CN115099865A

CN115099865A - Data processing method and device

Info

Publication number: CN115099865A
Application number: CN202210800863.1A
Authority: CN
Inventors: 张同心
Original assignee: Beijing Jingdong Tuoxian Technology Co Ltd
Current assignee: Beijing Jingdong Tuoxian Technology Co Ltd
Priority date: 2022-07-08
Filing date: 2022-07-08
Publication date: 2022-09-23

Abstract

The invention discloses a data processing method and device, and relates to the technical field of commodity recommendation. One embodiment of the method comprises: analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data; classifying the plurality of order data according to the analysis result, wherein the longitude and latitude corresponding to the plurality of order data belonging to the same class are within a preset longitude and latitude range; and analyzing the demand condition of each article in one or more pieces of order data belonging to the same class, and providing the analyzed result to the information demand side so that the information demand side manages the article according to the demand condition of the article. The embodiment can effectively improve the prediction accuracy aiming at the user requirements.

Description

Data processing method and device

Technical Field

The invention relates to the technical field of commodity recommendation, in particular to a data processing method and device.

Background

In a business scenario of an Online-Offline shop combination (O2O) of the internet, for example, business scenarios such as a takeout service, an Online taxi service, and various entrance services provided by Offline shops, order data generally need To be analyzed To count user demands in different areas in order To better meet the user demands.

At present, the order data is mainly analyzed according to the three-level addresses (province, city and district) of the order data, the order data belonging to the same three-level address is analyzed so as to predict the demands of users on goods under the same three-level address, and according to the prediction result, differentiated goods recommendation is performed on different areas, such as recommendation of medicines, health care products, health appliances and the like. The existing user demand prediction has larger granularity (the same three-level address), so that the prediction accuracy is lower.

Disclosure of Invention

In view of this, embodiments of the present invention provide a data processing method and apparatus, which can effectively improve prediction accuracy for user requirements.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a data processing method including:

analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data;

classifying the plurality of order data according to the analysis result, wherein the longitude and latitude corresponding to the plurality of order data belonging to the same class are within a preset longitude and latitude range;

and analyzing the demand condition of various articles in one or more pieces of order data belonging to the same class, and providing the analyzed result to an information demander so that the information demander manages the articles according to the demand condition of the articles.

Optionally, the data processing method further includes: dividing a plurality of area grids on a preset map, wherein each area grid corresponds to a preset longitude and latitude range;

the analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data comprises:

and determining the regional grids to which the longitude and latitude corresponding to the address information included in each order data belongs according to the corresponding longitude and latitude ranges of the regional grids, wherein the longitude and latitude corresponding to a plurality of order data belonging to the same regional grid are in the corresponding longitude and latitude ranges of the regional grids.

Optionally, the analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data includes:

converting the longitude and latitude corresponding to the address information into a first hash code aiming at the longitude and latitude corresponding to the address information included in each order data;

and determining that the order data with the same first hash code have similar longitude and latitude.

Optionally, the analyzing the demand condition of each item in one or more of the order data belonging to the same class includes:

for one or more of the order data included in each category, performing the following operations:

and predicting the demand degree of the user for the goods according to the feature codes of various goods included in one or more order data and the demand quantity corresponding to the feature codes.

Optionally, the dividing a plurality of area grids on the preset map includes:

converting the longitude and latitude on a preset map into a corresponding second hash code;

and dividing a plurality of longitudes and latitudes corresponding to the same second Hash code into the same area grid, and determining the latitude and longitude range of the area grid.

Optionally, the converting the longitude and latitude corresponding to the address information into a first hash code includes:

converting the longitude and latitude in the longitude and latitude corresponding to the address information into a binary character string with a set length;

combining the binary character string corresponding to the longitude and the binary character string corresponding to the latitude into a new binary character string in a character insertion mode;

and converting the new binary character string into a first hash code of 32 systems according to a preset 32-system table.

Optionally, the predicting the demand of the user for the item includes:

and calculating the demand degree of the user for the article according to the multiple demand quantities corresponding to the feature codes and the preset weight of each demand quantity.

Optionally, the converting the longitude and latitude on the preset map into a corresponding second hash code includes:

converting the longitude and latitude in the longitude and latitude on the map into a binary character string;

combining a binary string corresponding to longitude on the map and a binary string corresponding to latitude on the map into a new binary string corresponding to longitude and latitude on the map in a character interleaving mode;

and converting the new binary character string corresponding to the longitude and latitude on the map into a second hash code of the 32 system according to a preset 32-level tabulation.

Optionally, the data processing method further includes:

aggregating a plurality of adjacent area grids into a new area grid according to the length of the area grid and a preset area theoretical length so as to enable the difference value between the length of the new area grid and the area theoretical length to be within a preset difference value range;

and determining the latitude and longitude range of the new area grid.

Optionally, converting the longitude and latitude of the longitude and latitude into a binary string, including:

circularly executing the following operations by taking the longitude and the latitude as target data respectively until a loop stop condition is satisfied:

dividing the current data interval into two new data intervals by using the intermediate value of the current data interval corresponding to the target data;

under the condition that the target data belong to a first data interval of the two new data intervals, allocating a first numerical value belonging to a binary system to the target data, and taking the first data interval as the current data interval;

under the condition that the target data belong to a second data interval of the two new data intervals, distributing a second value belonging to a binary system to the target data, and taking the second data interval as the current data interval;

and after the circulation is finished, combining the first numerical values and/or the second numerical values obtained by the circulation to obtain a binary character string.

In a second aspect, an embodiment of the present invention provides a data processing apparatus, including: an analysis module, an order classification module, and a demand prediction module, wherein,

the analysis module is used for analyzing the similar situation between the longitude and latitude corresponding to the address information included in the plurality of order data;

the order classification module is used for classifying the order data according to the analysis result of the analysis module, wherein the order data belonging to the same class are corresponding to similar longitudes and latitudes;

the demand forecasting module is used for analyzing the demand condition of various articles in one or more pieces of order data belonging to the same class and providing the analyzed result to the information demander so that the information demander manages the articles according to the demand condition of the articles.

One embodiment of the above invention has the following advantages or benefits: because the similar situation between the latitude and the longitude corresponding to the address information included in the plurality of order data is analyzed, the similar situation can better aggregate the address information with similar distance, the plurality of order data with the latitude and the longitude within the preset latitude and longitude range are divided into the same class according to the analysis result, namely, the region with smaller granularity can be divided according to the latitude and longitude, so that the plurality of order data with the similar distance to the address information are divided into the same class, namely, the plurality of order data belonging to the smaller region are determined, and the article requirement of the region with smaller granularity is analyzed by analyzing the requirement situation of various articles in one or more of the order data belonging to the same class, thereby effectively improving the prediction accuracy aiming at the user requirement.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic diagram of a main flow of a data processing method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a main flow of dividing a plurality of area grids according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a partial map divided into a plurality of regional grids in accordance with an embodiment of the present invention;

fig. 4 is a schematic diagram of a main flow of analyzing a similarity between latitudes and longitudes corresponding to address information included in a plurality of order data according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a main flow of converting longitude and latitude corresponding to address information into a first hash code according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a main flow of converting longitudes and latitudes of longitudes and latitudes into binary strings according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of an architecture on which a data processing method according to an embodiment of the present invention depends;

FIG. 8 is a schematic diagram of the main modules of a data processing apparatus according to an embodiment of the present invention;

FIG. 9 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 10 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a data processing method according to an embodiment of the present invention. As shown in fig. 1, the data processing method may include the steps of:

step S101: analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data;

step S102: classifying the plurality of order data according to the analysis result, wherein the plurality of order data classified to the same class are in a preset longitude and latitude range;

step S103: and analyzing the demand condition of each article in one or more pieces of order data belonging to the same class, and providing the analyzed result to the information demand side so that the information demand side manages the article according to the demand condition of the article.

The address information included in the order data may be any one or more of the following addresses:

a shipping address, a customer order placement address, and an address of a store selected by the customer. The receiving address refers to an address of an article for receiving a receipt by a user through express; the order placing address of the user refers to an address located by the user terminal when the user places an order. For example, if the user selects an online item or an online service of a store with address B at address a, places an order, and delivers the item of the order to address C or performs the online service at address C, address a is the address of placing the order of the user, address B is the address of the store selected by the user, and address C is the shipping address.

The similarity between the longitude and latitude corresponding to the address information included in the plurality of order data is mainly related to the region granularity, the longitude and latitude with smaller span or smaller distance have similarity under the condition that the region granularity is smaller, and the longitude and latitude with larger span or larger distance have similarity under the condition that the region granularity is larger.

The latitude and longitude generally refer to the latitude and longitude of a location, for example, the latitude and longitude corresponding to the address information refer to the latitude and longitude corresponding to the address information. Correspondingly, the latitude and longitude range refers to a combination of the latitude and longitude ranges, an area can be determined through the latitude and longitude ranges, and the size of the determined area can be regulated and controlled through the regulation and control of the latitude and longitude ranges.

In addition, the preset longitude and latitude ranges can be multiple, and the multiple longitude and latitude ranges are not overlapped generally. Accordingly, the latitude and longitude corresponding to one order data is generally only within one latitude and longitude range.

It is to be understood that, as a result of the classification at step S102, in addition to the plurality of order data belonging to the same class, in a case where the longitude and latitude of the address information of a single order data and the longitude and latitude of the address information of other order data are not within the preset same longitude and latitude range, the single order data may be classified into a single class.

The information demand party can be various offline stores, online platforms and the like. The management of the article may be adjusting inventory of the article, an article information push policy, an article information retrieval policy, and the like.

In the embodiment shown in fig. 1, by analyzing the similarity between the latitude and longitude corresponding to the address information included in the plurality of order data, the similarity can better aggregate the address information with similar distances, according to the analysis result, the plurality of order data with the latitude and longitude belonging to the same preset latitude and longitude range are divided into the same class, that is, an area with smaller granularity can be divided according to the latitude and longitude, so as to realize the division of the plurality of order data with the similar distances belonging to the same class, that is, the plurality of order data belonging to the smaller area are determined, and by analyzing the demand condition of each article in one or more of the order data belonging to the same class, the analysis of the article demand of the area with smaller granularity is realized, so as to effectively improve the prediction accuracy for the user demand.

There may be two implementation manners of the step S101.

In this embodiment of the present invention, with respect to the first implementation manner of step S101, the data processing method further includes: dividing a plurality of regional grids on a preset map, wherein each regional grid corresponds to a preset longitude and latitude range; for example, the partial map shown in fig. 3 is divided into a plurality of area grids: wtw7, 7p, wtw7, 7r, wtw7, 7x, wtw7, 7n, wtw7, 7q, wtw7, 7w, wtw7, 7j, wtw7, 7m and wtw7, 7t, wherein the latitude and longitude ranges of each area grid are respectively: wtw7 longitude range of 7p is LO 1-LO 2, latitude range is LA 1-LA 2; wtw7 longitude range of 7r is LO 2-LO 3, latitude range is LA 1-LA 2; wtw7 longitude range of 7x is LO 3-LO 4, latitude range LA 1-LA 2; wtw7 longitude range of 7n is LO 1-LO 2, latitude range is LA 2-LA 3; wtw7 longitude range of 7q is LO 2-LO 3, latitude range LA 2-LA 3; wtw7 longitude range of 7w is LO 3-LO 4, latitude range LA 2-LA 3; wtw7 longitude range of 7j is LO 1-LO 2, latitude range is LA 3-LA 4; the longitude ranges of wtw7m are LO 2-LO 3, the longitude ranges of the latitude ranges of LA 3-LA 4 and wtw7t are LO 3-LO 4, and the longitude ranges of the latitude ranges of LA 3-LA 4. Accordingly, a specific implementation of analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data may include: and determining the regional grids to which the longitude and latitude corresponding to the address information included in each order data belong according to the corresponding longitude and latitude ranges of the regional grids, wherein the longitude and latitude corresponding to a plurality of order data belonging to the same regional grid are in the corresponding longitude and latitude ranges of the regional grids. For example, the longitude and latitude corresponding to order data 1, order data 2, and order data 3 all belong to area grid wtw7t, and then it is determined that the longitude and latitude corresponding to order data 1, order data 2, and order data 3 are within the longitude and latitude range corresponding to area grid wtw7 t. Through the process, the granularity of the area grids can be determined according to the needs, so that the requirements of users on different area granularities can be better met.

Specifically, as shown in fig. 2, the above-mentioned embodiment of dividing a plurality of area grids on a preset map may include the following steps:

step S201: converting the longitude and latitude on a preset map into a corresponding second hash code;

the region grids of the partial map as shown in fig. 3, wherein wtw7p, wtw7r, wtw7x, wtw7n, wtw7q, wtw7w, wtw7j, wtw7m and wtw7t are respectively second hash codes of the respective region grids.

Specifically, specific embodiments of this step may include: converting the longitude and latitude in the longitude and latitude on the map into a binary character string; combining a binary character string corresponding to longitude on a map and a binary character string corresponding to latitude on the map into a new binary character string corresponding to the longitude and the latitude on the map in a character interleaving mode; and converting the new binary character string corresponding to the longitude and latitude on the map into a second hash code of the 32 system according to a preset 32-level tabulation.

Specifically, the longer the length of the binary string, the smaller the granularity of the area grid, the smaller the size of the area, the shorter the length of the binary string, the larger the granularity of the area grid, and the larger the size of the area grid, and a user can set the length of the binary string according to actual requirements, so as to dynamically adjust the granularity or size of the area grid.

The character interleaving refers to that each character of a longitude binary string is interleaved among each character of a latitude binary string, so that each character of the longitude binary string in odd digits and each character of the latitude binary string in even digits in a new binary string are formed, or each character of the latitude binary string in odd digits and each character of the longitude binary string in even digits in the new binary string are formed. The new binary character string is formed by inserting characters, so that the front characters of the new binary character string of two pieces of address information with similar distances are basically consistent, and the similar address information can be guaranteed to belong to the same grid.

Step S202: and dividing a plurality of longitudes and latitudes corresponding to the same second Hash code into the same area grid, and determining the latitude and longitude range of the area grid.

Through the process, the regional grids can be divided according to the user requirements, so that the follow-up analysis on the article requirement condition is met, and the accuracy of the follow-up analysis is ensured.

Further, with respect to the first implementation manner of the step S101, the method may further include: aggregating a plurality of adjacent regional grids into a new regional grid according to the lengths of the regional grids and the preset regional theoretical length so as to enable the difference between the length of the new regional grid and the regional theoretical length to be within the preset difference range; determining the latitude and longitude range of the new area grid.

The longitude interval, the latitude interval and the area grid size corresponding to different binary string lengths can be shown in table 1 below.

TABLE 1

For example, when the length of the binary string is 1, both the longitude and latitude intervals are [ -23, 23], and the size of the grid is-2500 to 2500km, that is, when the length of the binary string is 1, both the longitude and latitude spans of one regional grid are 23- (-23) ═ 46, and the length of the grid is 2500- (-2500) ═ 5000. For another example, when the binary string length is 7, the longitude and latitude intervals are both [ -0.00068, 0.00068], the grid size is-0.076 to 0.076km, that is, when the binary string length is 7, the longitude and latitude spans of one regional grid are both 0.00068- (-0.0068) ═ 0.00136, and the grid length is 0.076- (-0.076) ═ 0.152.

For example, when the preset theoretical length of an area is 900 meters for an area grid divided by a binary string having a length of 7, 6 × 6 area grids need to be aggregated, and the obtained new area grid has a length of 0.152 × 6-0.912 km.

Through the process, the divided regional grids or the new regional grids obtained by aggregation can better meet the user requirements, so that the analysis result of the order data in the regional grids can more accurately reflect the user requirements.

In the embodiment of the present invention, as shown in fig. 4, the second implementation manner of step S101 may include the following steps:

step S401: converting the longitude and latitude corresponding to the address information into a first hash code aiming at the longitude and latitude corresponding to the address information included in each order data;

step S402: and determining that the plurality of order data with the same first hash codes have similar longitude and latitude.

Through the process, the order data which are close in distance, namely correspond to similar longitude and latitude can be determined, and the order data can be directly clustered according to the area.

Specifically, as shown in fig. 5, a specific implementation of the step S401 may include the following steps:

step S501: converting the longitude and latitude in the longitude and latitude corresponding to the address information into a binary character string with a set length;

for example, the longitude and latitude point corresponding to the address information of one order data is (121.4396, 31.1932), and the binary string of longitude 121.4396 obtained through this step is 110101100101101; a binary string of latitude 31.1932 of 101011000101110;

step S502: combining the binary character string corresponding to the longitude and the binary character string corresponding to the latitude into a new binary character string in a character interleaving mode;

for example, one implementation may be: the longitude and latitude binary character strings are recombined according to the principle of 'even number of latitude and odd number of longitude', and the new combined binary character string is as follows: 111001100111100000110011110110. in addition, the combination can be recombined according to the principle that longitude places even digits and latitude places odd digits. The method can ensure that the first bits of the area codes with similar longitude and latitude are the same so as to facilitate the subsequent retrieval of the area.

Step S503: and converting the new binary character string into a first hash code of 32 system according to a preset 32 system table.

In an embodiment of the present invention, the specific implementation manner of analyzing the demand condition of each item in one or more order data belonging to the same category may include:

for each of the one or more order data included in the category, performing the following:

and predicting the demand of the user for the goods according to the characteristic codes of various goods and the demand quantity corresponding to the characteristic codes, which are included in the one or more order data.

The specific implementation of predicting the demand of the user on the item may include: and calculating the demand degree of the user for the goods according to the multiple demand quantities corresponding to the feature codes and the preset weight of each demand quantity.

Specifically, the degree of demand of the user for the item can be calculated by the following calculation formula (1).

K＝ω ₁ V ₁ +ω ₂ V ₃ +ω ₃ V ₃ (1)

Wherein K represents the user demand degree; omega ₁ A weight characterizing a first set number of days; v ₁ Representing the average daily demand in a first set number of days; omega ₂ A weight characterizing a second set number of days; v ₂ Representing the average daily demand in a second set number of days; omega ₃ Characterizing a weight for a third set number of days; v ₃ And characterizing the average daily demand in a third set number of days. The first set number of days, the second set number of days, the third set number of days and their corresponding weights may be set according to the user's requirement. For example, the first set number of days, the second set number of days, and the third set number of days are 1 day, 3 days, and 15 days, respectively.

By the prediction mode, the consumption of computing resources can be effectively reduced, and meanwhile, the accuracy of a prediction result can be ensured.

In an embodiment of the present invention, as shown in fig. 6, the specific implementation of converting the longitude and the latitude of the longitude and the latitude into a binary string may include:

the following steps S601 to S605 are executed in a loop with the longitude and the latitude as target data, respectively, until a loop stop condition is satisfied:

step S601: dividing the current data interval into two new data intervals by using the intermediate value of the current data interval corresponding to the target data; in a case where the target data belongs to the first data interval of the two new data intervals, step S602 is executed; in the case where the target data belongs to the second data interval of the two new data intervals, performing step S604;

wherein, in the starting phase, the current data interval allocated for longitude is a complete interval [ -180,180] of longitude; the current data interval allocated for latitude is a complete interval of latitude [ -90,90 ].

Taking the latitude 31.1932 of the longitude and latitude points (121.4396, 31.1932) as an example, the current data interval at the beginning stage is [ -90,90], and the corresponding median is 0, then the [ -90,90] is divided into two new intervals [ -90,0] and [0,90], wherein the latitude 31.1932 belongs to the second data interval [0,90 ]. In the next cycle, the interval [0,90] is divided into two new intervals [0,45] and [45,90] by the median 45 as the current data interval, where the latitude 31.1932 belongs to the first data interval [0,45 ]. For example, if the first binary value corresponding to the first data interval is 1 and the second binary value corresponding to the second data interval is 0, the two characters obtained through two cycles are 10 … ….

An example of the first binary value corresponding to the first data interval and the second binary value corresponding to the second data interval in the two new data intervals and the obtained characters of the binary string corresponding to the latitude 31.1932 can be shown in table 2 below.

TABLE 2

Step S602: allocating a first numerical value belonging to a binary system to the target data, determining whether the current cycle period meets a cycle stop condition, and if so, executing a step S606; if not, executing step S603;

step S603: taking the first data interval as a current data interval, and executing the step S601;

step S604: allocating a second numerical value belonging to a binary system to the target data, determining whether the current cycle period meets a cycle stop condition, and if so, executing a step S606; if not, go to step S605;

step S605: taking the second data interval as the current data interval, and executing the step S601;

step S606: and combining the plurality of first numerical values and/or the plurality of second numerical values obtained by circulation to obtain a binary character string.

The architecture on which the above data processing method depends can be as shown in fig. 7. As shown in fig. 7, the architecture on which the data processing method depends may include a data layer, a logic layer and an application layer, where the data layer provides basic data required for the logic layer, such as order data, search result data, and the like, and generates grid data required for a network, such as a point of interest (AOI), a delivery point of delivery (POI), administrative region division data, and the like, the logic layer implements services of map service, data division, grid positioning, and address translation latitude and longitude, and the map division area grid and address information of the order data are divided by services of map service, data division, grid positioning, address translation latitude and longitude, and the like, so that the order data is processed according to the method provided in the above embodiment. In addition, the user can be correspondingly configured according to the requirement through time configuration and weight configuration, and finally, the processing result of the logic layer is displayed for the user through a business guidance tool, a recommendation strategy, a search test and the like arranged by the application layer, and the recommendation strategy and the search strategy obtained through further analysis on the processing result of the logic layer are provided for reference of a demand party such as a store and the like.

The logical layers shown with respect to fig. 7 may be packaged as a data processing apparatus. As shown in fig. 8, the data processing apparatus 800 may include: an analysis module 801, an order classification module 802, and a demand prediction module 803, wherein,

an analysis module 801, configured to analyze similarity between longitude and latitude corresponding to address information included in the plurality of order data;

the order classification module 802 is configured to classify the plurality of order data according to the analysis result of the analysis module 801, where the longitude and latitude corresponding to the plurality of order data belonging to the same class are within a preset longitude and latitude range;

the demand forecasting module 803 is configured to analyze demand situations of various items in one or more pieces of order data belonging to the same category, and provide the analyzed result to the information demander, so that the information demander manages the items according to the demand situations of the items.

In the embodiment of the present invention, the analysis module 801 is further configured to divide a plurality of area grids on a preset map, where each area grid corresponds to a preset longitude and latitude range; and determining the regional grids to which the longitude and latitude corresponding to the address information included in each order data belong according to the corresponding longitude and latitude ranges of the regional grids, wherein the longitude and latitude corresponding to a plurality of order data belonging to the same regional grid are in the corresponding longitude and latitude ranges of the regional grids.

In this embodiment of the present invention, the analysis module 801 is further configured to, for the longitude and latitude corresponding to the address information included in each order data, convert the longitude and latitude corresponding to the address information into a first hash code; and determining that the plurality of order data with the same first hash codes have similar longitude and latitude.

In this embodiment of the present invention, the demand predicting module 803 is further configured to, for one or more pieces of order data included in each category, perform demand forecasting on the demand degree of the user for the item according to the feature codes and the demand amounts corresponding to the feature codes of various items included in the one or more pieces of order data.

In the embodiment of the present invention, the analysis module 801 is further configured to convert the longitude and latitude on the preset map into a corresponding second hash code; and dividing a plurality of longitudes and latitudes corresponding to the same second Hash code into the same area grid, and determining the latitude and longitude range of the area grid.

In the embodiment of the present invention, the analysis module 801 is further configured to convert the longitude and the latitude of the longitude and the latitude corresponding to the address information into a binary string with a set length; combining a binary character string corresponding to the longitude and a binary character string corresponding to the latitude into a new binary character string in a character interleaving mode; and converting the new binary character string into a first hash code of 32 system according to a preset 32 system table.

In this embodiment of the present invention, the analysis module 801 is further configured to calculate a demand degree of the user for the item according to the multiple demand amounts corresponding to the feature codes and the preset weight of each demand amount.

In this embodiment of the present invention, the analysis module 801 is further configured to convert the longitude and latitude of the longitude and latitude on the map into a binary string; combining a binary character string corresponding to longitude on a map and a binary character string corresponding to latitude on the map into a new binary character string corresponding to the longitude and the latitude on the map in a character interleaving mode; and converting the new binary character string corresponding to the longitude and latitude on the map into a second hash code of the 32 system according to a preset 32-level tabulation.

In this embodiment of the present invention, the analysis module 801 is further configured to aggregate a plurality of adjacent area grids into a new area grid according to the length of the area grid and a preset area theoretical length, so that a difference between the length of the new area grid and the area theoretical length is within a preset difference range; and determining the latitude and longitude range of the new area grid.

In this embodiment of the present invention, the analyzing module 801 is further configured to take the longitude and the latitude as target data, and perform the following operations in a loop until a loop stop condition is satisfied:

dividing the current data interval into two new data intervals by using the intermediate value of the current data interval corresponding to the target data; under the condition that the target data belong to a first data interval of two new data intervals, allocating a first numerical value belonging to a binary system to the target data, and taking the first data interval as a current data interval; under the condition that the target data belongs to a second data interval of the two new data intervals, distributing a second value belonging to a binary system to the target data, and taking the second data interval as a current data interval;

and after the circulation is finished, combining the plurality of first numerical values and/or the plurality of second numerical values obtained by the circulation to obtain a binary character string.

Fig. 9 shows an exemplary system architecture 900 of a data processing method or data processing apparatus to which embodiments of the present invention may be applied.

As shown in fig. 9, the system architecture 900 may include

terminal devices

901, 902, 903, a network 904, a server 905, and an information push server 906. The network 904 is used to provide a medium for communication links between the

terminal devices

901, 902, 903 and the server 905, and between the server 905 and the information push server 906. Network 904 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

901, 902, 903 to interact with a server 905 over a network 904 to receive or send messages and the like. The

terminal devices

901, 902, 903 may have installed thereon various messenger client applications such as, for example only, a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, social platform software, etc.

The

terminal devices

901, 902, 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 905 may be a server that provides various services, such as a background management server (for example only) that provides support for an online interaction platform provided by offline services. The background management server may analyze and perform other processing on data such as order data of the online interaction platform, and send a processing result (for example, predicted demand of the user for the commodity — this is only an example) to the terminal device.

In addition, the server 905 may also send the processing result (for example, predicted demand of the user for the commodity — only an example) to the information push server 906, so that the information push server 906 adjusts a commodity push policy and the like based on the received processing result, so as to push commodity information for the user according to the commodity demand in each area more specifically according to the area.

It should be noted that the data processing method provided by the embodiment of the present invention is generally executed by the server 905, and accordingly, the data processing apparatus is generally disposed in the server 905.

It should be understood that the numbers of terminal devices, networks, servers and information push servers in fig. 9 are merely illustrative. There may be any number of terminal devices, networks, servers and information push servers, according to implementation needs.

Referring now to FIG. 10, a block diagram of a computer system 1000 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 10 is only an example, and should not bring any limitation to the functions and the use range of the embodiment of the present invention.

As shown in fig. 10, the computer system 1000 includes a Central Processing Unit (CPU)1001 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1002 or a program loaded from a storage section 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the system 1000 are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011. The computer program executes the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 1001.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an analysis module, an order classification module, and a demand prediction module. The names of these modules do not limit the module itself in some cases, and for example, the analysis module may be described as a "module that analyzes similarity between latitudes and longitudes corresponding to address information included in the plurality of order data".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data; classifying the plurality of order data according to the analysis result, wherein the longitude and latitude corresponding to the plurality of order data belonging to the same class are within a preset longitude and latitude range; and analyzing the demand condition of various articles in one or more pieces of order data belonging to the same class, and providing the analyzed result to the information demand side so that the information demand side manages the articles according to the demand condition of the articles.

According to the technical scheme of the embodiment of the invention, through analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data, the similarity can better aggregate the address information with similar distance, according to the analysis result, the plurality of order data with the longitude and latitude within the preset same longitude and latitude range are divided into the same class, namely, the region with smaller granularity can be divided according to the longitude and latitude, so that the plurality of order data with the similar distance belonging to the address information are divided into the same class, namely, the plurality of order data belonging to the smaller region are determined, and through analyzing the demand condition of various articles in one or more order data belonging to the same class, the article demand of the region with smaller granularity is analyzed, so that the prediction accuracy aiming at the user demand is effectively improved.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method, comprising:

2. The data processing method of claim 1,

further comprising: dividing a plurality of area grids on a preset map, wherein each area grid corresponds to a preset longitude and latitude range;

3. The data processing method of claim 1, wherein the analyzing similarity between the longitude and latitude corresponding to the address information included in the plurality of order data comprises:

4. The data processing method of claim 1, wherein the analyzing the demand condition of each item in one or more of the order data belonging to the same class comprises:

and predicting the demand degree of the user for the item according to the characteristic codes of various items included in one or more pieces of order data and the demand quantity corresponding to the characteristic codes.

5. The data processing method according to claim 2, wherein the dividing a plurality of area grids on a preset map comprises:

6. The data processing method according to claim 3, wherein the converting the latitude and longitude corresponding to the address information into a first hash code includes:

and converting the new binary character string into a 32-system first hash code according to a preset 32-system table.

7. The data processing method of claim 4, wherein predicting the desirability of the item by the user comprises:

and calculating the demand degree of the user for the article according to the various demand amounts corresponding to the feature codes and the preset weight of each demand amount.

8. The data processing method of claim 5, wherein the converting the longitude and latitude on the preset map into the corresponding second hash code comprises: converting the longitude and latitude in the longitude and latitude on the map into a binary character string;

9. The data processing method of claim 5, further comprising:

aggregating a plurality of adjacent regional grids into a new regional grid according to the length of the regional grid and a preset regional theoretical length so as to enable the difference between the length of the new regional grid and the regional theoretical length to be within a preset difference range;

and determining the latitude and longitude range of the new area grid.

10. The data processing method of claim 6 or 8, wherein converting the longitude and latitude of the latitude and longitude into a binary string comprises:

11. A data processing apparatus, comprising: an analysis module, an order classification module, and a demand prediction module, wherein,

the analysis module is used for analyzing the similarity between the longitude and latitude corresponding to the address information included in the plurality of order data;

the order classification module is used for classifying the order data according to the analysis result of the analysis module, wherein the longitude and latitude corresponding to the order data belonging to the same class are within a preset longitude and latitude range;

12. An electronic device for data processing, comprising:

one or more processors;

a storage device for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-10.

13. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-10.