to the sum of call detail records of a plurality of operators in the training time period in the training region; and/or the number of the regional population is determined according to the call detail record of the target operator in the training time period of the training region and the proportion parameter corresponding to the target operator; the proportion parameter is used for indicating the proportion of the call detail record of the target operator to the sum of the call detail records of all operators.

3. The method for predicting the number of real people according to claim 1, wherein the determining the number of the communication terminals of the area to be predicted in the target time period comprises:

4. The method for predicting the number of real people according to claim 1, wherein after determining the number of communication terminals in the area to be predicted, the method further comprises:

determining the region characteristic parameters of the region to be predicted;

5. The method of predicting the number of actual people as set forth in claim 4, wherein the regional characteristic parameters include at least one of a regional physical characteristic, a regional administrative level characteristic, a regional peripheral facility characteristic, and a regional peripheral competitive product characteristic.

6. The method for predicting the number of real people according to claim 5, wherein the determining the region characteristic parameter of the region to be predicted comprises:

and/or the presence of a gas in the gas,

7. The method of predicting a number of actual people according to any one of claims 1 to 6, wherein the regression network prediction model is trained according to the following steps:

8. The method of predicting a quantity of real population according to claim 1, wherein the regression network prediction model comprises at least one of a linear regression network model, a polynomial regression network model, a ridge regression algorithm model, a LightGBM regression model, a multi-layer perceptron network model, and a convolutional neural network model.

9. An apparatus for predicting a number of real people, the apparatus comprising:

10. An apparatus for predicting a number of real people, the apparatus comprising:

a memory storing executable program code;

a processor coupled with the memory;

the processor calls the executable program code stored in the memory to perform the method of predicting the number of real people according to any one of claims 1 to 8.