WO2019141072A1

WO2019141072A1 - Method, device, and client for recommending store information

Info

Publication number: WO2019141072A1
Application number: PCT/CN2018/125208
Authority: WO
Inventors: 俞文明
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-01-22
Filing date: 2018-12-29
Publication date: 2019-07-25
Also published as: TW201933232A; CN108492124A

Abstract

A method, device, and client for recommending store information. The method comprises: determining a consumer group to which a target user belongs, wherein the consumer group is determined by performing cluster analysis on the basis of a consumer feature vector used to represent consumer feature information of users (S102); acquiring store information of stores in which the users in the consumer group have been previous consumers, and identifying a piece of store information in the store information that appears at a number of times greater than or equal to a preset threshold (S104); and recommending to the target user the piece of store information that appears at the number of times greater than or equal to the preset threshold (S106).

Description

Store information recommendation method, device and client

Technical field

The embodiments of the present disclosure relate to the field of Internet communication technologies, and in particular, to a store information recommendation method, apparatus, and client.

Background technique

In recent years, with the rapid development of the Internet and the emergence of new retail, the Internet has accumulated a large number of user and store data, and the analysis and mining of these data can improve the user's store-to-store consumption rate. Therefore, the use of big data, artificial intelligence and other means to conduct online marketing recommendation activities has been valued by more and more businesses.

At present, when conducting marketing recommendation processing, it is often recommended based on the favorable rate or transaction volume of the store. For example, if a store has a high rating, the store with a high rating will be recommended to the user. Or, if the transaction volume of a certain store is high, the store with a high transaction volume is recommended to the user. However, in the above-mentioned existing recommendation methods, there are often cases in which the credit rate is increased in order to improve the favorable rate or the transaction amount, and there are different problems in different user consumption preferences, and the shop recommended to the user is not the shop that the user likes, and the recommendation effect is poor. Therefore, there is a need to provide a more reliable or more efficient solution.

Summary of the invention

The purpose of the embodiments of the present specification is to provide a method, a device, and a client for recommending store information, which can ensure that the recommended store information is more in line with the preferences of the target user, improve the response rate of the user to the recommended store information, and thereby improve the user's arrival at the store. Consumption rate.

Embodiments of the present specification are implemented as follows:

A method for recommending shop information, including:

Determining a consumption group in which the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

Obtaining the store information that the user has consumed in the consumption group, and identifying the store information that the number of occurrences of the store information in the store information is greater than or equal to a preset threshold;

The shop information whose number of occurrences is greater than or equal to a preset threshold is recommended to the target user.

A shop information recommendation device, comprising:

a consumption group determining module, configured to determine a consumption group in which the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

a group store information obtaining module, configured to acquire shop information that the user has consumed in the consumer group;

a store information identifying module, configured to identify shop information in which the number of occurrences of shop information in the store information is greater than or equal to a preset threshold;

The shop information recommendation module is configured to recommend the shop information that the number of occurrences is greater than or equal to a preset threshold to the target user.

A store information recommendation client includes a processor and a memory, the memory storing computer program instructions executed by the processor, the computer program instructions comprising:

It can be seen from the above that one or more embodiments of the present specification can perform the group division according to the consumption preference, and when the shop information recommendation is performed, after determining the consumer group where the target user is located, the user group can be directly similar to the target user. The user's consumption data in the consumption preference consumer group is recommended to the target user for the store information, which ensures that the recommended store information better meets the target user's preference, and improves the user's response probability to the recommended store information, thereby improving User to store consumption rate.

DRAWINGS

In order to more clearly illustrate one or more embodiments of the present specification or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, in the following description The drawings are merely some of the embodiments described in the specification, and those skilled in the art can obtain other drawings based on these drawings without any creative work.

1 is a schematic flow chart of an embodiment of a store information recommendation method provided by the present specification;

2 is a schematic flow chart of an embodiment of determining a consumption group by cluster analysis based on a consumption feature vector that characterizes user's consumption feature information provided by the present specification;

3 is a schematic structural diagram of an embodiment of a store information recommendation device provided by the present specification;

4 is a schematic structural diagram of a shop information recommendation client according to an exemplary embodiment of the present specification.

Detailed ways

The embodiment of the present specification provides a store information recommendation method, device and client.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the specification. The embodiments are only a part of the embodiments of the specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present specification without departing from the inventive scope should fall within the scope of the present disclosure.

A specific embodiment of a shop information recommendation method of this specification will be described below. 1 is a schematic flow chart of an embodiment of a store information recommendation method provided by the present specification. The present specification provides method operation steps as described in the embodiment or the flowchart, but the routine or non-creative work may include more or Fewer steps. The order of the steps recited in the embodiments is only one of the many steps of the order of execution, and does not represent a single order of execution. When the actual system or client product is executed, it may be executed sequentially or in parallel according to the method shown in the embodiment or the drawings (for example, a parallel processor or a multi-threaded environment). Specifically, as shown in FIG. 1, the method may include:

S102: Determine a consumption group where the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user.

In practical applications, online or offline merchants can conduct online referral marketing activities through the Internet service platform (hereinafter referred to as the service platform) to increase the user-to-store consumption rate. Specifically, the service platform of the embodiment of the present specification can recommend a store that meets the user's consumption preference to the user. In the embodiment of the present specification, the service platform may determine the consumer group in which the target user is located in the process of recommending the store to the user. Specifically, the consumer group is determined by cluster analysis based on a consumption feature vector that characterizes the user's consumption feature information.

In the embodiment of the present specification, the user on the service platform may first divide the user into a consumer group according to the consumption characteristic information of the user. In a specific embodiment, as shown in FIG. 2, FIG. 2 is a schematic flowchart of an embodiment of determining a consumption group by performing cluster analysis based on a consumption feature vector that characterizes user's consumption feature information provided in the present specification.

S1021: Acquire consumption characteristic information of a first quantity of users, where the first quantity of users includes the target user.

Specifically, the first number of users in the embodiment of the present specification may include users on the service platform. Preferably, when performing the physical store information recommendation process, it is considered that the user prefers to select a store with a relatively close distance for consumption. In the embodiment of the present specification, the user in the first preset area where the geographical location information is located in the first preset area of the business circle may be divided into corresponding groups, and correspondingly, the first quantity of users may include the geographical position on the service platform. The user is in the first preset area where the information is to be recommended. Specifically, the business circle in the embodiment of the present specification may include a consumption place including one or more physical stores.

Correspondingly, the target store may include a user on the service platform, and may also include a user in the first preset area where the geographic location information on the service platform is located at the location of the to-be-recommended business circle. In addition, in some embodiments, in order to improve the recommended conversion rate, the store information may be recommended in combination with the historical recommendation information to the user with a higher feedback rate of the recommendation information. Correspondingly, the target user may include a user whose feedback rate on the service platform is higher than or equal to a preset feedback rate. Specifically, the feedback rate of the user to the recommendation information herein may include a click rate and/or a consumption conversion rate. The preset feedback rate can be set in combination with actual application requirements.

Specifically, the first preset area of the location where the recommended business circle is located may be set according to actual application conditions, for example, may be set within 5 km from the location of the to-be-recommended business circle. Specifically, the geographic location information of the user herein may be a common fixed geographical location information of the user, such as a user's home address, a company address, and the like. Specifically, the geographical location information of the user may be obtained through user setting; in addition, it may also be obtained through a radio communication network (such as a GSM network, a CDMA network) or an external positioning method (such as GPS); and may also be transactioned from the user history. Data (such as online shopping data) is extracted by extracting address information.

Specifically, in the embodiment of the present specification, the consumption feature information may include information capable of reflecting a user's consumption preference. In practical applications, the user's consumption preferences are generally related to the user's economic base, background experience, spending power, and consumption habits. Correspondingly, the consumption feature information in the embodiment of the present specification may include at least one of the following:

Consumption basic attribute information, consumption ability information, consumption habit information.

In one embodiment, the consumption base attribute information may include economic basic information and background experience information of the user, such as housing situation information (whether there is room and housing grade), education information, and occupation information. The consumption capability information may include information capable of reflecting the user's consumption amount, for example, a user consumption level that is proportional to the user consumption amount (generally, the user consumption level is proportional to the user consumption amount). The consumption habit information may include information capable of reflecting user consumption data, such as brand information of a user purchasing an item, personal interest information, travel tool information, and the like.

S1023: Construct a consumption feature vector of the user based on the consumption feature information.

In practical applications, the consumption feature information may not be a numerical value, but a characterized representation of a certain degree or trend. In this case, the content of the characterized representation may be quantized to a specific value by a preset rule. Further, the quantized value can be used to characterize the corresponding consumption feature information. In a common example, the value of a dimension may be "medium", and the character may be quantized as a binary or hexadecimal value of its ASCII code.

In a specific embodiment, constructing the consumption feature vector of the user based on the consumption feature information may include:

1) quantizing the consumption feature information into a specific value based on a preset quantization rule corresponding to the user's consumption feature information;

2) constructing a first feature vector of the user based on the quantized specific value;

3) normalizing the first feature vector to obtain a normalized second feature vector, and using the second feature vector as the consumption feature vector.

Specifically, in the embodiment of the present specification, the preset quantization rule may be set in combination with the corresponding consumption feature information. In a specific embodiment, for example, whether the room is quantified as having a room of 1, and no room is 0. In another specific embodiment, for example, the user consumption level is quantified from high to low from 10 to 1.

Specifically, the consumption feature information that can reflect the user's consumption preference may include a plurality of different types of information, and the metrics of the specific values after the different types of consumption feature information are quantized are different. In the embodiment of the present specification, the first feature may be used. The quantized specific values in the vector are normalized. In a specific embodiment, for example, whether there is room and user consumption level as described above, the former is quantized to 0 or 1; the latter is quantized to 1 to 10. After standardization processing, whether the room and user consumption levels can be unified into Characterization is carried out using values between 0 and 1. Specifically, whether a room can be characterized by 0 or 1, the user consumption level can be characterized by 0.1 to 1.

In addition, it should be noted that each element in the second feature vector after the normalization process in the embodiment of the present specification is not limited to the value between 0 and 1 described above, and may be set to 0 to 100 in combination with actual application conditions. Other metrics.

In addition, in other embodiments, in the embodiment of the present specification, the method may further include:

Principal component analysis processing is performed on the second feature vector, and the feature vector after the principal component analysis process is used as the consumption feature vector.

Specifically, the principal component analysis processing in the embodiments of the present specification may include, but is not limited to, PCA (Principal Component Analysis). Here, the principal component analysis process can improve the representation of the consumer feature vector to the user's consumption preference, and at the same time, the dimension reduction of the consumption feature vector can be realized, and the subsequent calculation amount can be reduced.

S1025: Perform cluster analysis processing on the first number of users based on the similarity between the consumption feature vectors of the first number of users, to obtain a second number of consumption groups.

Specifically, the cluster analysis processing in the embodiment of the present disclosure may include, but is not limited to, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm or a k-means clustering algorithm.

In a specific embodiment, the DBSCAN clustering algorithm is introduced to perform cluster analysis processing on the first number of users based on the similarity between the consumption feature vectors of the first number of users, to obtain a second quantity. Specific methods for consumer groups:

In the process of cluster analysis processing, the DBSCAN clustering algorithm needs to first determine the cluster radius and the cluster minimum inclusion points. In the embodiment of the present specification, the third number of cluster radii and the cluster minimum inclusion point may be determined according to the similarity between the consumption eigenvectors of the first number of users.

In a specific embodiment, the consumption feature vector p(i) of any user of the first number of users' consumption feature vectors P={p(i); i=0,1, . . . The similarity between the user's consumption feature vectors {p(1), p(2),..., p(i-1), p(i+1),...,p(n)}; (p(i) Represents the consumption feature vector of the i-th user, and n represents the total number of users, that is, the first number). Then, according to the similarity degree, the order from the smallest to the largest D={d _i (k); k=n-1}, d _i (k) represents the consumption feature vector of the i-th user and the consumption of other users The k-th large similarity between the feature vectors; sorting the k-th largest similarity of the first number of users according to the similarity degree, from small to large; fitting a sorted according to the sorted similarity The similarity change curve determines the value of the similarity corresponding to the position where the change is sharply as the cluster radius; the minimum number of points of the cluster corresponding to the cluster radius may be set to the k value corresponding to the cluster radius.

Specifically, the similarity between the consumption feature vectors in the embodiment of the present specification may include at least one of the following:

Euclidean distance, cosine distance, Manhattan distance, Jacques coefficient.

In addition, it should be noted that the third quantity in the embodiment of the present specification is smaller than the first quantity.

Then, cluster analysis processing may be separately performed in combination with the third number of cluster radii and the cluster minimum inclusion point. Specifically, it may include:

1) selecting any unprocessed consumption feature vector from the first number of users' consumption characteristic vectors as an initial consumption feature vector, and finding that the similarity with the initial consumption feature vector is less than or equal to the current cluster radius Consumption feature vector.

2) if the number of consumption feature vectors less than or equal to the current cluster radius is greater than or equal to the current cluster minimum inclusion point number, the current consumption feature vector forms a cluster with the consumption feature vector less than or equal to the current cluster radius, and The current consumption feature vector is marked as accessed.

3) Using any of the consumer feature vectors that are not processed in the current cluster as the initial consumption feature vector, repeat steps 1) and 2) to determine the cluster, thereby expanding the cluster.

4) If the number of consumption feature vectors less than or equal to the current cluster radius is smaller than the current cluster minimum inclusion point, the point is temporarily marked as a noise point.

5) repeating the above steps to the unprocessed consumable feature vector of the first number of users' consumption characteristic vectors if all points within the current cluster are processed, ie marked as visited or noisy points The first number of users' consumption characteristic vectors are processed to obtain the grouped users.

In practical applications, if the cluster radius is too large in the cluster analysis process of the domain DBSCAN clustering algorithm, most points (ie, consumption feature vectors) will be clustered into the same cluster. A class radius that is too small will cause a cluster to split. The minimum value of the cluster containing the number of points is too large, which causes the points in the same cluster to be marked as outliers. Conversely, the minimum number of points in the cluster is too small, which leads to the discovery of a large number of core points. Therefore, in the embodiment of the present specification, the k value may be set in combination with an actual application, and at the same time, in order to ensure better grouping, multiple k values may be selected, and multiple sets of different cluster radii and cluster minimum included points are obtained, correspondingly By using multiple sets of different cluster radii and cluster minimum inclusion points, a plurality of different user groups can be obtained. According to the actual grouping effect, a user group is selected to divide the first number of users into the second number of consumer groups. group.

In a practical application, in determining a consumer group in which the target user is located, the consumer group in which the target user is located may be determined from the second number of consumption groups by using a user identifier such as a user name.

It can be seen from the technical solutions in the foregoing embodiments of the present specification that, in the embodiment of the present specification, the user is divided into the consumption group according to the consumption preference of the user, and when the store information recommendation is performed, the recommendation may be combined with the consumption group to ensure the recommendation. The store information is more in line with the target user's consumption preferences, thereby increasing the user's consumption rate.

S104: Acquire the store information that the user has consumed in the consumer group, and identify the store information that the number of occurrences of the store information in the store information is greater than or equal to a preset threshold.

In the embodiment of the present specification, the consumption preferences of users in the same consumer group are similar, and correspondingly, the store information frequently consumed by users in the same consumer group may be recommended to the target user. The store information consumed by the user in the consumption group may be acquired, and the store information in which the number of occurrences of the store information in the store information is greater than or equal to a preset threshold is identified.

In the embodiment of the present specification, the preset threshold may be set according to actual application requirements and the number of users in the consumption group, for example, set to half of the total number of users. Generally, the larger the preset threshold is, the greater the probability that the determined store information meets the target user's consumption preference.

In the embodiment of the present specification, the store information may include store basic information such as a shop name, a shop address, a store opening hours, and the like. In addition, in order to increase the user's arrival rate, the store information may further include: store offer information.

In addition, it should be noted that, in the embodiment of the present specification, the store information is not limited to the above-mentioned store basic information and store offer information, and may further include other information in an actual application, and the embodiment of the present specification is not limit.

S106: Recommend the shop information that the number of occurrences is greater than or equal to a preset threshold to the target user.

In the embodiment of the present specification, when the store information whose number of occurrences is greater than or equal to the preset threshold is recommended to the target user, the recommended time and the location information between the target user and the store may be combined to increase the user-to-store consumption rate.

In a specific embodiment, it is considered that some stores are consumed by the user for a fixed period of time, such as a restaurant. In the embodiment of the present specification, the shop information whose number of occurrences is greater than or equal to a preset threshold may be recommended to the target user in a preset consumption time corresponding to the shop information whose number of occurrences is greater than or equal to the preset threshold.

Specifically, the preset consumption time here may be set in combination with actual application conditions, and may include one or more time periods. For example, restaurant information can be recommended from 10:30 to 13:00 and 16:30 to 20:00.

In another specific embodiment, in consideration of the user generally prefers to go to a nearby store for consumption, in the embodiment of the present specification, the target user may be in the geographic location corresponding to the shop information whose number of occurrences is greater than or equal to a preset threshold. When the location information is in the second preset area, the shop information whose number of occurrences is greater than or equal to the preset threshold is recommended to the target user.

Specifically, the second preset area of the location where the geographical location information corresponding to the store information is located may be set according to the actual application, for example, may be set within 1 km from the location where the geographical location information is located.

In addition, in combination with actual application requirements, the recommended embodiments of the above two store information may be combined with each other. That is, the store information is recommended to the target user in the second preset area of the location where the geographical location information corresponding to the store information is located in the preset consumption time corresponding to the store information whose number of occurrences is greater than or equal to the preset threshold.

Further, the click rate and the conversion rate after each store information recommendation may be recorded as historical recommendation data, and it is convenient to select a recommended object of the most store information of the user who actively feeds back the recommendation information based on the historical recommendation information.

It can be seen that one or more embodiments of the store information recommendation method in the present specification can determine the consumer group according to the consumption preference, and determine the consumer group where the target user is located after performing the store information recommendation. Directly recommending the store information to the target user according to the consumption data of the user in the consumer group having similar consumption preferences with the target user, ensuring that the recommended store information better meets the preferences of the target user, and improves the user's recommended store information. The response probability, which in turn, can increase the user-to-store consumption rate.

In another aspect of the present specification, a store information recommendation device is provided. FIG. 3 is a schematic structural diagram of an embodiment of a store information recommendation device provided in the present specification. As shown in FIG. 3, the device 300 may include:

The consumption group determining module 310 may be configured to determine a consumption group in which the target user is located, where the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

The group store information obtaining module 320 may be configured to acquire store information that the user has consumed in the consumer group;

The store information identification module 330 may be configured to identify the store information in which the number of occurrences of the store information in the store information is greater than or equal to a preset threshold;

The store information recommendation module 340 can be configured to recommend the store information that the number of occurrences is greater than or equal to a preset threshold to the target user.

In another embodiment, the consumer group determined by the clustering analysis based on the consumption feature vector that characterizes the user's consumption feature information may include determining by using the following module:

The consumption feature information obtaining module may be configured to acquire consumption characteristic information of a first quantity of users, where the first quantity of users includes the target user;

a consumption feature vector construction module, configured to construct a consumption feature vector of the user based on the consumption feature information;

The row clustering analysis processing module may be configured to perform cluster analysis processing on the first number of users based on the similarity between the consumption feature vectors of the first number of users to obtain a second number of consumer groups.

In another embodiment, the consumption feature vector building module may include:

The quantizing unit may be configured to quantize the consumption feature information into a specific value based on a preset quantization rule corresponding to the user's consumption feature information;

a first feature vector construction unit, configured to construct a first feature vector of the user based on the quantized specific value;

The normalization processing unit may be configured to perform normalization processing on the first feature vector to obtain a normalized second feature vector, and use the second feature vector as the consumption feature vector.

In another embodiment, the consumption feature vector building module may further include:

The principal component analysis processing unit is configured to perform principal component analysis processing on the second feature vector, and use the feature vector after the principal component analysis process as the consumption feature vector.

In another embodiment, the apparatus 300 may further include:

The user determining module may be configured to determine, before acquiring the consumption feature information of the first quantity of users, the user in the first preset area where the geographical location information is located at the location of the to-be-recommended business circle, and the first preset area The user acts as the first number of users.

In another embodiment, the similarity may include at least one of the following:

Euclidean distance, cosine distance, Manhattan distance, Jacques coefficient.

In another embodiment, the consumption characteristic information may include at least one of the following:

In another embodiment, the store information recommendation module 340 can include:

The first store information recommendation unit may be configured to recommend the store information whose number of occurrences is greater than or equal to a preset threshold to the target user in a preset consumption time corresponding to the store information whose number of occurrences is greater than or equal to a preset threshold. .

The second store information recommendation unit may be configured to: when the target user is in the second preset area where the location information corresponding to the shop information corresponding to the preset threshold is greater than or equal to the preset threshold, the number of occurrences Store information greater than or equal to a preset threshold is recommended to the target user.

The above-mentioned shop information recommendation method or device provided by the embodiment of the present specification may be implemented by a processor executing a corresponding program instruction in a computer, such as using a C++ language of a Windows operating system on a PC side, or other programs such as using an android or iOS system. The design language is implemented in intelligent terminals, as well as processing logic based on quantum computers. As shown in FIG. 4, FIG. 4 is a schematic structural diagram of a shop information recommendation client according to an exemplary embodiment of the present specification. At the hardware level, the client can include processors, internal buses, network interfaces, memory, and non-volatile memory, and of course other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs to form a word string identification device at a logical level. Of course, in addition to the software implementation, the present application does not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc., that is, the execution body of the following processing flow is not limited to each logical unit, and may be Hardware or logic device.

An embodiment of the present specification further provides a store information recommendation client, including a processor and a memory, the memory storing computer program instructions executed by the processor, the computer program instructions may include:

In the embodiment of the present specification, the processor may include a central processing unit (CPU) or a graphics processing unit (GPU), and may of course include other single-chip microcomputers having logic processing capabilities, logic gate circuits, integrated circuits, etc., or Proper combination. The memory described in the embodiment of the present application may be a memory device for storing information. In a digital system, a device capable of storing binary data may be a memory; in an integrated circuit, a circuit having a storage function without a physical form may also be a memory such as a RAM, a FIFO, etc.; in the system, having a physical form of storage The device can also be called a memory or the like. When implemented, the memory can also be implemented by using a cloud memory. The specific implementation manner is well limited.

It can be seen that the embodiment of the store information recommendation method, device or client of the present specification can determine the consumption group according to the consumption preference, and after the store information recommendation, determine the consumer group where the target user is located, Directly recommending the store information to the target user according to the consumption data of the user in the consumer group having similar consumption preferences with the target user, ensuring that the recommended store information better meets the preferences of the target user, and improves the user's recommended store information. The response probability, which in turn, can increase the user-to-store consumption rate.

The foregoing description of the specific embodiments of the specification has been described. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the embodiments and still achieve the desired results. In addition, the processes depicted in the figures are not necessarily in a particular order or in a sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In the 1990s, improvements to a technology could clearly distinguish between hardware improvements (eg, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (for process flow improvements). However, as technology advances, many of today's method flow improvements can be seen as direct improvements in hardware circuit architecture. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented by hardware entity modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers program themselves to "integrate" a digital system on a single PLD without having to ask the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, today, instead of manually making integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in programming development, but before compiling The original code has to be written in a specific programming language. This is called the Hardware Description Language (HDL). HDL is not the only one, but there are many kinds, such as ABEL (Advanced Boolean Expression Language). AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., are currently the most commonly used VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be apparent to those skilled in the art that the hardware flow for implementing the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with a few hardware description languages.

The controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor. In the form of logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also appreciate that in addition to implementing the controller in purely computer readable program code, the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding. The form of a microcontroller or the like to achieve the same function. Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component. Or even a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.

The apparatus, module or unit set forth in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

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

Those skilled in the art will appreciate that embodiments of the invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of a method, apparatus, apparatus, and computer program product according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

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

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic cassette tape, magnetic tape storage, graphene storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

Those skilled in the art will appreciate that embodiments of the present specification can be provided as a method, apparatus, or computer program product. Accordingly, the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware. Moreover, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

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

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and the client embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The above descriptions are only examples of the present specification and are not intended to limit the present specification. Various modifications and changes can be made in the present specification to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the specification are intended to be included within the scope of the appended claims.

Claims

A method for recommending shop information, including:

Determining a consumption group in which the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

Obtaining the store information that the user has consumed in the consumption group, and identifying the store information that the number of occurrences of the store information in the store information is greater than or equal to a preset threshold;

The shop information whose number of occurrences is greater than or equal to a preset threshold is recommended to the target user.
The method of claim 1, wherein the consumer group determined based on the consumption feature vector characterizing the user's consumption feature information is determined in the following manner:

Obtaining consumption characteristic information of a first number of users, the first number of users including the target user;

Constructing a consumption feature vector of the user based on the consumption feature information;

Performing cluster analysis processing on the first number of users based on the similarity between the consumption feature vectors of the first number of users, to obtain a second number of consumption groups.
The method of claim 2, wherein the constructing the user's consumption feature vector based on the consumption feature information comprises:

The consumption feature information is quantized into a specific value based on a preset quantization rule corresponding to the user's consumption feature information;

Constructing a first feature vector of the user based on the quantized specific value;

Normalizing the first feature vector to obtain a normalized second feature vector, and using the second feature vector as the consumption feature vector.
The method of claim 3, wherein the method further comprises:

Principal component analysis processing is performed on the second feature vector, and the feature vector after the principal component analysis process is used as the consumption feature vector.
The method of claim 2, wherein the method further comprises: before acquiring the consumption characteristic information of the first number of users, the method further comprising:

Determining the geographical location information in the first preset area of the location where the business circle is to be recommended, and using the user in the first preset area as the first quantity of users.
The method of claim 2 wherein said similarity comprises at least one of:

Euclidean distance, cosine distance, Manhattan distance, Jacques coefficient.
The method according to any one of claims 1 to 6, wherein the consumption characteristic information includes at least one of the following:

Consumption basic attribute information, consumption ability information, consumption habit information.
The method according to any one of claims 1 to 6, wherein the recommending the shop information that the number of occurrences is greater than or equal to a preset threshold to the target user comprises:

And recommending the shop information whose number of occurrences is greater than or equal to a preset threshold to the target user in a preset consumption time corresponding to the shop information whose number of occurrences is greater than or equal to a preset threshold.
The method according to any one of claims 1 to 6, wherein the recommending the shop information that the number of occurrences is greater than or equal to a preset threshold to the target user comprises:

When the target user is in the second preset area where the location information corresponding to the shop information corresponding to the preset threshold is greater than or equal to the preset threshold, the store information whose number of occurrences is greater than or equal to the preset threshold is recommended to The target user.
A shop information recommendation device, comprising:

a consumption group determining module, configured to determine a consumption group in which the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

a group store information obtaining module, configured to acquire shop information that the user has consumed in the consumer group;

a store information identifying module, configured to identify shop information in which the number of occurrences of shop information in the store information is greater than or equal to a preset threshold;

The shop information recommendation module is configured to recommend the shop information that the number of occurrences is greater than or equal to a preset threshold to the target user.
The apparatus according to claim 10, wherein said consumer group determined based on the consumption feature vector characterizing the user's consumption feature information is determined by using the following module:

a consumption feature information obtaining module, configured to acquire consumption characteristic information of a first quantity of users, where the first quantity of users includes the target user;

a consumption feature vector construction module, configured to construct a consumption feature vector of the user based on the consumption feature information;

The row clustering analysis processing module is configured to perform cluster analysis processing on the first number of users based on the similarity between the consumption feature vectors of the first number of users, to obtain a second number of consumption groups.
The apparatus of claim 11, wherein the consumption feature vector building module comprises:

a quantization unit, configured to quantize the consumption feature information into a specific value based on a preset quantization rule corresponding to the user's consumption feature information;

a first feature vector construction unit, configured to construct a first feature vector of the user based on the quantized specific value;

And a normalization processing unit, configured to perform normalization processing on the first feature vector to obtain a normalized second feature vector, and use the second feature vector as the consumption feature vector.
The apparatus of claim 12, wherein the consumption feature vector building module further comprises:

The principal component analysis processing unit is configured to perform principal component analysis processing on the second feature vector, and use the feature vector after the principal component analysis process as the consumption feature vector.
The apparatus of claim 11 wherein said apparatus further comprises:

a user determining module, configured to determine, in the first preset area where the geographical location information is located at a location where the business circle is to be recommended, before acquiring the consumption characteristic information of the first quantity of users, The user acts as the first number of users.
The apparatus of claim 11 wherein said similarity comprises at least one of:

Euclidean distance, cosine distance, Manhattan distance, Jacques coefficient.
The apparatus according to any one of claims 10 to 15, wherein said consumption characteristic information comprises at least one of the following:

Consumption basic attribute information, consumption ability information, consumption habit information.
The device according to any one of claims 10 to 15, wherein the store information recommendation module comprises:

The first store information recommendation unit is configured to recommend the store information whose number of occurrences is greater than or equal to a preset threshold to the target user in a preset consumption time corresponding to the store information whose number of occurrences is greater than or equal to a preset threshold.
The device according to any one of claims 10 to 15, wherein the store information recommendation module comprises:

a second store information recommendation unit, configured to: when the target user is in a second preset area where the location information corresponding to the store information corresponding to the preset threshold is greater than or equal to a preset threshold, the number of occurrences is greater than Store information equal to a preset threshold is recommended to the target user.
A store information recommendation client includes a processor and a memory, the memory storing computer program instructions executed by the processor, the computer program instructions comprising:

Determining a consumption group in which the target user is located, wherein the consumption group is determined by cluster analysis based on a consumption feature vector that represents the consumption feature information of the user;

Obtaining the store information that the user has consumed in the consumption group, and identifying the store information that the number of occurrences of the store information in the store information is greater than or equal to a preset threshold;

The shop information whose number of occurrences is greater than or equal to a preset threshold is recommended to the target user.