CN114254206A

CN114254206A - Information recommendation strategy generation method and device, storage medium and computing equipment

Info

Publication number: CN114254206A
Application number: CN202210072864.9A
Authority: CN
Inventors: 王雪娟
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2022-01-21
Filing date: 2022-01-21
Publication date: 2022-03-29

Abstract

The invention provides an information recommendation strategy generation method and device, a storage medium and computing equipment, wherein the method comprises the following steps: acquiring online flow data of a target store within a set time period, wherein the online flow data comprises store exposure and order quantity; searching a target store type matched with a target store from a plurality of pre-divided store types based on online traffic data; and acquiring an information recommendation rule set corresponding to the type of the target store, and generating an information recommendation strategy for online recommendation of the target store according to the information recommendation rule. According to the scheme provided by the invention, the information recommendation of the online upper platform of the target store is realized by combining the store exposure and the order quantity of the online upper platform of the target store, so that the exposure and the transaction quantity of the online upper platform of the target store are effectively improved, and the recommendation efficiency of the store and articles in the store is improved.

Description

Information recommendation strategy generation method and device, storage medium and computing equipment

Technical Field

The invention relates to the technical field of intelligent catering, in particular to an information recommendation strategy generation method and device, a storage medium and computing equipment.

Background

Nowadays, with the acceleration of life rhythm, more and more users select an online trading platform to trade commodities, and particularly for a take-out platform, due to the requirements of the users, a large number of offline stores can simultaneously provide food selection services online. However, because the online platform stores and the types of articles are more, the online platform stores cannot realize online effective recommendation according to the characteristics of the online platform stores and the online platform stores, so that the exposure of the stores is low, and the order quantity of the stores is influenced finally.

Disclosure of Invention

In view of the above problems, the present invention has been made to provide an information recommendation policy generation method and apparatus, a storage medium, and a computing device that overcome or at least partially solve the above problems.

According to a first aspect of the embodiments of the present invention, there is provided an information recommendation policy generation method, including:

acquiring online flow data of a target store within a set time period, wherein the online flow data comprises store exposure and order quantity;

searching a target store type matched with the target store in a plurality of pre-divided store types based on the online traffic data;

and acquiring an information recommendation rule correspondingly set by the type of the target store, and generating an information recommendation strategy for online recommendation of the target store according to the information recommendation rule.

In another embodiment, the searching for the target store type matching the target store from among the pre-divided store types based on the online traffic data includes:

searching a target store coordinate point corresponding to the target store in a pre-established store coordinate system based on the online flow data;

and judging a target quadrant of the target store in the store coordinate system by using the store coordinate points, and taking the store type corresponding to the target quadrant as a target store type matched with the target store.

In another embodiment, before the online traffic data finds a target store coordinate point corresponding to the target store in a pre-established store coordinate system, the method further includes:

establishing a shop coordinate system by taking the conversion rate as an abscissa axis and the exposure amount as an ordinate axis, wherein the conversion rate is the ratio of the order quantity to the exposure amount;

counting online stores located in a set area range, and acquiring historical online flow data corresponding to each online store;

and setting the coordinate origin of the coordinate system of the store by integrating historical online flow data corresponding to each online store.

In another embodiment, the setting the origin of coordinates of the portal coordinate system by integrating historical online traffic data corresponding to each online portal includes:

taking the positive direction of the abscissa axis in the store coordinate system as the increasing direction of the conversion rate, and taking the positive direction of the ordinate axis as the increasing direction of the exposure;

determining a reference exposure and a reference conversion rate according to historical online flow data corresponding to each online store;

setting a coordinate origin of the portal coordinate system based on the reference exposure and the reference conversion rate.

In another embodiment, after setting the origin of coordinates of the coordinate system of the stores by integrating the historical online traffic data corresponding to each store, the method further includes:

setting store types corresponding to quadrants in the store coordinate system;

and setting an information recommendation rule corresponding to each store type according to the store flow characteristics corresponding to each store type.

In another embodiment, the setting of the information recommendation rule corresponding to each store type according to the store traffic characteristics corresponding to each store type includes:

analyzing store flow characteristics corresponding to the store types;

customizing at least one of a commodity structure rule, a store promotion rule and a single commodity promotion rule in a store according to the store flow characteristics; the store promotion rule or the single commodity promotion rule comprises promotion modes of at least one of promotion time periods and search promotion, platform homepage promotion, classified page promotion, fixed exhibition promotion, card coupon promotion and bidding promotion.

In another embodiment, the generating an information recommendation policy for online recommendation of the target store according to the information recommendation rule includes:

acquiring store recommendation information corresponding to the target store;

and acquiring an information recommendation rule correspondingly set according to the type of the target store, and generating an information recommendation strategy for performing online recommendation on the target store by using the information recommendation rule and combining the store recommendation information.

According to a second aspect of the present invention, there is provided an information recommendation policy generation apparatus, the apparatus including:

the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring online flow data of a target store in a set time period, and the online flow data comprises store exposure and order quantity;

the type matching module is used for searching a target store type matched with the target store in a plurality of pre-divided store types based on the online flow data;

and the strategy generation module is used for acquiring an information recommendation rule set corresponding to the type of the target store and generating an information recommendation strategy for online recommendation of the target store according to the information recommendation rule.

In another embodiment, the type matching module is further configured to:

In another embodiment, the apparatus further comprises a coordinate system establishing module;

the coordinate system establishing module is used for establishing a shop coordinate system by taking the conversion rate as an abscissa axis and the exposure amount as an ordinate axis, wherein the conversion rate is the ratio of the order quantity to the exposure amount;

In another embodiment, the coordinate system establishing module is further configured to:

In another embodiment, the coordinate system creation module is further configured to:

setting store types corresponding to quadrants in the store coordinate system;

analyzing store flow characteristics corresponding to the store types;

In another embodiment, the policy generation module is further configured to:

acquiring store recommendation information corresponding to the target store;

According to a third aspect of embodiments of the present invention, there is provided a computer-readable storage medium for storing a program code for executing the information recommendation policy generation method according to any one of the first aspect.

According to a fourth aspect of embodiments of the present invention, there is provided a computing device comprising a processor and a memory:

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to execute the information recommendation policy generation method according to any one of the first aspect according to instructions in the program code.

The method provided by the embodiment of the invention determines the type of a target store matched with the target store by combining the store exposure and the order quantity of the online upper platform of the target store, and further generates a corresponding information recommendation strategy by using an information recommendation rule preset for the type of the corresponding store, so that the information recommendation of the online upper platform of the target store is realized, the exposure and the transaction quantity of the online upper platform of the target store are effectively assisted, and the recommendation efficiency of the store and the articles in the store is improved.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart of an information recommendation policy generation method according to an embodiment of the invention;

FIG. 2 is a flow chart of an information recommendation policy generation method according to another embodiment of the present invention;

FIG. 3 illustrates a store type division diagram according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an information recommendation policy generation apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of an information recommendation policy generation apparatus according to another embodiment of the present invention;

FIG. 6 illustrates a schematic diagram of a computing device architecture, according to an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

The embodiment of the invention provides an information recommendation strategy generation method which can be applied to an online article trading platform, such as a take-out platform. As can be seen from fig. 1, the information recommendation policy generation method provided in the embodiment of the present invention at least includes the following steps S101 to S103.

S101, acquiring online flow data of a target store in a set time period, wherein the online flow data comprises the exposure and order quantity of the store.

The target store may be any store having an online platform corresponding to the online store, and the target store may be any store that provides food on the takeaway platform, for example, the takeaway platform. For the target store, online traffic data of the target store within a set time period may be obtained. In this embodiment, the set time period may be the previous day, the previous week or another time period, which is not limited in the embodiment of the present invention. The online flow data may include store exposure and order volume. The store exposure amount can be the exposure times of the target store on an online platform in the set time period, and the exposure amount is the sum of the exposure amounts of the online platform under various types of exposure pages; the order quantity is the number of orders received within a set time period by the entrance to the target store. For example, if the target store is store a on the takeaway platform, the corresponding online traffic data may include the exposure of store a in one day and the order quantity of store a in the same day, and the takeaway platform may expose the top page and the classified exposure page, so the exposure in this embodiment may be the sum of the exposure of the top page and the exposure of the classified page. In practical application, in order to make the data more accurate, the exposure (including the exposure of the first page and the exposure of the classified page) and the order amount within a certain time period may be obtained first, and the average exposure and the average order amount per day are further calculated as the on-line flow data corresponding to the target store.

S102, searching a target store type matched with the target store from a plurality of pre-divided store types based on the online traffic data.

After the online traffic data corresponding to the target store is acquired, the type of the target store corresponding to the target store can be further determined by using the online traffic data. Before that, a plurality of store types may be pre-divided, so as to select a target store type matching the target store from the plurality of store types according to the online traffic data of the target store.

In the embodiment of the present invention, four store types may be divided in advance, and may be respectively represented as a first attack type store, a second defense type store, a third test type store, and a fourth potential type store, and the four store types are also divided according to the exposure and the conversion rate of the stores, so that a target store type matching the target store type may be selected from the four stores by using the online flow data of the target store.

S103, obtaining an information recommendation rule set corresponding to the type of the target store, and generating an information recommendation strategy for online recommendation of the target store according to the information recommendation rule.

In this embodiment, for each store type mentioned in step S102, a corresponding information recommendation policy may be preset, and after the target store type corresponding to the target store is determined, an information recommendation rule corresponding to the target store type may be obtained, and then an information recommendation policy corresponding to the target store is generated by using the information recommendation rule, where the information recommendation policy may be used to recommend the target store on line, for example, a takeout platform recommends a certain store that can provide takeout service or recommends a meal sold by the store on line.

The embodiment of the invention provides an information recommendation strategy generation method, which is characterized in that a target store type matched with a target store is determined by combining the store exposure and the order quantity of the target store online upper platform, and then a corresponding information recommendation strategy is generated by using an information recommendation rule preset for the corresponding store type, so that the information recommendation of the target store online upper platform is realized, the target store is effectively assisted to improve the exposure and the transaction quantity of the online upper platform, and the recommendation efficiency of the stores and articles in the stores is improved.

Fig. 2 is a schematic flow chart of an information recommendation policy generation method according to another embodiment of the present invention, and as can be seen from fig. 2, the information recommendation policy generation method provided in the alternative embodiment of the present invention at least may include the following steps S201 to S206.

S201, acquiring the store exposure and the store order quantity of a target store in a set time period as the online flow data of the target store.

In the heavy embodiment, any one of the stores of the food is provided on the target store takeout platform, the takeout platform has a first page and a classification page, and the two store display pages are divided into two store display pages, and optionally, the daily average exposure and the average order quantity of the target store a within 30 days are obtained, wherein the average exposure is the sum of the first page average exposure and the classification page average exposure. In this embodiment, the set period is taken as one day, and a week or other time period may be set as the set time period in practical application.

After the store exposure amount and the order amount of the target store in the set period are acquired, the following steps S202 to S203 can be performed to find a target store type matching the target store from among a plurality of store types divided in advance based on the store exposure amount and the order amount.

S202, searching a target store coordinate point corresponding to the target store in a pre-established store coordinate system based on the store exposure and the store order quantity.

The store coordinate system in this embodiment is a coordinate system for classifying stores on the online platform, and specifically, referring to fig. 3, the store coordinate system is a planar coordinate system, in which the abscissa represents the conversion rate and the ordinate represents the exposure amount. Since the store exposure amount and the order amount of the target store have been acquired in step S201 described above, the target store coordinate point corresponding to the target store is searched in the store coordinate system shown in fig. 3.

Before searching for the target store coordinate point corresponding to the target store in step S202, a store coordinate system needs to be established, which may specifically include the following steps a1 to A3.

A1, establishing a shop coordinate system, namely the coordinate system shown in FIG. 3, with the conversion rate as the abscissa axis and the exposure amount as the ordinate axis. Wherein, the conversion rate is the ratio of the order quantity and the exposure quantity. For example, if the exposure of the store in the cycle is a and the order amount is b, the corresponding conversion rate is b/a.

A2, counting the online stores located in the set area range, and acquiring historical online flow data corresponding to each online store, wherein the historical online flow data can also include exposure and order quantity.

The set area range may be divided by the area range where the off-line geographical position corresponding to each on-line store is located, or may be divided by the distribution range of each on-line store. The historical online flow data may also include the average daily exposure and the average daily order amount within a set time period, which may be one month, 30 days, or other time periods.

And A3, setting the coordinate origin of the coordinate system of the store by integrating the historical online flow data corresponding to each online store.

Specifically, firstly, the positive direction of the abscissa axis in the store coordinate system is taken as the increasing direction of the conversion rate, and the positive direction of the ordinate axis is taken as the increasing direction of the exposure; secondly, determining reference exposure and reference conversion rate according to historical online flow data corresponding to online stores; finally, the origin of coordinates of the coordinate system of the store is set based on the reference exposure and the reference conversion rate.

Stores of different grid categories may have corresponding store coordinate systems, for example, stores under the Chinese food category of the takeaway platform may have corresponding store coordinate systems, and hot pot categories may have corresponding store coordinate systems. In determining the reference exposure and the reference conversion, data of stores belonging to the same grid category may be determined.

For example, the exposures of the respective stores may be ranked in order from high to low, and the exposure at the 20 th place, for example, may be designated as a reference exposure. In addition, the ratio of the order quantity and the exposure quantity of each store is firstly calculated to be used as the conversion rate, then the average conversion rate is calculated by combining the conversion rates of all stores to be used as the reference conversion rate, and the coordinate point of the reference exposure quantity and the reference conversion rate in the coordinate system is used as the origin coordinate. When the origin of the store coordinate system is determined, the origin of the coordinate system may be determined from the flow data corresponding to the store with the first order quantity ranking in the grid category. For example, the conversion rate corresponding to the store ranked first is calculated, and the conversion rate is used as the reference conversion rate.

Further, after the step a3 sets the origin of coordinates of the store coordinate system by integrating the historical online traffic data corresponding to each online store, the method may further include:

a4, setting store types corresponding to the quadrants in the store coordinate system.

Referring to fig. 3, the present embodiment may set corresponding store types for four quadrants in the store coordinate system. The first store type of the first quadrant is set as an attack type, the second store type of the second quadrant is set as a defense type, the third store type of the third quadrant is set as a test type, and the fourth store type of the fourth quadrant is set as a potential type.

And A5, setting information recommendation rules corresponding to the store types according to the store traffic characteristics corresponding to the store types. Optionally, store traffic characteristics corresponding to each store type may be analyzed first; and at least one of a commodity structure rule, a store promotion rule and a single commodity promotion rule in a store is customized according to the store flow characteristics. Store traffic characteristics may include the level of store exposure and/or the level of conversion. The commodity configuration rules may include commodity type, commodity price, and the like. The store promotion rule is directed at the promotion of a store, and the single commodity promotion rule is directed at the promotion of any commodity in the store.

Regardless of the store promotion rule or the single commodity promotion rule, the corresponding promotion rule can include at least one promotion mode of promotion time period and search promotion, platform homepage promotion, classified page promotion, fixed exhibition booth promotion, card coupon promotion and bidding promotion. The promotion time periods may be different time periods within a day, such as breakfast time periods, lunch time periods, afternoon tea time periods, and the like. The search promotion refers to promotion of a user on a search page when the user searches for a keyword on a platform. The classified page popularization is realized under different store classifications (such as western food, Chinese food, hot pot and the like). The fixed exhibition position popularization refers to the popularization of the APP or the small program corresponding to the online platform in the background position of the homepage or other fixed recommendation positions. The promotion of the card ticket can comprise the promotion of the way of distributing the coupon and the membership card, etc.

Specifically, if the exposure is low and the conversion rate is high, the bidding promotion release budget or the bidding price is appropriately reduced, and the promotion modes of searching promotion, platform homepage promotion and coupon increase are mainly adopted. If the exposure is high and the conversion rate is low, the promotion modes of platform homepage promotion, search page promotion and classification page promotion are preferentially adopted by reducing bidding promotion basic bids. If the exposure is low and the conversion rate is low, a bidding popularization mode can be adopted firstly, and the commodity structure is optimized. When the information recommendation rule is customized, the promotion time can be customized, and different promotion mode combinations are customized for different stores and different commodities in the stores.

For example, the exposure and conversion rate of an aggressive store in the first quadrant are relatively high, and the corresponding information recommendation rules may include reducing the bid promotion budget, adding an exclusive class, and displaying a class advertisement to maintain a high exposure. For example, commodity price rules and store promotion rules can be set, wherein the commodity price rules can specifically include issuing quota quantitative coupons, and the store promotion rules can include promoting stores and commodities at fixed exhibition positions, and the like. Store promotion rules can also include bid promotions, such as setting bid policies and period policies corresponding to bid promotions. The bidding strategy can comprise three types of numerical values of basic bidding, classification page and search page directional pricing and store budget. For example, the base bid is 0.8 yuan, the promotion budget is 50 yuan; the time interval strategy is set according to the characteristics of the store commodities, for example, the time interval strategy corresponding to the Chinese meal store can be a lunch time interval and a dinner time interval, and the time interval strategy of the dessert store can comprise a afternoon time interval and an morning time interval.

And the defensive type stores positioned in the second quadrant can analyze the reason of low conversion rate of each store in a targeted manner due to low conversion rate, so that the recommendation strategy is customized in a personalized manner. For example, by lowering the bidding promotion base bid and making directional bid for the classification page and the search page, the bidding strategy can include: basic bidding is 0.8 yuan, classification pages and search pages, directional pricing is 0.3-0.5 yuan, and store budget is 50 yuan; the time interval strategy is set according to the commodity characteristics of the store, if the time interval strategy corresponding to the Chinese food store can be a lunch time interval and a dinner time interval, the time interval strategy of the dessert store can comprise a afternoon time interval, an morning time interval and the like, so that the accurate flow is obtained, the conversion rate is improved, and the putting efficiency is improved.

The system is characterized in that a testability store in a third quadrant is provided, the flow rate is too low, the conversion is too low, the elbow is mutually blocked, a small amount of advertisements are introduced to test the efficiency of the store, the conversion rate or the exposure amount can be improved in a targeted manner, the promotion rules of the store and/or commodities can be specifically customized, various promotion modes are selected, and the like, and the bidding strategy can refer to a defense type store in a second quadrant. For example, store efficiency can be tested first by bid promotion and delivery, and whether the branch is to the second quadrant or the fourth quadrant; if shunting is carried out, a corresponding quadrant strategy is applied; if not, the store needs to optimize the infrastructure (such as improving the promotion strength, reducing the distribution cost, improving the LOGO style of the store, enriching the dishes and the like).

A potential store in the fourth quadrant may increase sales by increasing exposure and the promotion rules may prefer to select bid promotions. When the bidding is popularized, the popularization budget and the basic bid can be properly promoted, for example, the basic bid is 1.2 yuan, the popularization budget is 60 yuan, and the time period strategy is all day.

The method provided by the embodiment of the invention realizes the division of stores by utilizing the exposure and the conversion rate, and particularly, four quadrants are formed according to the exposure and the conversion rate. Wherein, the exposure is high, and the conversion rate is high and is a first quadrant; the exposure is high, and the conversion rate is low in a second quadrant; the exposure is low, and the conversion rate is low in the third quadrant; the exposure is low, and the conversion rate is high in the fourth quadrant. According to the embodiment, the stores are divided into four quadrants, the information recommendation rules are set for each quadrant in a targeted manner, the personalized setting of the recommendation rules of different types of stores can be realized, and the information recommendation efficiency is further improved.

And S203, judging a target quadrant of the target store in the store coordinate system by using the store coordinate points, and taking the store type corresponding to the target quadrant as the target store type matched with the target store.

According to the exposure of the store corresponding to the target store and the conversion rate of the store, the corresponding store coordinate point can be determined in the store coordinate system, and meanwhile, the quadrant of the store coordinate point in the store coordinate system is identified, and then the type of the target store is determined. In combination with the above description, if the target coordinate point is in the second quadrant, the type of the target store corresponding to the target store is a defensive type store, and if the target coordinate point is in the fourth quadrant, the type of the target store corresponding to the target store is a potential type store.

And S204, acquiring store recommendation information corresponding to the target store.

The store recommendation information of the target store may include advertisement background materials and LOGO corresponding to the target store, or information required for recommendation, such as pictures and text descriptions of goods to be recommended by the store, and may further include a promotion budget required for information recommendation, that is, a budget range of the target store for promotion on a certain day.

S205, acquiring an information recommendation rule set corresponding to the type of the target store.

And S206, generating an information recommendation strategy for online recommendation of the target store by combining the store recommendation information and the information recommendation rule corresponding to the type of the target store.

As described above, different recommendation rules are set for different store types, so that after store recommendation information of a target store is acquired, an information recommendation policy of the target store can be generated by using the information recommendation rules. For example, when bidding promotion is performed for an store, the specific promotion time and promotion manner also need to include parameters required by basic bidding, targeted pricing, and the like. After the information recommendation strategy of the target store is generated, the information recommendation strategy can be carried out in real time through the online platform, so that the target store or commodities contained in the target store can be preferentially recommended.

According to the method provided by the embodiment of the invention, four quadrants are formed in advance according to exposure amount and conversion rate, and no corresponding information recommendation rule is set in each quadrant, after the target store type matched with the target store is determined by combining the store exposure amount and the order amount of the target store online upper platform, the corresponding information recommendation strategy is generated by using the information recommendation rule preset by the target store type, so that the information recommendation of the target store online upper platform is realized, the exposure amount and the transaction amount of the target store online upper platform are effectively assisted to be increased, and the recommendation efficiency of the stores and the articles in the stores is improved.

Based on the same inventive concept, an information recommendation policy generation apparatus is further provided in the embodiments of the present invention, as shown in fig. 4, the information recommendation policy generation apparatus provided in the embodiments of the present invention may include a data acquisition module 410, a type matching module 420, and a policy generation module 430.

The data acquisition module 410 is used for acquiring online flow data of a target store in a set time period, wherein the online flow data comprises store exposure and order quantity;

the type matching module 420 is used for searching a target store type matched with the target store from a plurality of pre-divided store types based on the online traffic data;

the policy generating module 430 is configured to obtain an information recommendation rule set corresponding to the type of the target store, and generate an information recommendation policy for online recommendation of the target store according to the information recommendation rule.

In an optional embodiment of the present invention, the type matching module 420 may further be configured to:

searching a target store coordinate point corresponding to a target store in a pre-established store coordinate system based on the online flow data;

and judging a target quadrant of the target store in the store coordinate system by using the store coordinate points, and taking the store type corresponding to the target quadrant as the target store type matched with the target store.

In an optional embodiment of the present invention, as shown in fig. 5, the information recommendation policy generating module further includes a coordinate system establishing module 440;

the coordinate system establishing module 440 is used for establishing a shop coordinate system by taking the conversion rate as an abscissa axis and the exposure amount as an ordinate axis, wherein the conversion rate is the product of the shop click rate and the shop conversion rate; counting online stores located in a set area range, and acquiring historical online flow data corresponding to each online store; and setting the coordinate origin of the coordinate system of the store by integrating the historical online flow data corresponding to each online store.

In an optional embodiment of the present invention, the coordinate system establishing module 440 may further be configured to: taking the positive direction of the abscissa axis in the shop coordinate system as the increasing direction of the conversion rate, and taking the positive direction of the ordinate axis as the increasing direction of the exposure; determining a reference exposure and a reference conversion rate according to historical online flow data corresponding to each online store; the origin of coordinates of the coordinate system of the store is set based on the reference exposure and the reference conversion rate.

In an optional embodiment of the present invention, the coordinate system creating module 440 may further be configured to: setting store types corresponding to quadrants in a store coordinate system; and setting an information recommendation rule corresponding to each store type according to the store flow characteristics corresponding to each store type.

In an optional embodiment of the present invention, the coordinate system creating module 440 may further be configured to: analyzing store flow characteristics corresponding to each store type; customizing at least one of a commodity structure rule, a store promotion rule and a single commodity promotion rule in a store according to the store flow characteristics; the store promotion rule or the single commodity promotion rule comprises promotion modes of at least one of promotion time period and search promotion, platform homepage promotion, classified page promotion, fixed exhibition promotion, card coupon promotion and bidding promotion.

In an optional embodiment of the present invention, the policy generation module 430 may further be configured to: acquiring store recommendation information corresponding to a target store; and acquiring an information recommendation rule correspondingly set according to the type of the target store, and generating an information recommendation strategy for online recommendation of the target store by using the information recommendation rule in combination with store recommendation information.

It is clear to those skilled in the art that the specific working processes of the above-described systems, devices, modules and units may refer to the corresponding processes in the foregoing method embodiments, and for the sake of brevity, further description is omitted here.

The embodiment of the invention also provides a computer-readable storage medium, which is used for storing a program code, and the program code is used for executing the information recommendation strategy generation method described in the embodiment.

An embodiment of the present invention further provides a computing device, where the computing device includes a processor and a memory:

the processor is configured to execute the information recommendation policy generation method according to the above embodiment according to the instructions in the program code.

In an exemplary embodiment, referring to fig. 6, an embodiment of the present invention further provides a computing device, where the computing device includes a communication bus, a processor, a memory, and a communication interface, and may further include an input/output interface and a display device, where the functional units may complete communication with each other through the bus. The memory stores computer programs, and the processor is used for executing the programs stored in the memory and executing the steps of the information recommendation strategy generation method in the embodiment.

In addition, the functional units in the embodiments of the present invention may be physically independent of each other, two or more functional units may be integrated together, or all the functional units may be integrated in one processing unit. The integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

Those of ordinary skill in the art will understand that: the integrated functional units, if implemented in software and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computing device (e.g., a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention when the instructions are executed. And the aforementioned storage medium includes: u disk, removable hard disk, Read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disk, and other various media capable of storing program code.

Alternatively, all or part of the steps of implementing the foregoing method embodiments may be implemented by hardware (such as a computing device, e.g., a personal computer, a server, or a network device) associated with program instructions, which may be stored in a computer-readable storage medium, and when the program instructions are executed by a processor of the computing device, the computing device executes all or part of the steps of the method according to the embodiments of the present invention.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can be modified or some or all of the technical features can be equivalently replaced within the spirit and principle of the present invention; such modifications or substitutions do not depart from the scope of the present invention.

Claims

1. An information recommendation strategy generation method is characterized by comprising the following steps:

2. The method of claim 1, wherein finding the target store type that the target store matches among a plurality of pre-partitioned store types based on the online traffic data comprises:

3. The method of claim 2, wherein prior to the online traffic data finding a target store coordinate point corresponding to the target store in a pre-established store coordinate system, the method further comprises:

4. The method of claim 3, wherein the setting the origin of coordinates of the store coordinate system by integrating historical online traffic data corresponding to each online store comprises:

5. The method of claim 3, wherein the setting of the origin of coordinates of the coordinate system of the stores by integrating the historical online traffic data corresponding to each store further comprises:

setting store types corresponding to quadrants in the store coordinate system;

6. The method according to claim 5, wherein the setting of the information recommendation rule corresponding to each store type according to the store traffic characteristics corresponding to each store type comprises:

analyzing store flow characteristics corresponding to the store types;

7. The method according to any one of claims 1-6, wherein the generating an information recommendation policy for online recommendation to the target store in accordance with the information recommendation rule comprises:

acquiring store recommendation information corresponding to the target store;

8. An information recommendation policy generation apparatus, characterized in that the apparatus comprises:

9. A computer-readable storage medium characterized in that the computer-readable storage medium stores a program code for executing the information recommendation policy generation method of any one of claims 1 to 7.

10. A computing device, the computing device comprising a processor and a memory:

the processor is configured to execute the information recommendation policy generation method of any one of claims 1-7 according to instructions in the program code.