CN112465533A

CN112465533A - Intelligent product selection method and device and computing equipment

Info

Publication number: CN112465533A
Application number: CN201910857982.9A
Authority: CN
Inventors: 张美松
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Priority date: 2019-09-09
Filing date: 2019-09-09
Publication date: 2021-03-09

Abstract

The embodiment of the invention relates to the technical field of commodity management and discloses an intelligent commodity selection method, an intelligent commodity selection device and computing equipment. The method comprises the following steps: collecting user information related to a store and historical order information of the store from a database; respectively drawing a user and a store according to the user information and the historical order information to obtain a user drawing and a store drawing; determining a plurality of utility characteristic data according to the user portrait and the store portrait; determining the category of the store according to a plurality of the utility characteristic data; and determining a selection list of the stores according to the types of the stores. Through the mode, the embodiment of the invention can intelligently select products according to the actual user requirements, thereby avoiding subjectivity and blindness.

Description

Intelligent product selection method and device and computing equipment

Technical Field

The embodiment of the invention relates to the technical field of commodity management, in particular to an intelligent commodity selection method, an intelligent commodity selection device and computing equipment.

Background

Many stores select products by personal experience or company regulation, and perform operations such as putting and selling of products.

The current commodity selection method has the following defects: the target customer is not clear, the commodity is checked on the shelf and the user demand cannot be accurately identified, and the like, so that the product cannot be effectively selected.

Disclosure of Invention

In view of the foregoing, embodiments of the present invention provide an intelligent item selection method, apparatus, and computing device, which overcome or at least partially solve the above problems.

According to an aspect of an embodiment of the present invention, there is provided an intelligent item selection method, including: collecting user information related to a store and historical order information of the store from a database; respectively drawing a user and a store according to the user information and the historical order information to obtain a user drawing and a store drawing; determining a plurality of utility characteristic data according to the user portrait and the store portrait; determining the category of the store according to a plurality of the utility characteristic data; and determining a selection list of the stores according to the types of the stores.

In an optional manner, the determining the category of the store according to the plurality of utility characteristic data further includes: carrying out normalization processing on a plurality of utility characteristic data; determining the category of the store through factor analysis and cluster analysis according to the normalized utility characteristic data.

In an optional manner, the determining the category of the store through factor analysis and cluster analysis according to the normalized utility feature data further includes: judging whether correlation exists between the normalized effective characteristic data; if not, extracting a plurality of utility factors from the utility characteristic data, wherein one utility factor corresponds to one or more kinds of utility characteristic data; and classifying the stores through a hierarchical clustering algorithm according to the plurality of utility factors and the plurality of utility characteristic data, so as to determine the category of the stores.

In an optional manner, the determining the category of the store through factor analysis and cluster analysis according to the normalized utility feature data further includes: and carrying out variance analysis on the classification results of the stores to determine the classification number of the stores.

In an optional manner, the determining, from the user representation and the store representation, a plurality of utility feature data further includes: respectively acquiring a plurality of basic feature data from a user portrait and the store portrait; carrying out correlation detection on a plurality of basic characteristic data; and determining a plurality of utility characteristic data from a plurality of basic characteristic data according to the result of the correlation detection.

In an optional manner, the representing the user and the store according to the user information and the historical order information respectively further includes: portraying the user according to the user information, and portraying the store according to the historical order information; the user information comprises at least one of user age, user value, online time, terminal time, flow usage, terminal preference, package preference and content preference; the historical order information comprises at least one of product value, user size, consumption frequency, consumption crowd and user age.

In an optional manner, the determining the selection list of the stores according to the categories of the stores further includes: acquiring hot-sales product summaries of stores with the same category; and summarizing the hot sales products as a selection list of stores with the same category.

According to another aspect of the embodiments of the present invention, there is provided an intelligent item selecting apparatus, including: the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring user information related to a store and historical order information of the store from a database; the portrait module is used for respectively portraying the user and the store according to the user information and the historical order information so as to obtain the portrait of the user and the portrait of the store; the characteristic determining module is used for determining a plurality of utility characteristic data according to the user portrait and the store portrait; the category determining module is used for determining the category of the store according to the utility characteristic data; and the selection module is used for determining a selection list of the store according to the category of the store.

According to still another aspect of an embodiment of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus; the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the smart item selection method as described above.

According to another aspect of the embodiments 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 execute the intelligent item selecting method as described above.

According to the embodiment of the invention, the user information related to the store and the historical order information of the store are collected from the database, the user and the store are respectively drawn according to the user information and the historical order information to obtain the user drawing and the store drawing, a plurality of utility characteristic data are determined according to the user drawing and the store drawing, the type of the store is determined according to the plurality of utility characteristic data, the product selection list of the store is determined according to the type of the store, the user commonality of the store can be determined, the intelligent product selection is carried out according to the actual user requirement, and the subjectivity and the blindness are avoided.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments 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 chart illustrating a method for intelligent selection provided by an embodiment of the present invention;

FIG. 2 shows a flow chart of step 130 of FIG. 1;

FIG. 3 shows a flow chart of step 140 in FIG. 1;

FIG. 4 shows a flowchart of step 142 of FIG. 3;

FIG. 5 is a flow chart illustrating an actual application of the intelligent item selection method provided by the embodiment of the invention;

fig. 6 is a schematic structural diagram of an intelligent article selection device provided by an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.

Detailed Description

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

Fig. 1 shows a flowchart of an intelligent item selection method provided by an embodiment of the present invention. The method is applied in a computing device, such as a server in a communication network. As shown in fig. 1, the method comprises the steps of:

step 110, collecting user information related to the store and historical order information of the store from the database.

The database may be a big data platform in which one or more kinds of information of user basic information, store basic information, order information, terminal information, and product information are recorded. Based on the information in the database, user information related to the store and historical order information of the store can be obtained, and the user information and the historical order information can be used as indexes required for representing images.

The user information may include at least one of user age, user value, online duration, terminal duration, traffic usage, terminal preference, package preference, and content preference; the historical order information may include at least one of product value, user size, frequency of consumption, consumer population, user age. For example, the online duration, traffic usage, content preference, and the like are obtained according to the online information of the users around a certain store recorded in the database; and obtaining the user age, the consumer group and the like of a certain store according to the order information of the store recorded in the database.

And 120, respectively representing the user and the store according to the user information and the historical order information to obtain the user representation and the store representation.

Wherein, step 120 specifically includes: according to the user information, portraying the user to obtain a user portrait; and according to the historical order information, the store is represented to obtain the store representation. For example, the user is portrayed according to the age, the value, the online time, the terminal time, the traffic usage, the terminal preference, the package preference and the content preference of the user to obtain the user portrayal; and (4) portraying the store according to the product value, the user specification, the consumption frequency, the consumer group and the user age to obtain the store portrayal.

Optionally, in some other embodiments, the method may further include: collecting product information related to the store from a database; step 120 further comprises: and according to the product information, carrying out portrait on the product to obtain a product portrait. Wherein the product information comprises at least one of product value, user size, consumption frequency, consumer group and user age.

Step 130, determining a plurality of utility characteristic data according to the user portrait and the store portrait.

Wherein the utility feature data is a most representative feature selected from the user representation and the store representation and conveniently measured using the data value.

Specifically, as shown in fig. 2, step 130 includes:

step 131, acquiring a plurality of basic characteristic data from the user portrait and the store portrait respectively;

step 132, performing correlation detection on a plurality of basic characteristic data;

and step 133, determining a plurality of utility characteristic data from the plurality of basic characteristic data according to the result of the correlation detection.

In step 131, the base characteristic data is data that is conveniently scaled by data values. The base feature data obtained from the user representation and the store representation includes data for a number of features at a number of different stores. For example, the acquired basic feature data includes: user value data, traffic usage data, terminal duration data, etc. of store 1, and user value data, traffic usage data, terminal duration data, etc. of store 2.

In step 132, the correlation detection on the plurality of basic feature data may specifically be: and respectively carrying out correlation detection on every two basic characteristic data, or carrying out correlation detection on three basic characteristic data.

In step 133, if it is detected that two or three basic feature data are correlated, one of the correlated basic feature data is selected as the utility feature data. For example, it is assumed that the basic feature data includes data of user age, user value, online time, terminal time, traffic usage, user average value, hall access user ratio, user size, working crowd ratio, and order number, and the selected utility feature data is data of user value, traffic usage, terminal time, online time, user age, hall access user ratio, user size, working crowd ratio, and order number.

And step 140, determining the category of the store according to the plurality of utility characteristic data.

Specifically, as shown in fig. 3, step 140 includes:

step 141, normalizing the utility characteristic data;

and 142, determining the category of the store through factor analysis and cluster analysis according to the normalized utility characteristic data.

In step 141, since the utility feature data have different dimensions and are not comparable, it is necessary to normalize the utility feature data to achieve the uniformity and comparability of the utility feature data in terms of quantity. The method can be specifically realized by solving a correlation coefficient matrix of each utility characteristic data.

In step 142, because there is correlation between stores, a few irrelevant factors are used to reflect multiple pieces of original information with correlation through factor analysis and cluster analysis, so as to perform the functions of eliminating correlation and reducing dimensions.

As shown in fig. 4, step 142 may specifically include:

step 1421, determining whether there is a correlation between the normalized utility characteristic data;

step 1422, if not, extracting a plurality of utility factors from the plurality of utility characteristic data;

and step 1423, classifying the stores through a hierarchical clustering algorithm according to the utility factors and the utility characteristic data, so as to determine the types of the stores.

In step 1421, it is determined whether there is a correlation between the normalized utility characteristic data, so as to determine whether the selected utility characteristic data is suitable for factor analysis. The specific implementation mode can be as follows: outputting a sphericity test result of KMO and Bartlett by using SPSS, and if Sig is less than 0.05, indicating that no correlation exists between the normalized utility characteristic data, and performing factor analysis; if Sig is larger than or equal to 0.05, the fact that correlation exists among the normalized utility characteristic data is proved to be unsuitable for factor analysis, and then utility characteristic data need to be selected from the basic characteristic data again.

In step 1422, the utility factor is a factor capable of reflecting utility characteristic data, wherein a utility factor corresponds to one or more kinds of utility characteristic data. For example, assuming that the utility characteristic data includes data of user value, traffic usage, terminal duration, network duration, user age, hall access user duty ratio, user scale, working crowd duty ratio, and order number, 4 utility factors are extracted through factor analysis, wherein a factor 1 reflects terminal duration, network duration, and user age, a factor 2 reflects working crowd duty ratio and user value, a factor 3 reflects hall access user duty ratio and user scale, and a factor 4 reflects order number and traffic usage.

In step 1423, the specific implementation may be: calculating the score of each utility factor of each store according to the utility characteristic data of each store, classifying the stores through a hierarchical clustering algorithm, performing variance analysis on the classification result of the stores to determine the classification number of the stores, and classifying the stores according to the classification number.

And 150, determining a selection list of the stores according to the types of the stores.

The selection list is a product list used for getting on and off shelves in stores. Step 150 specifically includes: obtaining hot-sales product summaries of stores of the same category; and summarizing the hot sold products as a selection list of stores with the same category. For example, if stores are classified into 5 categories and stores 1, 5, and 7 belong to the same category, a summary of hot sales products of stores 1, 5, and 7 is obtained, and the summary of hot sales products of stores 1, 5, and 7 is used as a listing list of stores 1, 5, and 7, and products that do not belong to the summary of hot sales products are placed off the shelf.

It should be noted that the product in this embodiment may be a physical product (e.g., a smart terminal, a smart watch, etc.), and may also be a virtual product (e.g., a package of traffic packets, a package of monthly tenants, an e-commerce ticket code, etc.). The store in the present embodiment may be a physical store (e.g., a mobile business hall, a sales store, etc.), or may be a virtual store (e.g., an online business hall, an online shopping platform, etc.).

Fig. 5 shows a flow chart of an actual application of the intelligent item selecting method provided by the embodiment of the invention. As shown in fig. 5, the method includes:

step 210, collecting user information related to the store and historical order information of the store from the database.

And step 220, respectively representing the user and the store according to the user information and the historical order information to obtain the user representation and the store representation.

The method comprises the following steps of obtaining a user portrait according to the user age, the user value, the online time, the terminal time, the flow use, the terminal preference, the package preference and the content preference; and (4) portraying the store according to the product value, the user scale, the consumption frequency, the consumer group and the user age to obtain the store portrayal.

Step 230, determining utility characteristic data from the user representation and the store representation as: user value, traffic usage, terminal duration, online duration, user age, hall user duty ratio, user scale, worker population duty ratio, and order quantity data.

The utility characteristic data of each store is shown in table 1.

TABLE 1

And 241, carrying out normalization processing on the utility characteristic data of each store.

The results of normalization processing of the utility feature data of each store are shown in table 2.

TABLE 2

And 242, according to the normalized utility characteristic data, determining the category of each store through factor analysis applicability test, factor extraction, factor rotation, factor naming, factor score calculation, factor variable setting, store clustering and clustering effect test.

In the first step, a factor analysis suitability test is performed. And (4) checking whether correlation exists between the utility characteristics to judge whether factor analysis is suitable. And outputting the sphericity test results of KMO and Bartlett by using SPSS, wherein Sig is 0.000<0.05, and each utility characteristic passes factor analysis applicability test, which indicates that the utility characteristics are suitable for factor analysis. The results of the KMO and Bartlett tests are shown in Table 3.

TABLE 3

And secondly, factor extraction is carried out. From the common factor variance of the utility features, the interpretation degrees of the extracted factors on the 9 utility features exceed 70%, which shows that the extracted factors have certain explanatory power on the original features. Where the communality of utility features is shown in table 4.1 and the total explained variance is shown in table 4.2.

TABLE 4.1

	Initial	Extraction of
			Zscore (user value)	1.000	0.908
Zscore (flow use)	1.000	0.824
			Zscore (terminal time)	1.000	0.975
Zscore (duration on network)	1.000	0.974
			Zscore (age of user)	1.000	0.960
Zscore (living user ratio)	1.000	0.961
			Zscore (user scale)	1.000	0.952
Zscore (ratio of working population)	1.000	0.928
			Zscore (order quantity)	1.000	0.808

TABLE 4.2

From the total variance explained in table 4.2, the first 4 factors should be extracted according to the criterion of eigenvalue >1 (in the table, "component" is "factor", and "total" in the initial eigenvalue is eigenvalue of each factor), and it can be seen from the table that the cumulative variance contribution ratio of the first 4 factors is 92.315%, indicating that these factors can explain 92.119% of the total information amount.

And thirdly, performing factor rotation. From the component matrix, it is determined whether a factor rotation is required. Each feature in the matrix has a factor of 1 with a large factor load, i.e. 4 factors are separated by distinct regions in dimension, 4 factors with differentiated features. The composition matrix of each feature is shown in table 5.1.

TABLE 5.1

The numerical values in the table are called factor loads and represent the degree of interpretation of the characteristic information by the factors. From table 5.1, it can be seen that both factor 1 and factor 3 have the feature of "user scale" dimension, which indicates that there is correlation between the factors, and factor rotation is required to make the factors have the feature of differentiation. The method sets the factor rotation parameter to a factor load that does not show an absolute value <0.5, which makes it easier to observe the factor signature. By rotating the component matrix, only 1 factor on each feature of the matrix has a large (> 50%) factor load, i.e. 4 factors are distinctly separated in 10 dimensions, 4 factors have differentiated features. The rotational component matrix is shown in Table 5.2.

TABLE 5.2

And fourthly, naming the factors. The rotated component matrix effectively separates the dimension characteristics of 4 factors, so that the factors are named conveniently in order to visually present the dimension characteristics of each factor, and the corresponding relation between the factors and the characteristics sorted according to the rotated component matrix is shown in table 6.

TABLE 6

According to table 6, the factors are named as follows: the factor 1 reflects the characteristics of the dimensionality of terminal duration, network duration and user age, and is named as a user factor according to the dimension; the factor 2 reflects the characteristics of the dimensionality of 'working crowd ratio' and 'user value', and is named as 'value factor' according to the characteristic; the factor 3 reflects the dimension characteristics of 'the ratio of the users entering the hall' and 'the scale of the users', and is named as 'a scale factor' according to the dimension characteristics; the factor 4 reflects the characteristics of the "order quantity", "traffic usage" dimension, hence the name "usage factor".

And fifthly, calculating the factor score. The factor score refers to the score of each store at the extracted factor, with a higher score indicating that the store has more features of the factor. The component score coefficients of the respective features are shown in table 7.1.

TABLE 7.1

The factor scores were saved as new variables in the data file (as shown in table 7.2), indicating that each store had a score of 4 factors, which laid the foundation for the next step in determining the factor type of the store.

TABLE 7.2

And sixthly, setting a factor variable. According to the score of each factor of each store in the component score coefficient matrix, the type of the factors of the stores can be determined, for example, the score of a factor 2 is the highest among the scores of 4 factors of store 1, so that the value of the factor variable of store 1 is 2, which indicates that the store belongs to the type of a factor 2, i.e., a "value type" store. The factor types of stores are shown in table 8.

TABLE 8

Shop name	Factor 1	Factor 2	Factor 3	Factor 4	Factor category
						Shop 1	0.30	1.07	-1.38	0.66	2.00
Shop 2	0.86	-1.17	2.15	-0.56	3.00
						Shop 3	1.50	-0.58	-0.41	2.20	4.00
Shop 4	0.59	0.02	-0.29	-1.03	1.00
						Shop 5	-0.53	1.24	-0.73	0.37	2.00
Shop 6	0.28	0.48	0.82	1.43	4.00
						Shop 7	0.07	2.74	0.60	0.56	2.00
Shop 8	-1.81	-0.20	0.23	-0.12	3.00
						Shop 9	0.38	-0.94	-0.43	-1.16	1.00
Store 10	-0.07	-0.64	-0.09	0.70	4.00
						Store 11	-0.71	-0.94	1.04	0.92	3.00
Store 12	-2.13	-0.85	0.54	0.81	4.00
						Store 13	1.54	-0.34	-0.86	-0.65	1.00
Store 14	0.80	-0.51	-0.25	-0.02	1.00
						Store 15	-0.04	0.66	-0.12	-1.60	2.00
Store 16	0.50	-0.68	0.39	0.13	1.00
						Store 17	-1.45	-0.71	-1.21	-0.58	4.00
Store 18	-0.51	1.01	2.13	-0.99	3.00
						Store 19	0.44	0.33	-1.05	-1.09	1.00

And seventhly, clustering stores. The stores are classified by a hierarchical clustering algorithm by taking 4 factors as variables (as shown in table 9), and the results of clustering the stores into 3-8 classes can be seen from the table.

TABLE 9

And eighthly, checking the clustering effect. Respectively carrying out variance analysis on the 3-8 types of results, finding that the effect of clustering the stores into 5 types is the best, and as can be seen from the variance analysis results (shown in table 10.1) of clustering into 5 types, the factor significance P is less than 0.05, which indicates that all types of stores subdivided by clustering have significance differences in all factors, and the clustering effect is good.

According to the differentiated performance of various stores on various characteristics, various subdivision stores can be named, and the method comprises the following steps: high-end elite population, low-end worker population, middle-aged and elderly people, family life population and college student population. The differentiation performance of each characteristic of each store is shown in table 10.2.

TABLE 10.1

TABLE 10.2

Wherein, the characteristic characteristics of stores 1, 5, 7 are: the working crowd is high in occupation ratio and the user value is high; the characteristic features of the stores 2, 18 are: the occupancy ratio of the users entering the hall is high, the scale of the users is large, the user value is low, and the occupancy ratio of the working population is high; the characteristic features of stores 3, 6, 10, 11, 14, 16 are: large order quantity, large average age of users and low user value; the characteristic features of stores 4, 9, 13, 15, 19 are: the on-line time is long, the terminal time is long and high, the user value is low, and the working crowd ratio is low; the characteristic features of the stores 8, 12, 17 are: the traffic is used more, the average age of the users is small, the user value is low, and the on-line time is low;

and step 250, acquiring hot sales product summaries of stores with the same category according to the categories of the stores, and taking the hot sales product summaries as the option lists of the stores with the same category to determine the option lists of the stores.

For example, as can be seen from table 10.2, store 1, store 5, and store 7 all belong to high-end elite population type stores. Counting the order quantity of the stores 1, 5 and 7 according to the products, sorting the order quantity from large to small, and determining the products with the top rank as the hot-sold products of the stores. Since the stores 1, 5, and 7 belong to the same type of store, hot sales products of the three stores are collected as a selection list of the three stores.

According to the embodiment of the invention, the user information related to the store and the historical order information of the store are collected from the database, the user and the store are respectively represented according to the user information and the historical order information to obtain the user representation and the store representation, a plurality of utility characteristic data are determined according to the user representation and the store representation, the stores are classified according to the plurality of utility characteristic data through factor analysis and cluster analysis to determine the type of the store, the selection list of the store is determined according to the type of the store, the user commonality of the store can be determined, the intelligent selection is carried out according to the actual user requirement, the subjectivity and the blindness are avoided, the data can be automatically collected, the optimization iteration of an intelligent selection model is realized, and the accuracy of the model is continuously improved.

Fig. 6 shows a schematic structural diagram of an intelligent article selection device according to an embodiment of the present invention. As shown in fig. 6, the apparatus 300 includes: an acquisition module 310, a representation module 320, a feature determination module 330, a category determination module 340, and a selection module 350.

The acquisition module 310 is configured to acquire user information related to a store and historical order information of the store from a database; the image module 320 is used for respectively drawing the user and the store according to the user information and the historical order information to obtain a user image and a store image; the feature determination module 330 is configured to determine a plurality of utility feature data according to the user representation and the store representation; the category determination module 340 is configured to determine a category of the store according to a plurality of the utility feature data; the choice module 350 is configured to determine a list of choices for the store according to the category of the store.

In an alternative, the category determination module 340 includes a normalization unit and a category determination unit. The normalization unit is used for performing normalization processing on the utility characteristic data; the category determination unit is used for determining the category of the store through factor analysis and cluster analysis according to the normalized utility characteristic data.

In an optional manner, the category determining unit is specifically configured to: judging whether correlation exists between the normalized effective characteristic data; if not, extracting a plurality of utility factors from the utility characteristic data, wherein one utility factor corresponds to one or more kinds of utility characteristic data; and classifying the stores through a hierarchical clustering algorithm according to the plurality of utility factors and the plurality of utility characteristic data, so as to determine the category of the stores.

In an optional manner, the category determining unit is further specifically configured to: and carrying out variance analysis on the classification results of the stores to determine the classification number of the stores.

In an optional manner, the feature determining module 330 is specifically configured to: respectively acquiring a plurality of basic characteristic data from a user portrait and the store portrait; carrying out correlation detection on a plurality of basic characteristic data; and determining a plurality of utility characteristic data from a plurality of basic characteristic data according to the result of the correlation detection.

In an alternative manner, the image module 320 is specifically configured to: portraying the user according to the user information, and portraying the store according to the historical order information; the user information comprises at least one of user age, user value, online time, terminal time, flow use, terminal preference, package preference and content preference; the historical order information comprises at least one of product value, user size, consumption frequency, consumption crowd and user age.

In an optional manner, the selection module 350 is specifically configured to: acquiring hot-sales product summaries of stores with the same category; and summarizing the hot sales products as a selection list of stores with the same category.

It should be noted that the intelligent product selection device provided in the embodiment of the present invention is a device capable of executing the intelligent product selection method, and all embodiments of the intelligent product selection method are applicable to the device and can achieve the same or similar beneficial effects.

An embodiment of the present invention provides a computer storage medium, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to execute the intelligent item selection method in any of the above method embodiments.

Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform a method of intelligent selection in any of the above method embodiments.

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

As shown in fig. 7, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.

Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute the intelligent article selection method in any of the method embodiments described above.

In particular, program 410 may include program code comprising computer operating instructions.

The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present 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.

And a memory 406 for storing a program 410. The memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, 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. In addition, embodiments of the present invention are 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 embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention 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 is, the claimed invention 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 placed 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 of skill in the art will understand that while some embodiments herein include some features included in other embodiments, rather than others, 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.

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. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims

1. An intelligent item selection method, characterized in that the method comprises:

collecting user information related to a store and historical order information of the store from a database;

respectively drawing a user and a store according to the user information and the historical order information to obtain a user drawing and a store drawing;

determining a plurality of utility characteristic data according to the user portrait and the store portrait;

determining the category of the store according to a plurality of the utility characteristic data;

and determining a selection list of the stores according to the types of the stores.

2. The method of claim 1, wherein determining the category of the store from the plurality of utility profile data further comprises:

carrying out normalization processing on a plurality of utility characteristic data;

and determining the category of the store through factor analysis and cluster analysis according to the normalized utility characteristic data.

3. The method of claim 2, wherein determining the category of the store by factor analysis and cluster analysis from the normalized utility feature data further comprises:

judging whether correlation exists between the normalized utility characteristic data;

if not, extracting a plurality of utility factors from the utility characteristic data, wherein one utility factor corresponds to one or more kinds of utility characteristic data;

and classifying the stores through a hierarchical clustering algorithm according to the plurality of utility factors and the plurality of utility characteristic data, so as to determine the category of the stores.

4. The method of claim 1, wherein determining the category of the store by factor analysis and cluster analysis from the normalized utility feature data further comprises:

and carrying out variance analysis on the classification results of the stores to determine the classification quantity of the stores.

5. The method of claim 1, wherein determining a plurality of utility feature data from the user representation and the store representation further comprises:

respectively acquiring a plurality of basic characteristic data from a user portrait and the store portrait;

carrying out correlation detection on a plurality of basic characteristic data;

and determining a plurality of pieces of utility characteristic data from a plurality of pieces of basic characteristic data according to the result of the correlation detection.

6. The method of claim 1, wherein said representing a user and a store from said user information and said historical order information, respectively, further comprises:

portraying the user according to the user information, and portraying the store according to the historical order information;

the user information comprises at least one of user age, user value, online time, terminal time, flow usage, terminal preference, package preference and content preference;

the historical order information comprises at least one of product value, user size, consumption frequency, consumption crowd and user age.

7. The method of any of claims 1-6, wherein determining the list of options for the store based on the category of the store further comprises:

acquiring hot-sales product summaries of stores with the same category;

and summarizing the hot sales products as a selection list of stores with the same category.

8. An intelligent item selection device, the device comprising:

the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring user information related to a store and historical order information of the store from a database;

the portrait module is used for respectively portraying the user and the store according to the user information and the historical order information so as to obtain the portrait of the user and the portrait of the store;

the characteristic determining module is used for determining a plurality of utility characteristic data according to the user portrait and the store portrait;

the category determining module is used for determining the category of the store according to the utility characteristic data;

and the selection module is used for determining a selection list of the store according to the category of the store.

9. 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 configured to store at least one executable instruction that causes the processor to perform the operations of the smart option method of any of claims 1-7.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the smart option method of any one of claims 1-7.