CN107730313B

CN107730313B - Shop recommendation method and device based on recommendation reason

Info

Publication number: CN107730313B
Application number: CN201710919510.2A
Authority: CN
Inventors: 刘逸哲; 吴振元; 林建国; 沈丹
Original assignee: Koubei Shanghai Information Technology Co Ltd
Current assignee: Koubei Shanghai Information Technology Co Ltd
Priority date: 2017-09-30
Filing date: 2017-09-30
Publication date: 2020-11-03
Anticipated expiration: 2037-09-30
Also published as: CN112150212A; CN107730313A

Abstract

The invention discloses a store recommendation method and device based on recommendation reasons. The method comprises the following steps: receiving a shop recommendation request carrying a user identifier sent by a client; obtaining the information of a shop list to be displayed according to the shop recommendation request; acquiring user interest tag information corresponding to at least one user interest dimension according to the user identification; aiming at each shop to be displayed, searching at least one recommendation reason matched with each user interest dimension according to user interest label information corresponding to at least one user interest dimension; according to the method, the system and the device for recommending the shops to be displayed, one recommendation reason is selected from at least one recommendation reason and the information of the shop list to be displayed is combined and pushed to the client, so that the client can display the recommendation reason and the shop information to the user, different recommendation reasons for recommending the shops to the user can be achieved for different users, personalized push recommendation reasons are achieved, the recommendation reasons are diverse and rich, and the service providing difference is guaranteed by combining the interests of the user.

Description

Shop recommendation method and device based on recommendation reason

Technical Field

The invention relates to the technical field of information processing, in particular to a shop recommendation method and device based on recommendation reasons.

Background

With the development of the information-oriented society, people are more and more accustomed to using a network to search or select a consuming store, and generally show some recommendation reasons to users together with the store, but in the prior art, the shop signboard is generally used as the recommendation reason, for example, "the store is sauerkraut, or store activity and coupon information is used as the recommendation reason, or some fixed recommendation reasons are manually edited for use in the showing process.

The reason for this recommendation is, to a certain extent, some reference suggestions are provided for the selection of the user, and the user experience is improved to a certain extent, but the disadvantages are that the reason is uniform, the reason is lack of variation, the aesthetic fatigue of the user is easy to cause, and most of the recommendation reasons are not necessarily the interest points of the user, for example, some users only care about the taste, and the recommendation reason is "parking convenience near the shop", which is not meaningful at all, and for different users, the provided recommendation reasons are the same, and the difference of the recommendation reasons cannot be realized.

Disclosure of Invention

In view of the above, the present invention has been made to provide a recommendation-reason-based store recommendation method and a corresponding recommendation-reason-based store recommendation apparatus that overcome or at least partially solve the above problems.

According to an aspect of the present invention, there is provided a store recommendation method based on a recommendation reason, including:

receiving a shop recommendation request carrying a user identifier sent by a client;

obtaining the information of a shop list to be displayed according to the shop recommendation request;

acquiring user interest tag information corresponding to at least one user interest dimension according to the user identification;

aiming at each shop to be displayed, searching at least one recommendation reason matched with each user interest dimension according to the user interest label information corresponding to the at least one user interest dimension;

and aiming at each store to be shown, selecting one recommendation reason from at least one recommendation reason and pushing the combination of the recommendation reason and the store list information to be shown to the client so that the client can show the recommendation reason and the store information to the user.

Optionally, the selecting, for each store to be presented, one reason for recommendation from the at least one reason for recommendation, and pushing the selected reason for recommendation to the client in combination with the list information of the stores to be presented further includes:

sequencing the at least one recommendation reason according to the user interest dimension priority aiming at each shop to be shown;

and selecting a recommendation reason from at least one recommendation reason according to the sorting result of the recommendation reasons, and pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner.

Optionally, before the selected recommendation reason is pushed to the client in combination with the information of the store list to be shown, the method further comprises:

sorting the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason;

the step of pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner further comprises the following steps:

and pushing the selected recommendation reason and the sorted information of the shop list to be displayed to the client in a combined manner.

Optionally, the selecting, for each store to be shown, one reason for recommendation from the at least one reason for recommendation and pushing the selected reason for recommendation to the client in combination with the list information of the stores to be shown further includes:

determining the weight corresponding to each user interest dimension according to the user interest dimension priority;

randomly selecting a recommendation reason from at least one recommendation reason according to the probability corresponding to the weight;

and pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner.

Optionally, the at least one user interest dimension comprises: a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business turn dimension, a user comment preference dimension, and/or a scene tag dimension;

the information of the shop list to be displayed comprises the following steps: store identification and location information.

Optionally, the user historical behavior dimension includes: the user history recent browsing dimension, the user history most frequent consumption dimension, and the user history recent consumption dimension;

the priority of the user history recent browsing dimension, the user history most frequent consumption dimension and the user history most recent consumption dimension is sequentially reduced and is higher than the priority of other user interest dimensions.

Optionally, the method further comprises: and if at least one recommendation reason matched with the user historical behavior dimension is found, the shop to be displayed corresponding to the at least one recommendation reason matched with the user historical behavior dimension is placed at the top in the shop list to be displayed.

Optionally, the method further comprises: obtaining shop characteristic label information according to the shop request;

for each store to be displayed, according to the user interest tag information corresponding to the at least one user interest dimension, finding at least one recommendation reason matched with each user interest dimension further comprises:

and aiming at each store to be displayed, searching the store characteristic label information according to the user interest label information corresponding to the at least one user interest dimension to determine at least one recommendation reason matched with each user interest dimension.

Optionally, the store characteristic tag information comprises: dish recommendation words, taste recommendation words and service recommendation words.

Optionally, the receiving the store recommendation request with the user identifier sent by the client further includes:

and receiving a shop recommendation request which is sent by a client through triggering a trigger button corresponding to a preset scene and carries a user identifier.

Optionally, the obtaining of the information of the store list to be displayed according to the store recommendation request further includes:

and obtaining the information of the shop list to be displayed according to the position information in the shop recommendation request.

According to another aspect of the present invention, there is provided a store recommendation apparatus based on a recommendation reason, including:

the receiving module is suitable for receiving a shop recommendation request carrying a user identifier sent by a client;

the first obtaining module is suitable for obtaining the information of the shop list to be displayed according to the shop recommendation request;

the second acquisition module is suitable for acquiring user interest tag information corresponding to at least one user interest dimension according to the user identification;

the searching module is suitable for searching at least one recommendation reason matched with each user interest dimension according to the user interest label information corresponding to the at least one user interest dimension aiming at each shop to be displayed;

the pushing module is suitable for selecting one recommendation reason from at least one recommendation reason and pushing the combination of the recommendation reason and the store list information to be displayed to the client side aiming at each store to be displayed so that the client side can display the recommendation reason and the store information to the user.

Optionally, the pushing module further comprises:

the recommendation reason sorting unit is suitable for sorting the at least one recommendation reason according to the user interest dimension priority aiming at each shop to be displayed;

and the pushing unit is suitable for selecting a recommendation reason from at least one recommendation reason according to the sorting result of the recommendation reasons and pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner.

Optionally, the push unit is further adapted to: sorting the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason;

Optionally, the pushing module further comprises:

the weight determining unit is suitable for determining the weight corresponding to each user interest dimension according to the user interest dimension priority;

the selecting unit is suitable for randomly selecting one recommendation reason from at least one recommendation reason according to the probability corresponding to the weight;

and the pushing unit is suitable for pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner.

Optionally, the apparatus further comprises: and the top placement module is suitable for placing the shop to be displayed corresponding to the at least one recommendation reason matched with the user historical behavior dimension in the shop list to be displayed if the at least one recommendation reason matched with the user historical behavior dimension is found.

Optionally, the first obtaining module is further adapted to: obtaining shop characteristic label information according to the shop request;

the lookup module is further adapted to: and aiming at each store to be displayed, searching the store characteristic label information according to the user interest label information corresponding to the at least one user interest dimension to determine at least one recommendation reason matched with each user interest dimension.

Optionally, the receiving module is further adapted to: and receiving a shop recommendation request which is sent by a client through triggering a trigger button corresponding to a preset scene and carries a user identifier.

Optionally, the first obtaining module is further adapted to: and obtaining the information of the shop list to be displayed according to the position information in the shop recommendation request.

According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the shop recommendation method based on the recommendation reason.

According to still another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the store recommendation method based on the recommendation reason as described above.

According to the scheme provided by the invention, a shop recommendation request carrying a user identifier sent by a client is received, shop list information to be displayed is obtained according to the shop recommendation request, user interest label information corresponding to at least one user interest dimension is obtained according to the user identifier in the shop recommendation request, at least one recommendation reason matched with each user interest dimension is searched for each shop to be displayed according to the user interest label information corresponding to the at least one user interest dimension, and for each shop to be displayed, one recommendation reason is selected from the at least one recommendation reason and the shop list information to be displayed are combined and pushed to the client so that the client can display the recommendation reason and the shop information to a user. According to the scheme of the embodiment of the invention, different recommendation reasons for recommending shops to the user are realized for different users, personalized recommendation reasons for pushing are realized, the recommendation reasons are diversified and rich, the provision of different services is guaranteed by combining the user interest, and the defects of poor user experience caused by single pushed recommendation reason in the existing recommendation reason pushing method and incapability of providing the recommendation reasons in a targeted manner for different users are avoided.

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.

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 diagram illustrating a store recommendation method based on a reason for recommendation according to one embodiment of the invention;

FIG. 2 is a schematic flow diagram illustrating a store recommendation method based on a reason for recommendation according to another embodiment of the invention;

FIG. 3 is a schematic flow diagram illustrating a store recommendation method based on a reason for recommendation according to yet another embodiment of the present invention;

FIG. 4 is a schematic diagram of a store recommendation apparatus based on a recommendation reason according to an embodiment of the present invention;

FIG. 5 is a schematic diagram showing a store recommendation apparatus according to another embodiment of the present invention;

FIG. 6 is a schematic diagram showing a store recommendation apparatus according to a recommendation reason according to another embodiment of the present invention;

FIG. 7 illustrates a block diagram of a computing device, according to one embodiment of the invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may 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 disclosure to those skilled in the art.

FIG. 1 is a flow chart illustrating a store recommendation method based on a recommendation reason according to one embodiment of the invention. As shown in fig. 1, the method comprises the steps of:

and S100, receiving a shop recommendation request carrying a user identifier sent by a client.

The client according to the embodiment of the present invention may include, but is not limited to, a mobile phone, a Personal Digital Assistant (PDA), a Tablet Computer (Tablet Computer), a Personal Computer (PC), and the like.

Specifically, the user triggers a function of store recommendation based on a recommendation reason provided by an application installed on the client, that is, the user is considered to send a store recommendation request carrying user identifiers, wherein each user has a unique user identifier, and the users can be distinguished according to the user identifiers, so that the recommendation reason corresponding to the stores can be pushed to the users individually according to the user identifiers. It is to be understood that the application may be a native app (native app) installed on the client, or may also be a web page program (webApp) of a browser on the client, and this embodiment is not particularly limited thereto.

And step S101, obtaining the information of the shop list to be displayed according to the shop recommendation request.

Specifically, after receiving a shop recommendation request sent by a client, the information of the shop list to be shown can be obtained according to the shop recommendation request, wherein, the number of the shops to be shown can be preset, for example, in order to make the shop information pushed to the user more comprehensive and the user selectivity higher, the number of stores to be displayed may be set higher, such as 20 or 30, by way of example only, without any limiting effect, of course, the number of the stores to be displayed can be set according to the display screen of the client, for example, the model information of the client can be carried in the store recommendation request, the size of the display screen of the client can be determined according to the model information, so that the number of shops to be displayed is determined, as such, the number of stores to be displayed may be relatively small, but without requiring any other drag operation by the user.

Step S102, obtaining user interest label information corresponding to at least one user interest dimension according to the user identification.

The user interest dimensions embody the user interests differently from different aspects, and generally, the user interest dimensions are approximately the same for different users, however, for an individual, under the same user interest dimension, the user interest label information of the user interest dimensions may be different for different users, and the user interest label information directly embodies the user interests, so that the user interest label information corresponding to at least one user interest dimension needs to be acquired according to the user identification.

Step S103, aiming at each shop to be displayed, at least one recommendation reason matched with each user interest dimension is searched according to the user interest label information corresponding to at least one user interest dimension.

After step S102, at least one reason for recommendation matching with each user interest dimension in each store to be shown needs to be found, in order to avoid the problem of uniqueness of the reason for recommendation and the defect that the reason for recommendation cannot be provided specifically for different users, at least one reason for recommendation matching with each user interest dimension needs to be found according to the user interest tag information corresponding to at least one user interest dimension.

And step S104, selecting one recommendation reason from at least one recommendation reason and pushing the combination of the recommendation reason and the store list information to be displayed to the client, so that the client can display the recommendation reason and the store information to the user.

The recommendation reasons obtained in step S103 may be multiple, but all searched recommendation reasons do not need to be displayed to the user, so for each store to be displayed, one recommendation reason and the store list information to be displayed may be selected from at least one recommendation reason and pushed to the client in combination, so that the client displays the recommendation reason and the store information to the user, and therefore, even if the same store is recommended to different users, due to different user interest tag information, the searched recommendation reasons are different, personalized recommendation reasons are realized, and it is ensured that differentiated services are provided.

According to the method provided by the embodiment of the invention, a shop recommendation request carrying a user identifier sent by a client is received, shop list information to be displayed is obtained according to the shop recommendation request, user interest label information corresponding to at least one user interest dimension is obtained according to the user identifier in the shop recommendation request, for each shop to be displayed, at least one recommendation reason matched with each user interest dimension is searched according to the user interest label information corresponding to at least one user interest dimension, for each shop to be displayed, one recommendation reason is selected from the at least one recommendation reason and the shop list information to be displayed are combined and pushed to the client, so that the client can display the recommendation reason and the shop information to a user. Based on the scheme of the embodiment of the invention, different recommendation reasons for recommending shops to the user can be realized for different users, personalized recommendation reasons for pushing are realized, and different services are provided, so that the defects of poor user experience caused by too single recommendation reason pushed in the existing recommendation reason pushing method and incapability of providing recommendation reasons for different users in a targeted manner are avoided.

FIG. 2 is a flow chart illustrating a store recommendation method based on a recommendation reason according to another embodiment of the invention. As shown in fig. 2, the method comprises the steps of:

and step S200, receiving a shop recommendation request carrying a user identifier, which is sent by a client through triggering a trigger button corresponding to a preset scene.

The shop recommendation method based on the recommendation reason can be applied to different scenes, for example, a service of 'customizing for you', a 'eye of people' service and a 'searching' service provided by an application installed on a client side, and a user clicks a trigger button corresponding to 'customizing for you', 'eye of people' and 'searching', namely the user side can be regarded as sending a shop recommendation request carrying a user identifier.

Step S201, obtaining the information of the shop list to be displayed according to the position information in the shop recommendation request.

Specifically, the store recommendation request sent by the client may also carry current location information of the user, and store list information to be displayed is obtained according to the current location information of the user, for example, store information in a corresponding range may be obtained by using the current location information of the user as a central point and a preset distance as a radius, for example, 1 km, where the store list information to be displayed includes: the system comprises a shop identifier and position information, wherein the shop identifier can be a shop name specifically, and the position information represents the distance between the shop and the current position of a user. In order to make the store information pushed to the user more comprehensive and the user selectivity higher, a person skilled in the art can set the number of stores to be displayed according to needs, which is not specifically described herein.

Step S202, obtaining user interest label information corresponding to at least one user interest dimension according to the user identification.

Specifically, the at least one user interest dimension includes: the method comprises the steps of obtaining a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business district dimension, a user comment preference dimension and/or a scene label dimension, wherein the user historical behavior dimension represents behaviors of user historical browsing, historical purchasing and the like; the user interest category dimension represents categories of user historical preference, can be determined according to the historical consumption behaviors of the user, and can indicate the classification of the stores; the user interest business circle dimension is a description of the business circle frequently visited by the user; the user comment preference dimension reflects the store subject information concerned by the user; the scene label dimension represents the crowd and the like suitable for the shop.

The user interest dimensions embody the user interests differently from different aspects, and generally, the user interest dimensions are approximately the same for different users, however, from individual aspect, under the same user interest dimension, the user interest label information of different users and user interest dimension pairs may be different, and the user interest label information directly embodies the user interests. Therefore, user interest tag information corresponding to at least one user interest dimension needs to be acquired according to the user identification, and for the user interest category dimension, some user interest tag information may be a hot pot, and some user interest tag information may be a barbecue; for another example, for the dimension of the user interest business circle, some user interest tag information of the user may be a royal wellian business circle, and some user interest tag information of the user may be a western business circle, which is not described in any detail.

Step S203, aiming at each shop to be displayed, at least one recommendation reason matched with each user interest dimension is searched according to the user interest label information corresponding to at least one user interest dimension.

After step S202, at least one recommendation reason matching each user interest dimension in each store to be shown needs to be found, for a certain store to be shown, there may not be user interest tag information corresponding to a certain user interest dimension, for example, for a user historical behavior dimension, a user may not have browsed a store recently or consumed at the store, so that a recommendation reason matching the user interest dimension is not found, and of course, there may also be user interest tag information corresponding to multiple user interest dimensions in a certain store to be shown, so that multiple recommendation reasons can be found.

Taking the user interest dimension as the user interest business zone dimension as an example, whether each store to be shown belongs to the user interest business zone range can be judged according to the user interest business zone list, for example, taking mall A as an example, defining that shops within two kilometers of mall A belong to the business district, shops beyond two kilometers do not belong to the business district, if shop B to be displayed is within two kilometers of mall A, then it is determined that store B belongs to a business district, at least one referral matching the user interest business district dimensions is found, the reason for recommendation may be generated by the server, for example, a recommendation reason template corresponding to a user interest business dimension, such as "shops around XX you are frequent", filling in a corresponding template according to the business district information to generate a corresponding recommendation reason, for example, the recommendation reason may specifically be "a store near huanglong you go often".

According to the embodiment of the invention, the store characteristic label information can also be obtained according to the store recommendation request, and the store characteristic label information can also comprise: the dish recommendation words, the taste recommendation words and the service recommendation words can be evaluations of other users to the stores or store inherent attribute information set by store owners aiming at the stores, some better recommendation words can be directly used as corresponding recommendation reasons, for example, the evaluations of other users C to the stores B are 'super-cheap and high in cost performance', the evaluations can be directly used as recommendation reasons matched with the preference dimensions of the user comments, of course, some recommendation words can be simpler, for example, 'spicy', and for the recommendation words, the server needs to perform corresponding processing, for example, corresponding recommendation reasons are generated according to the recommendation words and corresponding recommendation reason templates. There is no specific list of at least one recommendation reason matching each user interest dimension, and table 1 shows a sample of recommendation reasons corresponding to different user interest dimensions:

table 1:

user interest dimension	Sample reason for recommendation
		User historical behavior dimension	Store you just browsed
User interest category dimension	Recommended according to your hot pot preference
		User tide label preference dimension	Recommendation for dessert control
User interest business circle dimension	You often go to a store near Dioscorea nipponica
		Scene tag dimension	Good places of lovers' appointments specially selected for you
User comment preference dimension	Super-cheap and high performance-price ratio

And step S204, sequencing at least one recommendation reason for each shop to be displayed according to the user interest dimension priority.

In the embodiment of the present invention, the priority levels of different user interest dimensions are different, for example, the priority levels of a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business circle dimension, a user comment preference dimension, and a scene tag dimension may be sequentially reduced, which is only an example, the user interest dimension corresponds to other priority levels, where the priority level of the user historical behavior dimension is the highest regardless of the change of the priority level, and the user historical behavior dimension includes: a user history recent browsing dimension, a user history most frequent consumption dimension and a user history most recent consumption dimension; the priority of the user history recent browsing dimension, the user history most frequent consumption dimension and the user history most recent consumption dimension is sequentially reduced and is higher than the priority of the other user interest dimensions.

The user interest dimension priorities indicate a certain order, so that for each store to be shown, at least one obtained recommendation reason can be ranked according to the user interest dimension priorities, namely, the recommendation reasons in the store are ranked, so that a more appropriate recommendation reason can be conveniently selected and pushed to the client.

And step S205, selecting a reason for recommendation from at least one reason for recommendation according to the sorting result of the reason for recommendation.

After the at least one recommendation reason is ranked according to the user interest dimension priority, a ranking result of the recommendation reasons is obtained, and then the recommendation reason is selected from the at least one recommendation reason according to the ranking result of the recommendation reasons, for example, the first recommendation reason is selected.

And S206, sequencing the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason.

After the recommendation reason is selected from the at least one recommendation reason according to the sorting result of the recommendation reason, the stores to be displayed may be sorted according to the user interest dimension priority corresponding to the selected recommendation reason, for example, the priorities of the user history behavior dimension, the user interest category dimension, the user tidemark preference dimension, the user interest business circle dimension, the user comment preference dimension, and the scene label dimension are set to be sequentially lowered, and after the recommendation reason is selected from the at least one recommendation reason according to the sorting result of the recommendation reason, the recommendation reason and the user interest dimension of each store to be displayed are shown in table 2:

TABLE 2

Shop mark	Reason for recommendation	User interest dimension
			Shop A	Store you just browsed	User historical behavior dimension
Shop B	Recommendation for dessert control	User tide label preference dimension
			Shop C	Good places of lovers' appointments specially selected for you	Scene tag dimension
Shop D	You often go to a store near Dioscorea nipponica	User interest business circle dimension
			Shop E	Recommended according to your hot pot preference	User interest category dimension
Shop F	Super-cheap and high performance-price ratio	User comment preference dimension

Sequencing the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason, and obtaining a sequenced store list as follows: store A, store E, store B, store D, store F, and store C.

And step S207, combining and pushing the selected recommendation reason and the sorted to-be-displayed shop list information to the client so that the client can display the recommendation reason and the shop information to the user.

After the stores to be displayed are ranked according to the user interest dimension priority corresponding to the selected recommendation reason, the selected recommendation reason and the ranked store list information to be displayed are combined and pushed to the client side, the client side displays the store list information and the recommendation reason to the user, and the user can select the corresponding consuming stores by taking the corresponding recommendation reason as a reference.

In an optional embodiment of the invention, after the reason for recommendation is selected from at least one reason for recommendation according to the sorting result of the reason for recommendation, the selected reason for recommendation and the information of the store list to be displayed are directly combined and pushed to the client, and the stores do not need to be sorted.

In an optional implementation manner of the invention, the priority of the user historical behavior dimension is specified to be highest, if at least one recommendation reason matched with the user historical behavior dimension is found, the recommendation reason corresponding to the user historical behavior dimension can be directly selected without sequencing the recommendation reasons of the shop to be shown, when the shop display is carried out, the shop to be shown corresponding to the at least one recommendation reason matched with the user historical behavior dimension can be laid in the shop list to be shown for placing, and the position sequence of other shops to be shown moves downwards by one place.

According to the method provided by the embodiment of the invention, the recommendation reasons for recommending shops to the user are different for different users by combining with the user interest tag information push recommendation reasons, personalized push recommendation reasons are realized, the pushed recommendation reasons can be ensured to be in accordance with the user interests, and the recommendation reasons are ensured to be diverse and rich, so that differentiated services are provided, the defects that the pushed recommendation reasons in the existing recommendation reason push method are too single and the recommendation reasons cannot be provided for different users in a targeted manner, so that the user experience is poor are overcome, the displayed shops are sorted according to the user interest dimension priority corresponding to the selected recommendation reasons, the shops more in accordance with the user interests are preferentially displayed, and the user can select the shops conveniently.

FIG. 3 is a flow chart illustrating a store recommendation method based on a recommendation reason according to another embodiment of the invention. As shown in fig. 3, the method comprises the steps of:

and step S300, receiving a shop recommendation request which is sent by a client through triggering a trigger button corresponding to a preset scene and carries a user identifier.

Step S301, obtaining the information of the shop list to be displayed according to the position information in the shop recommendation request.

Step S302, obtaining user interest label information corresponding to at least one user interest dimension according to the user identification.

Step S303, aiming at each shop to be displayed, at least one recommendation reason matched with each user interest dimension is searched according to the user interest label information corresponding to at least one user interest dimension.

Steps S300 to S303 in the embodiment of the present invention are similar to steps S200 to S203 in the embodiment shown in fig. 2, and are not described again here.

Step S304, determining the weight corresponding to each user interest dimension according to the user interest dimension priority.

Specifically, the different priorities of the user interest dimensions make the weights corresponding to the user interest dimensions different, the priority of the user interest dimension is high, it can be determined that the weight corresponding to the user interest dimension is high, and the priority of the user interest dimension is low, then the weight corresponding to the user interest dimension is low, so that the weight corresponding to each user interest dimension can be determined.

Step S305, aiming at each shop to be shown, randomly selecting a recommendation reason from at least one recommendation reason according to the probability corresponding to the weight.

After the weights corresponding to the user interest dimensions are determined, one recommendation reason can be randomly selected from at least one recommendation reason according to the probabilities corresponding to the weights, for example, the weights of the user historical behavior dimension, the user interest category dimension, the user tide label preference dimension, the user interest business turn dimension, the user comment preference dimension and the scene label dimension are respectively 0.4, 0.2, 0.1 and 0.1, and then the probabilities of the recommendation reasons corresponding to the user interest dimension selected from the at least one recommendation reason are respectively 0.4, 0.2, 0.1 and 0.1, so that the diversity of the recommendation reasons is ensured.

And S306, pushing the selected recommendation reason and the information of the shop list to be displayed to the client in a combined manner so that the client can display the recommendation reason and the shop information to the user.

After a recommendation reason is randomly selected from at least one recommendation reason according to the probability corresponding to the weight, the selected recommendation reason and the shop list information to be displayed are combined and pushed to the client, the shop list information and the recommendation reason are displayed to the user by the client, and the user can select the corresponding consuming shop by taking the corresponding recommendation reason as a reference.

According to the method provided by the embodiment of the invention, the recommendation reason is pushed by combining the user interest tag information, and the pushed recommendation reason is randomly selected, so that different recommendation reasons for recommending shops to the user are different for different users, personalized push recommendation reasons are realized, the pushed recommendation reasons can be ensured to be in accordance with the user interests, and the recommendation reasons are ensured to be diverse and rich, so that differentiated services are provided, and the defects that the pushed recommendation reasons in the existing recommendation reason pushing method are too single, and the recommendation reasons cannot be provided for different users in a targeted manner, so that the user experience is poor are overcome.

Fig. 4 is a schematic structural diagram of a store recommendation device based on a recommendation reason according to an embodiment of the present invention. As shown in fig. 4, the apparatus includes: the device comprises a receiving module 400, a first obtaining module 410, a second obtaining module 420, a searching module 430 and a pushing module 440.

The receiving module 400 is adapted to receive a store recommendation request carrying a user identifier sent by a client.

The first obtaining module 410 is adapted to obtain the information of the store list to be displayed according to the store recommendation request.

The second obtaining module 420 is adapted to obtain user interest tag information corresponding to at least one user interest dimension according to the user identifier.

The searching module 430 is adapted to search, for each store to be displayed, at least one recommendation reason matching each user interest dimension according to the user interest tag information corresponding to the at least one user interest dimension.

The pushing module 440 is adapted to select one recommendation reason from the at least one recommendation reason for each store to be displayed, combine the selected recommendation reason with the store list information to be displayed, and push the combination to the client, so that the client can display the recommendation reason and the store information to the user.

Optionally, the at least one user interest dimension comprises: a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business turn dimension, a user comment preference dimension, and/or a scene tag dimension; the user historical behavior dimension includes: a user history recent browsing dimension, a user history most frequent consumption dimension and a user history most recent consumption dimension; the priority of the user history recent browsing dimension, the user history most frequent consumption dimension and the user history most recent consumption dimension is sequentially reduced and is higher than the priority of the other user interest dimensions.

Optionally, the apparatus further comprises: the top module 450 is adapted to, if at least one recommendation reason matching the user historical behavior dimension is found, lay the store to be shown corresponding to the at least one recommendation reason matching the user historical behavior dimension in the store list to be shown for top placement.

According to the device provided by the embodiment of the invention, a shop recommendation request carrying a user identifier sent by a client is received, shop list information to be displayed is obtained according to the shop recommendation request, user interest label information corresponding to at least one user interest dimension is obtained according to the user identifier in the shop recommendation request, for each shop to be displayed, at least one recommendation reason matched with each user interest dimension is searched according to the user interest label information corresponding to at least one user interest dimension, for each shop to be displayed, one recommendation reason is selected from the at least one recommendation reason and the shop list information to be displayed are combined and pushed to the client, so that the client can display the recommendation reason and the shop information to a user. Based on the scheme of the embodiment of the invention, different recommendation reasons for recommending shops to the user can be realized for different users, personalized recommendation reasons for pushing are realized, and different services are provided, so that the defects of poor user experience caused by too single recommendation reason pushed in the existing recommendation reason pushing method and incapability of providing recommendation reasons for different users in a targeted manner are avoided.

Fig. 5 is a schematic structural diagram of a store recommendation apparatus based on a recommendation reason according to another embodiment of the present invention. As shown in fig. 5, the apparatus includes: the system comprises a receiving module 500, a first obtaining module 510, a second obtaining module 520, a searching module 530 and a pushing module 540.

The receiving module 500 is adapted to receive a store recommendation request carrying a user identifier, which is sent by a client by triggering a trigger button corresponding to a preset scene.

The first obtaining module 510 is adapted to obtain the information of the store list to be displayed according to the position information in the store recommendation request.

The second obtaining module 520 is adapted to obtain the user interest tag information corresponding to at least one user interest dimension according to the user identifier.

The searching module 530 is adapted to search, for each store to be displayed, at least one recommendation reason matching each user interest dimension according to the user interest tag information corresponding to the at least one user interest dimension.

In an optional embodiment of the invention, the first obtaining module is further adapted to: obtaining shop characteristic label information according to the shop request, wherein the shop characteristic label information comprises: dish recommendation words, taste recommendation words and service recommendation words.

The pushing module 540 further includes: the recommendation reason sorting unit 541 is suitable for sorting at least one recommendation reason for each store to be displayed according to the user interest dimension priority;

the pushing unit 542 is adapted to select a recommendation reason from at least one recommendation reason according to a sorting result of the recommendation reasons, and push the selected recommendation reason and the information of the store list to be displayed to the client in combination, so that the client can display the recommendation reason and the store information to the user.

Wherein the pushing unit 542 is further adapted to: sorting the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason;

According to the device provided by the embodiment of the invention, by combining with the user interest tag information push recommendation reasons, different recommendation reasons for recommending shops to the user can be realized for different users, personalized push recommendation reasons are realized, the pushed recommendation reasons can be ensured to be in accordance with the user interests, and the recommendation reasons are ensured to be diverse and rich, so that differentiated services are provided, the defects that the pushed recommendation reasons in the existing recommendation reason push method are too single and the recommendation reasons cannot be provided for different users in a targeted manner, so that the user experience is poor are overcome, the displayed shops are sorted according to the user interest dimension priority corresponding to the selected recommendation reasons, the shops in accordance with the user interests are preferentially displayed, and the user can select the shops conveniently.

Fig. 6 is a schematic structural diagram of a store recommendation apparatus based on a recommendation reason according to still another embodiment of the present invention. As shown in fig. 6, the apparatus includes: the device comprises a receiving module 600, a first obtaining module 610, a second obtaining module 620, a searching module 630 and a pushing module 640.

The receiving module 600 is adapted to receive a store recommendation request carrying a user identifier, which is sent by a client by triggering a trigger button corresponding to a preset scene.

The first obtaining module 610 is adapted to obtain the information of the store list to be displayed according to the position information in the store recommendation request.

The second obtaining module 620 is adapted to obtain user interest tag information corresponding to at least one user interest dimension according to the user identifier.

The searching module 630 is adapted to search, for each store to be displayed, at least one recommendation reason matching each user interest dimension according to the user interest tag information corresponding to the at least one user interest dimension.

The pushing module 640 further includes: the weight determining unit 641 is adapted to determine the weight corresponding to each user interest dimension according to the user interest dimension priority;

the selecting unit 642 is adapted to randomly select a recommendation reason from at least one recommendation reason according to the probability corresponding to the weight;

the pushing unit 643 is adapted to push the selected recommendation reason and the to-be-presented store list information to the client in combination, so that the client presents the recommendation reason and the store information to the user.

According to the device provided by the embodiment of the invention, the recommendation reason is pushed by combining the user interest tag information, and the pushed recommendation reason is randomly selected, so that different recommendation reasons for recommending shops to users are different for different users, personalized push recommendation reasons are realized, the pushed recommendation reasons can be ensured to be in accordance with the user interests, and the recommendation reasons are ensured to be diverse and rich, so that differentiated services are provided, and the defects that the pushed recommendation reasons in the existing recommendation reason pushing method are too single, and the recommendation reasons cannot be provided for different users in a targeted manner, so that the user experience is poor are overcome.

The embodiment of the application also provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the store recommendation method based on the recommendation reason in any method embodiment.

Fig. 7 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in fig. 7, the computing device may include: a processor (processor)702, a Communications Interface 704, a memory 706, and a communication bus 708.

Wherein:

the processor 702, communication interface 704, and memory 706 communicate with each other via a communication bus 708.

A communication interface 704 for communicating with network elements of other devices, such as clients or other servers.

The processor 702 is configured to execute the program 710, and may specifically execute the relevant steps in the foregoing store recommendation method embodiment based on the recommendation reason.

In particular, the program 710 may include program code that includes computer operating instructions.

The processor 702 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

The memory 706 stores a program 710. The memory 706 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 710 may be specifically configured to cause the processor 702 to perform the methods in the embodiments illustrated in fig. 1-3.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in a recommendation-based store recommendation device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A store recommendation method based on a recommendation reason, comprising:

acquiring user interest tag information corresponding to at least one user interest dimension according to the user identification; under the same user interest dimension, the user interest label information corresponding to the user interest dimensions of different users is different, and the user interest label information reflects the interest of the users;

2. The method of claim 1, wherein selecting one reason for recommendation from at least one reason for recommendation and pushing the selected reason for recommendation to the client in combination with the list information of the stores to be shown further comprises:

3. The method of claim 2, wherein prior to pushing the selected reason for recommendation to the client in combination with the store list to be presented information, the method further comprises:

4. The method as claimed in claim 1, wherein the selecting one recommendation reason from at least one recommendation reason for each store to be shown and pushing the selected recommendation reason to the client in combination with the store list information to be shown further comprises:

5. The method of any of claims 1-4, wherein the at least one user interest dimension comprises: a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business turn dimension, a user comment preference dimension, and/or a scene tag dimension;

6. The method of claim 5, wherein the user historical behavior dimension comprises: a user history recent browsing dimension, a user history most frequent consumption dimension and a user history most recent consumption dimension;

7. The method of claim 6, wherein the method further comprises: and if at least one recommendation reason matched with the user historical behavior dimension is found, the shop to be displayed corresponding to the at least one recommendation reason matched with the user historical behavior dimension is placed at the top in the shop list to be displayed.

8. The method of claim 1, wherein the method further comprises: obtaining shop characteristic label information according to the shop recommendation request;

9. The method of claim 8, wherein the store trait tag information comprises: dish recommendation words, taste recommendation words and service recommendation words.

10. The method according to any one of claims 1 to 4, wherein the receiving of the store recommendation request carrying the user identifier sent by the client further comprises:

11. The method according to any one of claims 1-4, wherein the obtaining of the information of the shop list to be shown according to the shop recommendation request further comprises:

12. A store recommendation apparatus based on a reason for recommendation, comprising:

the second acquisition module is suitable for acquiring user interest tag information corresponding to at least one user interest dimension according to the user identification; under the same user interest dimension, the user interest label information corresponding to the user interest dimensions of different users is different, and the user interest label information reflects the interest of the users;

13. The apparatus of claim 12, wherein the pushing module further comprises:

14. The apparatus of claim 13, wherein the pushing unit is further adapted to: sorting the stores to be displayed according to the user interest dimension priority corresponding to the selected recommendation reason;

15. The apparatus of claim 12, wherein the pushing module further comprises:

16. The apparatus of any one of claims 12-15, wherein the at least one user interest dimension comprises: a user historical behavior dimension, a user interest category dimension, a user tidemark preference dimension, a user interest business turn dimension, a user comment preference dimension, and/or a scene tag dimension;

17. The apparatus of claim 16, wherein the user historical behavior dimension comprises: a user history recent browsing dimension, a user history most frequent consumption dimension and a user history most recent consumption dimension;

18. The apparatus of claim 17, wherein the apparatus further comprises: and the top placement module is suitable for placing the shop to be displayed corresponding to the at least one recommendation reason matched with the user historical behavior dimension in the shop list to be displayed if the at least one recommendation reason matched with the user historical behavior dimension is found.

19. The apparatus of claim 12, wherein the first obtaining module is further adapted to: obtaining shop characteristic label information according to the shop recommendation request;

20. The apparatus of claim 19, wherein the store trait tag information comprises: dish recommendation words, taste recommendation words and service recommendation words.

21. The apparatus of any of claims 12-15, wherein the receiving means is further adapted to: and receiving a shop recommendation request which is sent by a client through triggering a trigger button corresponding to a preset scene and carries a user identifier.

22. The apparatus of any one of claims 12-15, wherein the first obtaining module is further adapted to: and obtaining the information of the shop list to be displayed according to the position information in the shop recommendation request.

23. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the store recommendation method based on the recommendation reason according to any one of claims 1-11.

24. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the recommendation reason based store recommendation method of any one of claims 1-11.