CN113553500A - Merchant information recommendation method and device, electronic equipment and storage medium - Google Patents

Merchant information recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113553500A
CN113553500A CN202110730143.8A CN202110730143A CN113553500A CN 113553500 A CN113553500 A CN 113553500A CN 202110730143 A CN202110730143 A CN 202110730143A CN 113553500 A CN113553500 A CN 113553500A
Authority
CN
China
Prior art keywords
aoi
recommended
merchant
poi
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110730143.8A
Other languages
Chinese (zh)
Other versions
CN113553500B (en
Inventor
王力
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202110730143.8A priority Critical patent/CN113553500B/en
Publication of CN113553500A publication Critical patent/CN113553500A/en
Application granted granted Critical
Publication of CN113553500B publication Critical patent/CN113553500B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application discloses a merchant information recommendation method, a merchant information recommendation device, electronic equipment and a storage medium, wherein the method comprises the following steps: when the order quantity exceeds the servable order quantity, determining all AOIs in a distribution area to which the POI of the merchant to be recommended belongs; according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI, respectively determining the relevance of each AOI and the to-be-recommended merchant POI; determining at least one AOI according to the correlation between each AOI and the POI of the merchant to be recommended, wherein the AOI is used as the AOI to be recommended; and sending the information of the POI of the merchant to be recommended to a user terminal positioned in the AOI to be recommended. The embodiment of the application realizes that the order of the POI of the business to be recommended is concentrated into at least one AOI, thereby improving the order density, improving the distribution efficiency, relieving the distribution pressure, and enabling the user to find favorite dishes in a rush hour, and improving the user experience.

Description

Merchant information recommendation method and device, electronic equipment and storage medium
Technical Field
The embodiment of the application relates to the technical field of internet, in particular to a merchant information recommendation method and device, electronic equipment and a storage medium.
Background
In a take-out scene, due to objective conditions such as weather, traffic control, transport capacity tension and the like, when the order quantity exceeds the quantity capable of being served, the order can be exploded through manual examination.
The existing burst policy mainly has two types: 1) the trade company explodes the order: aiming at the situations of slow meal delivery and the like of merchants, the orders of the merchants are reduced by improving the delivery cost, reducing the delivery range and the like; 2) regional blasting: aiming at the situations of high order quantity and insufficient transportation capacity in the area, the order is reduced by reducing the distribution range of merchants in the area and restraining the demand of users. Fig. 1 is a schematic diagram of a reduced distribution range in a business order scene in the prior art, and fig. 2 is a schematic diagram of a reduced distribution range in a regional order scene in the prior art, as shown in fig. 1 and fig. 2, when an order is exploded, the distribution range of a merchant is reduced to the periphery of the business, and the distribution range is greatly reduced.
In the single explosion scene, the existing merchant information recommendation mode mainly reduces orders by reducing the merchant distribution range, and although the mode can relieve distribution pressure, a large number of orders are reduced, so that a user can not find favorite dishes in the single explosion scene, the user experience is influenced, and the distribution of the orders is still dispersed after the distribution range is reduced, and the distribution efficiency is influenced.
Disclosure of Invention
The embodiment of the application provides a merchant information recommendation method and device, electronic equipment and a storage medium, and the merchant information recommendation method and device are beneficial to improving order density, improving distribution efficiency and improving user experience.
In order to solve the above problem, in a first aspect, an embodiment of the present application provides a merchant information recommendation method, including:
when the order quantity exceeds the servable order quantity, determining all AOIs in a distribution area to which the POI of the merchant to be recommended belongs;
according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI, respectively determining the relevance of each AOI and the to-be-recommended merchant POI;
determining at least one AOI according to the correlation between each AOI and the POI of the merchant to be recommended, wherein the AOI is used as the AOI to be recommended;
and sending the information of the POI of the merchant to be recommended to a user terminal positioned in the AOI to be recommended.
In a second aspect, an embodiment of the present application provides a merchant information recommendation device, including:
the in-area AOI determining module is used for determining all AOI in the distribution area to which the POI of the merchant to be recommended belongs when the order quantity exceeds the serviceable order quantity;
the correlation determination module is used for respectively determining the correlation between each AOI and the to-be-recommended merchant POI according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI;
the to-be-recommended AOI determining module is used for determining at least one AOI according to the correlation between each AOI and the to-be-recommended merchant POI, and the AOI is used as the to-be-recommended AOI;
and the business information recommending module is used for sending the information of the business POI to be recommended to the user terminal positioned in the AOI to be recommended.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the merchant information recommendation method according to the embodiment of the present application.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the merchant information recommendation method disclosed in the present application.
According to the merchant information recommendation method, the merchant information recommendation device, the electronic equipment and the storage medium, when the current order volume exceeds the servable order volume, all AOIs in a distribution area to which a merchant POI to be recommended belongs are determined, the correlation between each AOI and the merchant POI to be recommended is respectively determined according to historical data of the merchant POI to be recommended and historical data of each AOI, at least one AOI is determined according to the correlation between each AOI and the merchant POI to be recommended and serves as the AOI to be recommended, information of the merchant POI to be recommended is sent to a user terminal located in the AOI to be recommended, the order of the merchant POI to be recommended is concentrated into the at least one AOI, the order density is improved, the distribution efficiency can be improved, the distribution pressure can be relieved, a user can also find favorite dishes in a peak period, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic illustration of a reduced delivery envelope in a prior art merchant waybill scenario;
FIG. 2 is a schematic illustration of a reduced delivery envelope in a prior art area blast scene;
fig. 3 is a flowchart of a merchant information recommendation method according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a model for predicting the relevance of AOI and POI in the embodiment of the present application;
FIG. 5 is a schematic diagram of a recommendation range of merchant information in a merchant waybill scenario in an embodiment of the present application;
FIG. 6 is a schematic diagram of a recommendation range of merchant information in a regional business burst scenario in an embodiment of the present application;
fig. 7 is a schematic structural diagram of a merchant information recommendation device according to a second embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
As shown in fig. 3, the merchant information recommendation method provided in this embodiment includes: step 310 to step 340.
And step 310, when the order quantity exceeds the serviceable order quantity, determining all AOIs in the distribution area to which the POI of the merchant to be recommended belongs.
The amount of serviceable orders may be a preset numerical value, or a numerical value dynamically determined according to information such as the current amount of delivery capacity, the current distribution of delivery capacity, and the amount of orders of merchants, or may be information manually triggered by the merchants according to their own service conditions.
When the order size exceeds the amount of serviceable orders, the delivery envelope needs to be narrowed to reduce the partial order. In the embodiment Of the application, when the distribution range is reduced, the order is collected into at least one AOI (Area Of Interest), at this time, a suitable AOI needs to be determined, so that the single amount is not reduced too much, all AOIs in a distribution Area to which a to-be-recommended merchant POI (Point Of Interest) belongs need to be determined, then, at least one AOI can be determined from all AOIs, and information Of the to-be-recommended merchant POI is recommended to a user terminal in the determined at least one AOI. Wherein, the AOI may be a cell or an office building or the like.
In one embodiment of the present application, when the order quantity exceeds the serviceable order quantity, determining all AOIs in the distribution area to which the POI of the merchant to be recommended belongs includes:
when the order quantity of the current merchant POI exceeds the serviceable order quantity, taking the current merchant POI as a merchant POI to be recommended, and determining all AOI in a distribution area to which the merchant POI to be recommended belongs; or
When the order quantity in the distribution area exceeds the servable order quantity, determining all AOIs in the distribution area, acquiring merchant POI clusters in the distribution area, traversing the merchant POI clusters, and taking the current merchant POI clusters as the merchant POIs to be recommended.
The order quantity exceeds the amount of the serviceable order, namely the condition of the blast order occurs, and the conditions can be divided into two conditions, namely a merchant blast order and a regional blast order. In a business order explosion scene, the order quantity of the current business POI exceeds the serviceable order quantity, at the moment, the current business POI of the business order explosion is taken as the business POI to be recommended, and all AOIs in a distribution area to which the business POI to be recommended belongs are determined. In an area waybill scene, the order quantity of a current distribution area exceeds the amount of serviceable waybill, at this time, a merchant POI cluster in the distribution area can be obtained from the storage position of the merchant POI cluster, or the merchant POI cluster in the distribution area is clustered in real time to obtain the merchant POI cluster in the distribution area, an AOI to be recommended is respectively determined for each POI cluster, at this time, all merchant POI clusters in the distribution area need to be traversed, the traversed current merchant POI cluster is used as a merchant POI to be recommended, at this time, the merchant POI to be recommended comprises a plurality of merchant POIs, and the merchant POIs are used as a whole to perform information recommendation. The merchant POI cluster refers to a plurality of merchant POIs which are close to each other.
In an embodiment of the present application, before the acquiring a merchant POI cluster in the distribution area, the method further includes: and clustering the merchant POI according to the longitude and latitude coordinates of the merchant POI in the distribution area to obtain a merchant POI cluster in the distribution area.
In an online scene, according to longitude and latitude coordinates of merchant POIs in a distribution area, clustering the merchant POIs in the distribution area through a dbscan algorithm, clustering the merchant POIs which are close to each other to the same merchant POI cluster to obtain a plurality of merchant POI clusters in the distribution area, and storing the merchant POI clusters in the distribution area. And (4) clustering the POI of the merchants in the distribution area under the line, and directly acquiring the offline clustering result when the area is exploded, thereby improving the online processing speed.
And 320, respectively determining the relevance of each AOI and the POI of the merchant to be recommended according to the historical data of the POI of the merchant to be recommended and the historical data of each AOI.
The relevance between the AOI and the to-be-recommended merchant POI represents the love degree of a user group in the AOI to the to-be-recommended merchant POI.
Analyzing and sorting historical data of the to-be-recommended merchant POI and historical data of each AOI, determining basic features of the to-be-recommended merchant, user group features in each AOI and cross features of the to-be-recommended merchant and each AOI, respectively predicting the relevance of each AOI, inputting the user group features of one AOI, the basic features of the to-be-recommended merchant POI and the cross features of the AOI and the to-be-recommended merchant POI into a relevance prediction model of the AOI and the POI, processing the features through the relevance prediction model to obtain the relevance of the AOI and the to-be-recommended merchant, and respectively predicting through the relevance prediction model by each AOI to obtain the relevance of each AOI and the to-be-recommended merchant POI.
In an embodiment of the present application, respectively determining, according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI, a correlation between each AOI and the to-be-recommended merchant POI includes: according to the historical data of the business POI to be recommended and the historical data of each AOI, respectively determining the user group characteristics of each AOI, the basic characteristics of the business POI to be recommended and the cross characteristics of the business POI to be recommended and each AOI; determining the distance between the POI of the merchant to be recommended and each AOI, and acquiring current time characteristics; and respectively determining the relevance of each AOI and the merchant POI to be recommended according to the user group characteristics, the basic characteristics, the cross characteristics, the distance and the current time characteristics.
Analyzing historical data of the to-be-recommended merchant POI, and counting the historical sales volume of the to-be-recommended merchant POI, the historical sales volume of the to-be-recommended merchant POI at the current moment, the activity information of the to-be-recommended merchant POI and the like to obtain the basic characteristics of the to-be-recommended merchant POI. And respectively determining user group characteristics aiming at each AOI, respectively analyzing historical data of each AOI, and determining order quantity, user conversion rate, user distribution information and the like in each AOI to obtain the user group characteristics of each AOI. And comprehensively analyzing the historical data of each AOI and the historical data of the POI of the merchant to be recommended respectively, determining the historical order quantity, the historical user click rate and the like of the POI of the merchant to be recommended in each AOI, and obtaining the cross characteristics of the POI of the merchant to be recommended and each AOI. Respectively determining the distance between the POI of the merchant to be recommended and each AOI based on the longitude and latitude coordinates of the POI of the merchant to be recommended and the longitude and latitude coordinates of each AOI, and acquiring current time characteristics (such as the time period, the week number and the like of the current time). And respectively inputting the corresponding user group characteristics, the cross characteristics of the business POI to be recommended, the basic characteristics of the business POI to be recommended, the distance, the current time characteristics and the like into a correlation prediction model of the AOI and the POI for each AOI, and obtaining the correlation between each AOI and the business POI to be recommended through the processing of the correlation prediction model.
Fig. 4 is a schematic structural diagram of a prediction model of relevance between AOI and POI in the embodiment of the present application, and as shown in fig. 4, features of a user group of AOI, a basic feature of a to-be-recommended merchant POI, a cross feature, a distance, a current time feature of AOI and POI, and the like are spliced into a whole, and the relevance between AOI and the to-be-recommended merchant POI is obtained through processing of multiple full connection layers.
Through analysis based on historical data of the to-be-recommended merchant POI and historical data of each AOI, the relevance between the AOI and the to-be-recommended merchant POI is determined, and the relevance can be determined accurately, so that the distribution density of orders can be improved, the distribution efficiency can be improved, and the distribution pressure can be reduced.
And 330, determining at least one AOI as the AOI to be recommended according to the correlation between each AOI and the POI of the merchant to be recommended.
According to the relevance of each AOI to-be-recommended merchant, selecting at least one AOI with the highest relevance from all AOIs as the AOI to be recommended; or, according to the relevance of each AOI to the merchant to be recommended and by combining the historical unit quantity of the merchant POI to be recommended and the current unit quantity of the merchant POI to be recommended of each AOI, at least one AOI with the highest relevance is selected from all the AOIs to serve as the AOI to be recommended.
In an embodiment of the present application, the determining, as the AOI to be recommended, at least one AOI according to a correlation between each AOI and the POI of the merchant to be recommended includes: determining the AOI with the highest correlation in a preset number as the AOI to be selected; and determining at least one AOI to be selected as the AOI to be recommended according to the correlation between the AOI to be selected and the POI of the merchant to be recommended, the current unit quantity of the AOI to be selected to the POI of the merchant to be recommended and the historical unit quantity of the POI of the merchant to be recommended.
After the relevance between all AOIs in the distribution area and the POI of the merchant to be recommended is determined, the preset number of AOIs with the highest relevance are determined from all AOIs to serve as the AOI to be selected, and at least one AOI is determined from the AOIs to be selected subsequently to serve as the AOI to be recommended. When determining the AOI to be recommended from the AOI to be selected, determining at least one AOI to be selected, of which the sum of the current units does not exceed the historical units of the POI of the merchant to be recommended, from the AOI to be selected according to the sequence of the relevance from high to low, and taking the determined at least one AOI to be selected as the AOI to be recommended. The preset number of AOIs with the highest correlation are determined to be the AOIs to be selected, and at least one AOI to be selected is determined from the AOIs to be selected on the basis of the correlation, the current single amount of the AOI to be selected and the historical single amount of the POI of the merchant to be recommended to be used as the AOI to be recommended, so that the calculation amount for determining the current single amount can be reduced, and the processing speed is improved.
In an embodiment of the present application, determining at least one to-be-selected AOI as the to-be-recommended AOI according to the correlation between the to-be-selected AOI and the to-be-recommended merchant POI, the current amount of the to-be-selected AOI to the to-be-recommended merchant POI, and the historical amount of the to-be-recommended merchant POI includes: determining the number of distributable merchants of each AOI to be selected at the current moment; determining the weight of each AOI to be selected according to the number of distributable merchants and the inverse relation between the weight and the number of distributable merchants; reordering the AOIs to be selected in the preset number according to the correlation and the weight; and determining at least one AOI to be selected from the reordered AOIs to be selected according to the current list of the AOI to be selected to the POI of the merchant to be recommended and the historical list of the POI of the merchant to be recommended, and taking the AOI to be selected as the AOI to be recommended.
Wherein the inverse relationship of the weight to the dispatchable quantity is a monotonically decreasing function of the weight with respect to the dispatchable quantity.
Counting the number of distributable merchants of each AOI to be selected at the current moment; determining the weight of each AOI to be selected according to the number of distributable merchants of each AOI to be selected and the inverse relation between the weight and the number of distributable merchants, so as to carry out right lifting on the AOI to be selected with a small number of distributable merchants and carry out right reduction on the AOI to be selected with a large number of distributable merchants; then, reordering the preset number of AOIs to be selected according to the relevance of the AOI to be selected to the POI of the merchant to be recommended and the weight of the AOI to be selected; and determining TopK AOIs to be selected from the reordered AOIs to be selected, namely determining at least one AOI to be selected as the AOI to be recommended, so that the sum of the current single amount of the AOI to be recommended does not exceed the historical single amount of the POI of the merchant to be recommended. The weight of the AOI to be selected is determined based on the number of the distributable merchants, so that the weight of the AOI to be selected with a small number of the distributable merchants is increased, the weight of the AOI to be selected with a large number of the distributable merchants is decreased, the AOI to be selected with a small number of the distributable merchants can be preferentially selected as the AOI to be recommended, the user requirement of the AOI to be recommended is met, and the supply of the AOI to be recommended is guaranteed.
In an optional implementation, the reordering the preset number of AOIs to be selected according to the correlation and the weight includes: adjusting the correlation corresponding to the AOI to be selected according to the weight of the AOI to be selected to obtain the adjusted correlation; and reordering the AOI to be selected according to the adjusted relevance corresponding to each AOI to be selected.
After determining the weight of the AOI to be selected, adjusting the correlation between the AOI to be selected and the POI of the merchant to be recommended by using the weight of the AOI to be selected, namely multiplying the weight of the AOI to be selected by the correlation between the AOI to be selected and the POI of the merchant to be recommended to obtain the adjusted correlation of the AOI to be selected; and reordering the AOI to be selected according to the sequence of the adjusted relevance from high to low. By adjusting the relevance by using the weight of the AOI to be selected and reordering the relevance, the AOI area with higher relevance and less distributable merchants can be preferentially selected as the AOI area to be recommended so as to ensure the supply of the AOI area with less distributable merchants.
In an optional implementation manner, determining at least one to-be-selected AOI from the reordered to-be-selected AOIs as the to-be-recommended AOI according to the current inventory of the to-be-selected AOI to the to-be-recommended merchant POI and the historical inventory of the to-be-recommended merchant POI includes: and determining at least one AOI to be selected from the reordered AOIs to be selected according to the sequence, so that the sum of the current single amount of the at least one AOI to be selected to the POI of the merchant to be recommended does not exceed the historical single amount of the POI of the merchant to be recommended, and determining the at least one AOI to be selected as the AOI to be recommended.
When the to-be-selected AOI is reordered, if the ordering is performed according to the adjusted order of the relevance from high to low, at least one to-be-selected AOI can be determined from the reordered to-be-selected AOIs according to the order from the beginning, so that the sum of the current single quantity of the to-be-selected AOI to the to-be-recommended merchant POI does not exceed the historical single quantity of the to-be-recommended merchant POI. When at least one AOI to be selected is determined, firstly, comparing the current unit quantity of a business POI to be recommended by a first AOI with the historical unit quantity of the business POI to be recommended; if the current single amount of the first AOI is smaller than the historical single amount of the POI of the merchant to be recommended, comparing the sum of the current single amounts of the first AOI and the second AOI with the historical single amount of the POI of the merchant to be recommended; if the sum of the current single quantities of the first AOI and the second AOI is larger than the historical single quantity of the POI of the merchant to be recommended, determining the first AOI as at least one AOI to be selected, if the sum of the current single quantities of the first AOI and the second AOI is equal to the historical single quantity of the POI of the merchant to be recommended, determining the first AOI and the second AOI as at least one AOI to be selected, if the sum of the current single quantities of the first AOI and the second AOI is larger than the historical single quantity of the POI of the merchant to be recommended, continuing to compare the sum of the current single quantities of the first AOI, the second AOI and the third AOI with the historical single quantity of the POI of the merchant to be recommended until the sum of the current single quantities of at least two POIs to be selected is larger than the historical single quantity of the POI of the merchant to be recommended, stopping comparison, and determining the sum of the current single quantities of the POI to be selected except the last POI to be selected in the at least two AOI to be selected as at least one AOI to be selected. The current single amount of the to-be-recommended merchant POI of the AOI to be selected can be an estimated result, and the historical single amount of the to-be-recommended merchant POI is the historical single amount of the to-be-recommended merchant POI in the current time period.
The maximum supply of the AOI to be recommended is ensured by ensuring that the sum of the current single amount of at least one AOI to be selected to the POI of the merchant to be recommended does not exceed the historical single amount of the POI of the merchant to be recommended.
And step 340, sending the information of the POI of the merchant to be recommended to a user terminal positioned in the AOI to be recommended.
And sending commodity information and other information of the to-be-recommended merchant POI to a user terminal in the to-be-recommended AOI, so that the user terminal in the to-be-recommended AOI can display the information of the to-be-recommended merchant POI, and the user terminals in other areas can not receive the information of the to-be-recommended merchant POI, thereby reducing the distribution area of the to-be-recommended merchant POI. The other information may be, for example, activity information or the like.
In a business order explosion scene, a business POI to be recommended is a business POI, and at this time, a schematic diagram of a business information recommendation range determined by the business information recommendation method provided by the embodiment of the present application is shown in fig. 5, that is, an order is concentrated into at least one AOI (AOI pointed by an arrow), so that order density is improved, and distribution efficiency can be improved.
In an area business burst scene, a business POI to be recommended is a business POI cluster and includes a plurality of business POIs, and at this time, a schematic diagram of a business information recommendation range determined by the business information recommendation method provided by the embodiment of the present application is shown in fig. 6, and orders of each business POI cluster are respectively collected into at least one AOI (AOI pointed by an arrow), so that order density is improved, and distribution efficiency can be improved.
According to the business information recommendation method provided by the embodiment of the application, when the current order volume exceeds the servable order volume, all AOIs in a distribution area to which business POIs to be recommended belong are determined, the correlation between each AOI and the business POIs to be recommended is respectively determined according to the historical data of the business POIs to be recommended and the historical data of each AOI, at least one AOI is determined according to the correlation between each AOI and the business POIs to be recommended and serves as the business POIs to be recommended, information of the business to be recommended is sent to a user terminal located in the business to be recommended, the order of the business POIs to be recommended is concentrated into the at least one AOI, the order density is improved, the distribution efficiency can be improved, the distribution pressure can be relieved, the user can also find favorite dishes in a peak period, and the user experience is improved.
Example two
As shown in fig. 7, the merchant information recommendation apparatus 700 according to this embodiment includes:
the intra-area AOI determining module 710 is configured to determine all AOIs in a distribution area to which the to-be-recommended merchant POI belongs when the order quantity exceeds the serviceable order quantity;
a relevance determining module 720, configured to determine, according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI, a relevance between each AOI and the to-be-recommended merchant POI;
the to-be-recommended AOI determining module 730 is configured to determine, according to a correlation between each AOI and the to-be-recommended merchant POI, at least one AOI as an AOI to be recommended;
and the merchant information recommending module 740 is configured to send the information of the merchant POI to be recommended to the user terminal located in the AOI to be recommended.
Optionally, the module for determining AOI to be recommended includes:
the to-be-selected AOI determining unit is used for determining the AOIs with the highest correlation and the preset number as the to-be-selected AOIs;
and the to-be-recommended AOI determining unit is used for determining at least one to-be-selected AOI as the to-be-recommended AOI according to the correlation between the to-be-selected AOI and the to-be-recommended merchant POI, the current unit quantity of the to-be-selected AOI to the to-be-recommended merchant POI and the historical unit quantity of the to-be-recommended merchant POI.
Optionally, the to-be-recommended AOI determining unit includes:
the number-of-distributable merchants determining subunit is used for determining the number of distributable merchants of each AOI to be selected at the current moment;
the weight determining subunit is configured to determine, according to the number of distributable merchants and an inverse relationship between the weight and the number of distributable merchants, a weight of each to-be-selected AOI;
a reordering subunit, configured to reorder, according to the correlation and the weight, the preset number of AOIs to be selected;
and the to-be-recommended AOI determining subunit is used for determining at least one to-be-recommended AOI from the reordered to-be-selected AOIs according to the current inventory of the to-be-selected AOI to the to-be-recommended merchant POI and the historical inventory of the to-be-recommended merchant POI, and the to-be-recommended AOI is used as the to-be-recommended AOI.
Optionally, the reordering subunit is specifically configured to:
adjusting the correlation corresponding to the AOI to be selected according to the weight of the AOI to be selected to obtain the adjusted correlation;
and reordering the AOI to be selected according to the adjusted relevance corresponding to each AOI to be selected.
Optionally, the to-be-recommended AOI determining subunit is specifically configured to:
and determining at least one AOI to be selected from the reordered AOIs to be selected according to the sequence, so that the sum of the current single amount of the at least one AOI to be selected to the POI of the merchant to be recommended does not exceed the historical single amount of the POI of the merchant to be recommended, and determining the at least one AOI to be selected as the AOI to be recommended.
Optionally, the correlation determination module includes:
the cross feature determination unit is used for respectively determining the user group feature of each AOI, the basic feature of the to-be-recommended merchant POI and the cross feature of the to-be-recommended merchant POI and each AOI according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI;
the distance and time characteristic determining unit is used for determining the distance between the POI of the merchant to be recommended and each AOI and acquiring the current time characteristic;
and the correlation determination unit is used for respectively determining the correlation between each AOI and the POI of the merchant to be recommended according to the user group characteristics, the basic characteristics, the cross characteristics, the distance and the current time characteristics.
Optionally, the intra-area AOI determining module is specifically configured to:
when the order quantity of the current merchant POI exceeds the serviceable order quantity, taking the current merchant POI as a merchant POI to be recommended, and determining all AOI in a distribution area to which the merchant POI to be recommended belongs; or
When the order quantity in the distribution area exceeds the servable order quantity, determining all AOIs in the distribution area, acquiring merchant POI clusters in the distribution area, traversing the merchant POI clusters, and taking the current merchant POI clusters as the merchant POIs to be recommended.
Optionally, the apparatus further comprises:
and the POI clustering module is used for clustering the merchant POI according to the longitude and latitude coordinates of the merchant POI in the distribution area to obtain a merchant POI cluster in the distribution area.
The merchant information recommendation device provided in the embodiment of the present application is used for implementing each step of the merchant information recommendation method described in the first embodiment of the present application, and specific implementation manners of each module of the device refer to the corresponding step, which is not described herein again.
The merchant information recommending device provided by the embodiment of the application determines all AOIs in a distribution area to which a merchant POI to be recommended belongs when the current order volume exceeds a serviceable order volume, determines the correlation between each AOI and the merchant POI to be recommended according to historical data of the merchant POI to be recommended and historical data of each AOI, determines at least one AOI as the AOI to be recommended, and sends information of the merchant POI to be recommended to a user terminal located in the AOI to be recommended, so that orders of the merchant POI to be recommended are concentrated in the at least one AOI, the order density is improved, the distribution efficiency can be improved, the distribution pressure can be relieved, favorite dishes of a user can be found in a rush hour, and the user experience is improved.
EXAMPLE III
Embodiments of the present application also provide an electronic device, as shown in fig. 8, the electronic device 800 may include one or more processors 810 and one or more memories 820 connected to the processors 810. Electronic device 800 may also include input interface 830 and output interface 840 for communicating with another apparatus or system. Program code executed by processor 310 may be stored in memory 820.
The processor 810 in the electronic device 800 calls the program code stored in the memory 820 to execute the merchant information recommendation method in the above-described embodiment.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the merchant information recommendation method according to the first embodiment of the present application.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The merchant information recommendation method, the merchant information recommendation device, the electronic device and the storage medium provided by the embodiment of the application are introduced in detail, a specific example is applied in the description to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Claims (11)

1. A merchant information recommendation method is characterized by comprising the following steps:
when the order quantity exceeds the servable order quantity, determining all AOIs in a distribution area to which the POI of the merchant to be recommended belongs;
according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI, respectively determining the relevance of each AOI and the to-be-recommended merchant POI;
determining at least one AOI according to the correlation between each AOI and the POI of the merchant to be recommended, wherein the AOI is used as the AOI to be recommended;
and sending the information of the POI of the merchant to be recommended to a user terminal positioned in the AOI to be recommended.
2. The method according to claim 1, wherein the determining at least one AOI according to the correlation between each AOI and the POI of the merchant to be recommended as the AOI to be recommended comprises:
determining the AOI with the highest correlation in a preset number as the AOI to be selected;
and determining at least one AOI to be selected as the AOI to be recommended according to the correlation between the AOI to be selected and the POI of the merchant to be recommended, the current unit quantity of the AOI to be selected to the POI of the merchant to be recommended and the historical unit quantity of the POI of the merchant to be recommended.
3. The method according to claim 2, wherein determining at least one AOI to be selected as the AOI to be recommended according to the correlation between the AOI to be selected and the merchant POI to be recommended, the current unit amount of the AOI to be selected to the merchant POI to be recommended and the historical unit amount of the merchant POI to be recommended comprises:
determining the number of distributable merchants of each AOI to be selected at the current moment;
determining the weight of each AOI to be selected according to the number of distributable merchants and the inverse relation between the weight and the number of distributable merchants;
reordering the AOIs to be selected in the preset number according to the correlation and the weight;
and determining at least one AOI to be selected from the reordered AOIs to be selected according to the current list of the AOI to be selected to the POI of the merchant to be recommended and the historical list of the POI of the merchant to be recommended, and taking the AOI to be selected as the AOI to be recommended.
4. The method according to claim 3, wherein the reordering the preset number of AOIs to be selected according to the correlation and the weight comprises:
adjusting the correlation corresponding to the AOI to be selected according to the weight of the AOI to be selected to obtain the adjusted correlation;
and reordering the AOI to be selected according to the adjusted relevance corresponding to each AOI to be selected.
5. The method according to claim 3, wherein determining at least one AOI to be selected from the reordered AOIs to be selected according to the current inventory of the AOI to be selected for the business POI to be recommended and the historical inventory of the business POI to be recommended as the AOI to be recommended comprises:
and determining at least one AOI to be selected from the reordered AOIs to be selected according to the sequence, so that the sum of the current single amount of the at least one AOI to be selected to the POI of the merchant to be recommended does not exceed the historical single amount of the POI of the merchant to be recommended, and determining the at least one AOI to be selected as the AOI to be recommended.
6. The method according to claim 1, wherein the determining the relevance of each AOI and the to-be-recommended merchant POI according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI respectively comprises:
according to the historical data of the business POI to be recommended and the historical data of each AOI, respectively determining the user group characteristics of each AOI, the basic characteristics of the business POI to be recommended and the cross characteristics of the business POI to be recommended and each AOI;
determining the distance between the POI of the merchant to be recommended and each AOI, and acquiring current time characteristics;
and respectively determining the relevance of each AOI and the merchant POI to be recommended according to the user group characteristics, the basic characteristics, the cross characteristics, the distance and the current time characteristics.
7. The method of claim 1, wherein when the order volume exceeds the serviceable order volume, determining all AOIs in the distribution area to which the POI of the merchant to be recommended belongs comprises:
when the order quantity of the current merchant POI exceeds the serviceable order quantity, taking the current merchant POI as a merchant POI to be recommended, and determining all AOI in a distribution area to which the merchant POI to be recommended belongs; or
When the order quantity in the distribution area exceeds the servable order quantity, determining all AOIs in the distribution area, acquiring merchant POI clusters in the distribution area, traversing the merchant POI clusters, and taking the current merchant POI clusters as the merchant POIs to be recommended.
8. The method of claim 7, further comprising, prior to said obtaining a cluster of merchant POIs within said shipping area:
and clustering the merchant POI according to the longitude and latitude coordinates of the merchant POI in the distribution area to obtain a merchant POI cluster in the distribution area.
9. A merchant information recommendation apparatus, comprising:
the in-area AOI determining module is used for determining all AOI in the distribution area to which the POI of the merchant to be recommended belongs when the order quantity exceeds the serviceable order quantity;
the correlation determination module is used for respectively determining the correlation between each AOI and the to-be-recommended merchant POI according to the historical data of the to-be-recommended merchant POI and the historical data of each AOI;
the to-be-recommended AOI determining module is used for determining at least one AOI according to the correlation between each AOI and the to-be-recommended merchant POI, and the AOI is used as the to-be-recommended AOI;
and the business information recommending module is used for sending the information of the business POI to be recommended to the user terminal positioned in the AOI to be recommended.
10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the merchant information recommendation method of any one of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the merchant information recommendation method according to any one of claims 1 to 8.
CN202110730143.8A 2021-06-29 2021-06-29 Merchant information recommendation method and device, electronic equipment and storage medium Active CN113553500B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110730143.8A CN113553500B (en) 2021-06-29 2021-06-29 Merchant information recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110730143.8A CN113553500B (en) 2021-06-29 2021-06-29 Merchant information recommendation method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113553500A true CN113553500A (en) 2021-10-26
CN113553500B CN113553500B (en) 2023-01-17

Family

ID=78102513

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110730143.8A Active CN113553500B (en) 2021-06-29 2021-06-29 Merchant information recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113553500B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109345299A (en) * 2018-09-21 2019-02-15 北京三快在线科技有限公司 A kind of method and device adjusting service range
CN109598447A (en) * 2018-12-10 2019-04-09 拉扎斯网络科技（上海）有限公司 With pressurization pressure adjustment, order allocation method and device, electronic equipment and medium
CN109636013A (en) * 2018-11-27 2019-04-16 拉扎斯网络科技（上海）有限公司 Dispense generation method, device, electronic equipment and the storage medium of range
CN109658034A (en) * 2018-12-28 2019-04-19 拉扎斯网络科技（上海）有限公司 Dispense range generation method, dispatching pressure regulating method, device and server
CN111539591A (en) * 2019-09-23 2020-08-14 拉扎斯网络科技（上海）有限公司 Data processing method and device, readable storage medium and electronic equipment
CN112016863A (en) * 2019-05-29 2020-12-01 拉扎斯网络科技（上海）有限公司 Method and device for determining distribution range, readable storage medium and electronic equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109345299A (en) * 2018-09-21 2019-02-15 北京三快在线科技有限公司 A kind of method and device adjusting service range
CN109636013A (en) * 2018-11-27 2019-04-16 拉扎斯网络科技（上海）有限公司 Dispense generation method, device, electronic equipment and the storage medium of range
CN109598447A (en) * 2018-12-10 2019-04-09 拉扎斯网络科技（上海）有限公司 With pressurization pressure adjustment, order allocation method and device, electronic equipment and medium
CN109658034A (en) * 2018-12-28 2019-04-19 拉扎斯网络科技（上海）有限公司 Dispense range generation method, dispatching pressure regulating method, device and server
CN112016863A (en) * 2019-05-29 2020-12-01 拉扎斯网络科技（上海）有限公司 Method and device for determining distribution range, readable storage medium and electronic equipment
CN111539591A (en) * 2019-09-23 2020-08-14 拉扎斯网络科技（上海）有限公司 Data processing method and device, readable storage medium and electronic equipment

Also Published As

Publication number Publication date
CN113553500B (en) 2023-01-17

Similar Documents

Publication Publication Date Title
CN109558989B (en) Queuing time prediction method, queuing time prediction device, queuing time prediction equipment and computer readable storage medium
CN108833458B (en) Application recommendation method, device, medium and equipment
CN110505165B (en) Method and device for unloading edge calculation tasks based on bidirectional auction mechanism
EP3446469B1 (en) Method of user behavior based service dispatch
CN110582064B (en) Short message distribution method, device, equipment and medium
CN112950119B (en) Method, device, equipment and storage medium for splitting instant logistics order
US20200134361A1 (en) Data processing method and apparatus
CN112506619B (en) Job processing method, job processing device, electronic equipment and storage medium
CN113923529A (en) Live broadcast wheat connecting method, device, equipment and storage medium
CN111080126B (en) Task allocation method and device
CN114501351A (en) Flow control method, flow control equipment and storage medium
CN107798125B (en) Access judgment method, system, equipment and storage medium based on intimacy model
CN106850822B (en) Load balancing method, equipment and distributed system
CN113221005A (en) Customer service pushing method, server and related products
CN113553500B (en) Merchant information recommendation method and device, electronic equipment and storage medium
CN114140033B (en) Service personnel allocation method and device, electronic equipment and storage medium
CN110879752B (en) Resource allocation method and device, readable storage medium and electronic equipment
CN113760550A (en) Resource allocation method and resource allocation device
CN114493132A (en) Resource allocation method and device and electronic equipment
CN114048010A (en) Method, device, equipment and storage medium for controlling service timeout time
CN111311150B (en) Distribution task grouping method, platform, electronic equipment and storage medium
CN114549106A (en) Method and device for displaying merchant information, storage medium and electronic equipment
CN113656605A (en) Customer service distribution method and device
CN111091262A (en) Distribution resource recall method, device, server and storage medium
CN113743435A (en) Business data classification model training method and device, and business data classification method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant