CN116029798A - User demand recommendation method, system, electronic equipment and readable storage medium - Google Patents
User demand recommendation method, system, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116029798A CN116029798A CN202310282824.1A CN202310282824A CN116029798A CN 116029798 A CN116029798 A CN 116029798A CN 202310282824 A CN202310282824 A CN 202310282824A CN 116029798 A CN116029798 A CN 116029798A
- Authority
- CN
- China
- Prior art keywords
- style
- category
- push
- user
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a user demand recommending method, a system, electronic equipment and a readable storage medium, wherein the method comprises the steps of obtaining user history data in preset time, wherein the user history data comprises a plurality of pieces of browsing data, and each piece of browsing data comprises commodity category and style identification; determining category weights and style weights corresponding to browsing data according to user historical data, a preset style category comparison table and preset weight calculation rules; based on the feature determining rule, determining a feature style and a feature category according to the commodity category, the style identification and the style category comparison table; and determining push content and push duty ratio corresponding to the push content according to the category weight, the style weight, the feature style, the feature category and a preset recommendation method, and pushing. The invention has the effect of improving the activity of the user.
Description
Technical Field
The present disclosure relates to the field of data analysis, and in particular, to a user demand recommendation method, system, electronic device, and readable storage medium.
Background
At present, in an e-commerce shopping platform, the user's behavior habit is mainly analyzed, the historical behavior data of the user is utilized, the user's browsing, paying attention to or adding shopping carts and other behaviors are analyzed, the purchase intention of the user on a commodity is quantified, effective information is recommended to the user, the time for screening the information by the user is saved, and the effective utilization rate of the information is also improved.
However, the disadvantage of this recommendation method is that the more definite the preference of the user is, the more the style of the commodity recommended to the user is fixed, the single content browsed by the user appears, and aesthetic fatigue is easily caused to the user, so that the liveness of the user is reduced.
The prior art solutions described above have the following drawbacks: there is a problem in that user liveness is lowered.
Disclosure of Invention
In order to improve the problem of reduced user activity, the application provides a user demand recommendation method, a system, electronic equipment and a readable storage medium.
In a first aspect of the present application, a user demand recommendation method is provided. The method comprises the following steps:
acquiring user history data in preset time, wherein the user history data comprises a plurality of pieces of browsing data, and each piece of browsing data comprises commodity category and style identification;
determining category weights and style weights corresponding to the browsing data according to the user historical data, a preset style category comparison table and a preset weight calculation rule;
based on a feature determining rule, determining a feature style and a feature category according to the commodity category, the style identification and a style category comparison table;
and determining push content and push proportion corresponding to the push content and pushing according to the category weight, the style weight, the characteristic style, the characteristic category and a preset recommendation method.
According to the technical scheme, the category weight and the style weight are calculated by acquiring the user history data in the preset time, the latest browsing preference of the user is analyzed according to the category weight and the style weight, different characteristic styles and characteristic categories are determined according to different preferences of the user, then the push proportion corresponding to the push content and the push content is determined according to the characteristic styles, the characteristic categories and the recommendation method, and the push is completed, so that different push contents and different push proportion of different push contents can be customized for the user according to the browsing habit of the user, the browsing preference of the user is more attached to the user to a certain extent, and positive influence is generated on improving the activity of the user.
In a possible implementation manner, the determining, according to the user history data, a preset style category comparison table and a preset weight calculation rule, a category weight and a style weight corresponding to the user history data includes:
the style category comparison table comprises all commodity categories, all style identifications, category association degrees among the commodity categories and style association degrees among the style identifications;
acquiring style data volume and category data volume corresponding to the user history data, wherein the style data volume represents the number of different style identifications included in the user history data, and the category data volume represents the number of different commodity categories included in the user history data;
acquiring the total number of styles and the total number of categories in the style category comparison table;
the category weight = the category data amount/the total number of categories;
the style weight = the amount of style data/the total number of styles.
In one possible implementation manner, the determining, based on the feature determining rule, a feature style and a feature category according to the commodity category, the style identification and a style category comparison table includes:
according to the user history data and the style category comparison table, acquiring the style association degree of the style identification corresponding to the user history data and other style identifications and the category association degree of the commodity category corresponding to the user history data and other commodity categories;
when the style association degree is within a preset association threshold range, other style marks corresponding to the style association degree are feature styles;
and when the category association degree is within a preset association threshold range, the other commodity categories corresponding to the category association degree are feature categories.
In one possible implementation manner, the determining, according to the category weight, the style weight, the feature style, the feature category, and a preset recommendation method, a push content and a push ratio corresponding to the push content, and pushing includes:
the pushing content comprises commodities corresponding to the characteristic styles, commodities corresponding to the characteristic categories, commodities corresponding to the style identifiers and commodities corresponding to the commodity categories;
determining a user type according to the style weight, the category weight and a preset weight comparison table, wherein the user type represents wide browsing preference or preference concentration of a user;
respectively determining a push duty ratio corresponding to a characteristic category, a push duty ratio corresponding to a characteristic style, a push duty ratio corresponding to the style identification and a push duty ratio corresponding to the commodity category according to the user type and the recommended proportion table;
and completing pushing according to the pushing content and the pushing proportion corresponding to the pushing content.
In one possible implementation, the method further includes:
acquiring the characteristic style, characteristic browsing data of the characteristic category and the client liveness, wherein the characteristic browsing data comprises browsing time and browsing duration;
classifying the characteristic browsing data according to the browsing time;
acquiring the browsing sum of the browsing duration of each type of characteristic browsing data;
calculating a correlation coefficient of the client liveness and the browsing sum based on a preset correlation calculation rule;
and adjusting the push content and the push duty ratio corresponding to the push content according to the correlation coefficient and the push adjustment rule.
In one possible implementation manner, the adjusting the push content and the push ratio corresponding to the push content according to the correlation coefficient and the push adjustment rule includes:
when the correlation coefficient is greater than zero;
judging whether the correlation coefficient is smaller than a correlation threshold value or not;
if yes, not adjusting the push duty ratio corresponding to the push content;
if not, based on the duty ratio adjustment table, increasing the push duty ratio corresponding to the push content.
In one possible implementation manner, the adjusting the push content and the push ratio corresponding to the push content according to the correlation coefficient and the push adjustment rule further includes:
and when the correlation coefficient is smaller than zero, reducing the push duty ratio corresponding to the push content based on a duty ratio adjustment table.
In a second aspect of the present application, a user demand recommendation system is provided. The system comprises:
the data acquisition module is used for acquiring user history data in preset time, wherein the user history data comprises a plurality of pieces of browsing data, and each piece of browsing data comprises commodity category and style identification;
the weight calculation module is used for determining category weights and style weights corresponding to the user history data according to the user history data, a preset style category comparison table and a preset weight calculation rule;
the feature determining module is used for determining a feature style and a feature category according to the commodity category, the style identification and the style category comparison table based on feature determining rules;
and the pushing determination module is used for determining pushing content and pushing duty ratio corresponding to the pushing content according to the category weight, the style weight, the characteristic style, the characteristic category and a preset recommendation method.
In a third aspect of the present application, an electronic device is provided. The electronic device includes: a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method as described above when executing the program.
In a fourth aspect of the present application, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method as according to the first aspect of the present application.
In summary, the present application includes at least one of the following beneficial technical effects:
the latest browsing preference of the user is analyzed by acquiring the user history data in the preset time, different characteristic styles and characteristic categories are determined according to different preferences of the user, then the push content and the push duty ratio corresponding to the push content are determined according to the characteristic styles, the characteristic categories and the recommendation method, and the push is completed, so that the user browsing preference is more attached to the user to a certain extent, and the activity of the user is improved.
Drawings
Fig. 1 is a flow chart of a user demand recommendation method provided in the present application.
Fig. 2 is a schematic structural diagram of a user demand recommendation system provided in the present application.
Fig. 3 is a schematic structural diagram of an electronic device provided in the present application.
In the figure, 200, a user demand recommendation system; 201. a data acquisition module; 202. a weight calculation module; 203. a feature determination module; 204. a pushing determination module; 301. a CPU; 302. a ROM; 303. a RAM; 304. an I/O interface; 305. an input section; 306. an output section; 307. a storage section; 308. a communication section; 309. a driver; 310. removable media.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.
The embodiment of the application provides a user demand recommendation method, and the main flow of the method is described as follows.
As shown in fig. 1:
step S101: and acquiring user history data in a preset time.
Specifically, the user history data includes a plurality of browsing data, each browsing data includes a commodity category and a style identifier, each browsing data corresponds to browsing a commodity, and each browsing data includes a commodity category and a style identifier. The commodity category indicates the types of commodities including foods, furniture, clothing, etc., and the style identification includes the style of a certain type of commodity, for example, the style of furniture includes new style, mediterranean style, new classical style, european style, japanese style, nordic style, industrial style, post modern style, garden style, modern brief style, etc., and the style of clothing includes fresh wind, leisure wind, sports wind, business wind, brief wind, etc. The preset time is a set time, generally, the user history data of the previous year or the previous two years of the current time is obtained instead of all the user history data, the preference of the user in the last period of time can be analyzed by obtaining the user history data in the preset time, if all the user history data are obtained, the latest preference of the user may be weakened, and a larger error exists in the subsequent analysis result.
Step S102: and determining the category weight and the style weight corresponding to the user history data according to the user history data, a preset style category comparison table and a preset weight calculation rule.
Specifically, the style category comparison table includes all commodity categories, all style identifications, category association degrees among all commodity categories, and style association degrees among all style identifications. And acquiring the style data volume and the category data volume corresponding to the user history data, wherein the style data volume represents the number of different style identifications included in the user history data, and the category data volume represents the number of different commodity categories included in the user history data. For example, the user history data has ten pieces of browsing data, wherein the style with 4 pieces of browsing data is identified as an industrial style, the style with 4 pieces of browsing data is identified as a garden style, the style with 2 pieces of browsing data is identified as an European style, and the style data amount is 3. The category data amount is the same as the style data amount, and will not be described here. And acquiring the total number of styles and the total number of categories in the style category comparison table, wherein the total number of styles represents the number of all the style identifications, and the total number of categories represents the number of all the commodity categories. The above category weight = category data amount/total number of categories; the above style weight=style data amount/style total.
Step S103: based on the feature determining rule, determining a feature style and a feature category according to the commodity category, the style identification and the style category comparison table.
Specifically, according to the user history data and the style category comparison table, the style association degree of the style identifier corresponding to the user history data and other style identifiers and the category association degree of the commodity category corresponding to the user history data and other commodity categories are obtained. The other style identifications include other style identifications in addition to the style identifications appearing in the user history data. The other commodity categories include commodity categories other than those appearing in the user history data. When the style association degree is within the preset association threshold value range, the style concerned by the user and other styles with higher similarity are indicated, and the styles with higher similarity can be recommended to the user, and other styles corresponding to the style association degree are identified as feature styles. When the category association degree is within a preset association threshold value, a user who purchases or pays attention to the commodity category also purchases or pays attention to the commodity corresponding to the commodity category, and other commodity categories corresponding to the category association degree are feature categories.
Step S104: and determining push content and push duty ratio corresponding to the push content according to the category weight, the style weight, the feature style, the feature category and a preset recommendation method, and pushing.
Specifically, the pushing content includes a commodity corresponding to the characteristic style, a commodity corresponding to the characteristic category, a commodity corresponding to the style identification, and a commodity corresponding to the commodity category; determining a user type according to the style weight, the category weight and a preset weight comparison table, wherein the user type represents wide browsing preference or preference concentration of a user; and respectively determining a push duty ratio corresponding to the characteristic category, a push duty ratio corresponding to the characteristic style, a push duty ratio corresponding to the style identification and a push duty ratio corresponding to the commodity category according to the user type and the recommended proportion table, and completing push. The weight comparison table comprises style weights, category weights and user types corresponding to the style weights and the category weights. The recommended proportion table comprises a user type, a push duty ratio corresponding to a characteristic category, a push duty ratio corresponding to a characteristic style, a push duty ratio corresponding to a style identification and a push duty ratio corresponding to a commodity category.
In one example, when both the category weight and the style weight are greater than sixty percent, the user is indicated to be of a type that is relatively broad for both category and style preferences. And carrying the user type into a recommended proportion table to obtain a specific push duty ratio. The specific push duty cycle for this user is: pushing commodities of commodity categories browsed by a user to seventy percent of total push content, namely, pushing proportion corresponding to the commodity categories is seventy percent; pushing commodities of commodity categories which are not browsed by the user to be thirty percent of the total push content, namely, the push proportion corresponding to the characteristic categories is thirty percent; pushing commodities with style marks browsed by a user to seventy percent of total push content, namely, pushing the commodities with style marks corresponding to seventy percent; the commodity pushing of the style identification which is not browsed by the user accounts for thirty percent of the total pushing content, namely the pushing ratio corresponding to the characteristic style is thirty percent.
In another example, when the category weight is greater than seventy percent and the style weight is less than twenty percent, the user is indicated to be of a type that is more extensive for the category and more focused for the style's preference. And carrying the user type into a recommended proportion table to obtain a specific push duty ratio. The specific push duty cycle for this user is: pushing commodities in commodity categories browsed by a user to be fifty percent of the total push content, namely, the push ratio corresponding to the commodity categories is fifty percent; pushing commodities of commodity categories which are not browsed by the user to be fifty percent of the total push content, namely, the push proportion corresponding to the characteristic categories is fifty percent; pushing the commodity with the style identifier browsed by the user to ninety percent of the total push content, namely, enabling the pushing ratio corresponding to the style identifier to be ninety percent; and pushing the commodity which is not browsed by the user and is identified by the style to be ten percent of the total push content, namely, the push ratio corresponding to the characteristic style is ten percent.
It can be understood that each commodity includes a style identification and a commodity category, and when the push of the commodity category is relatively large and the push of the style identification is relatively small, the commodity category is shown to push a plurality of different commodities, but the styles are relatively concentrated. For example, the recommended commodity categories include clothing, furniture, cloth, and ornaments. The recommended commercial styles all tend to be consistent, for example, both pink girl winds or both black and white and gray conciseness winds.
The user demand recommendation method further comprises the following steps: and acquiring the characteristic browsing data and adjusting the push content and the push duty ratio corresponding to the push content according to the characteristic browsing data and the push adjustment rule.
Specifically, the characteristic style, characteristic browsing data of the characteristic category and the client activity are obtained, wherein the characteristic browsing data comprises browsing time and browsing duration, the browsing time indicates from which point in time to start browsing, and the browsing duration indicates the stay time length of an interface of the commodity; classifying the characteristic browsing data according to the browsing time; for example, the daily feature browsing data is taken as a class in units of days. Acquiring the browsing sum of the browsing duration of each type of characteristic browsing data; and calculating the correlation coefficient of the client liveness and the browsing sum based on a preset correlation calculation rule. The above-mentioned correlation calculation rule is a technical means known to those skilled in the art, and in this embodiment, the above-mentioned correlation calculation rule is a calculation method of a spearman correlation coefficient, that is, the above-mentioned correlation coefficient is a spearman correlation coefficient, and in other embodiments, other correlation calculation rules may be used, which is not limited herein. And adjusting the push content and the push duty ratio corresponding to the push content according to the correlation coefficient and the push adjustment rule. When the correlation coefficient is larger than zero and smaller than the correlation threshold, the client activity is positively correlated with the characteristic browsing data, but the client activity is not obviously improved, and the current push content is kept, namely the push duty ratio corresponding to the push content is not adjusted; when the correlation coefficient is larger than the correlation threshold, the client activity is positively correlated with the characteristic browsing data, the client activity is obviously improved, and the push duty ratio corresponding to the push content is increased based on the duty ratio adjustment table; when the correlation coefficient is smaller than zero, the push content corresponding to the increased feature style and feature category, which indicates that the client liveness is inversely correlated with the feature browsing data, reduces the client liveness, and based on the duty ratio adjustment table, reduces the push duty ratio corresponding to the push content. The above-mentioned calculation method of the client activity is a technology known to those skilled in the art, and will not be described herein. The duty cycle adjustment table includes a correlation coefficient and a corresponding adjustment duty cycle.
In one example, the correlation coefficient is a spearman coefficient, the correlation threshold is 0.5, when the correlation coefficient is greater than 0 and less than 0.5, the client activity is positively correlated with the characteristic browsing data, but there is no obvious positive effect on improving the client activity, and the current push content is maintained, i.e. the push duty ratio corresponding to the push content is not adjusted. When the correlation coefficient is greater than 0.5, the client activity is positively correlated with the feature browsing data, the push content corresponding to the feature style and the feature category plays a certain positive role in the client activity, the push duty ratio corresponding to the push content is increased based on the duty ratio adjustment table, for example, when the correlation coefficient is 0.7, the corresponding adjustment duty ratio is +5%, namely, the push duty ratio of the commodity corresponding to the feature category and the feature style is increased by five percent. When the correlation coefficient is smaller than 0, the push content corresponding to the characteristic style and the characteristic category, which indicates that the client activity is negatively correlated with the characteristic browsing data, has a certain negative influence on the client activity, and based on the duty ratio adjustment table, the push duty ratio corresponding to the push content is reduced, for example, the correlation coefficient is-0.3, and the corresponding adjustment duty ratio is-10%, namely, the duty ratio of commodity push corresponding to the characteristic category and the characteristic style is reduced by ten percent. When the reduced duty ratio is larger than the original push duty ratio, the push of the characteristic style and the characteristic category is deleted, for example, the duty ratio corresponding to the characteristic style and the characteristic category is ten percent, the adjustment duty ratio is-20 percent, namely, the push duty ratio of twenty percent is reduced by more than ten percent, so that the push content corresponding to the characteristic style and the characteristic category is deleted.
Referring to fig. 2, the user demand recommendation system 200 includes:
the data acquisition module 201 is configured to acquire user history data within a preset time, where the user history data includes a plurality of browsing data, and each browsing data includes a commodity category and a style identifier;
the weight calculation module 202 is configured to determine a category weight and a style weight corresponding to the user history data according to the user history data, a preset style category comparison table and a preset weight calculation rule;
the feature determining module 203 is configured to determine a feature style and a feature class according to the commodity class, the style identifier, and a style class comparison table based on a feature determining rule;
the push determining module 204 is configured to determine push content and a push duty ratio corresponding to the push content according to the category weight, the style weight, the feature style, the feature category, and a preset recommendation method, and push.
It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the described module, which is not described herein again.
The embodiment of the application discloses electronic equipment. Referring to fig. 3, the electronic device includes a Central Processing Unit (CPU) 301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage portion 307 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other by a bus. An input/output (I/O) interface 304 is also connected to the bus.
The following components are connected to the I/O interface 304: an input section 305 including a keyboard, a mouse, and the like; an output portion 306 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 307 including a hard disk and the like; and a communication section 308 including a network interface card such as a LAN card, a modem, or the like. The communication section 308 performs communication processing via a network such as the internet. A driver 309 is also connected to the I/O interface 304 as needed. A removable medium 310 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 309 as needed, so that a computer program read out therefrom is installed into the storage section 307 as needed.
In particular, according to embodiments of the present application, the process described above with reference to flowchart fig. 1 may be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 308, and/or installed from the removable media 310. The above-described functions defined in the apparatus of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 301.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the application referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or their equivalents is possible without departing from the spirit of the application. Such as the above-mentioned features and the technical features having similar functions (but not limited to) applied for in this application are replaced with each other.
Claims (10)
1. A user demand recommendation method, comprising:
acquiring user history data in preset time, wherein the user history data comprises a plurality of pieces of browsing data, and each piece of browsing data comprises commodity category and style identification;
determining category weights and style weights corresponding to the browsing data according to the user historical data, a preset style category comparison table and a preset weight calculation rule;
based on a feature determining rule, determining a feature style and a feature category according to the commodity category, the style identification and a style category comparison table;
and determining push content and push proportion corresponding to the push content and pushing according to the category weight, the style weight, the characteristic style, the characteristic category and a preset recommendation method.
2. The method for recommending user demands according to claim 1, wherein determining the category weight and the style weight corresponding to the user history data according to the user history data, a preset style category comparison table and a preset weight calculation rule comprises:
the style category comparison table comprises all commodity categories, all style identifications, category association degrees among the commodity categories and style association degrees among the style identifications;
acquiring style data volume and category data volume corresponding to the user history data, wherein the style data volume represents the number of different style identifications included in the user history data, and the category data volume represents the number of different commodity categories included in the user history data;
acquiring the total number of styles and the total number of categories in the style category comparison table;
the category weight = the category data amount/the total number of categories;
the style weight = the amount of style data/the total number of styles.
3. The user demand recommendation method according to claim 2, wherein said determining a feature style and feature category from said commodity category, said style identification and a style category comparison table based on feature determination rules comprises:
according to the user history data and the style category comparison table, acquiring the style association degree of the style identification corresponding to the user history data and other style identifications and the category association degree of the commodity category corresponding to the user history data and other commodity categories;
when the style association degree is within a preset association threshold range, other style marks corresponding to the style association degree are feature styles;
and when the category association degree is within a preset association threshold range, the other commodity categories corresponding to the category association degree are feature categories.
4. The method for recommending user demands according to claim 1, wherein determining push content and push duty ratio corresponding to the push content and pushing according to the category weight, the style weight, the feature style, the feature category and a preset recommending method comprises:
the pushing content comprises commodities corresponding to the characteristic styles, commodities corresponding to the characteristic categories, commodities corresponding to the style identifiers and commodities corresponding to the commodity categories;
determining a user type according to the style weight, the category weight and a preset weight comparison table, wherein the user type represents wide browsing preference or preference concentration of a user;
respectively determining a push duty ratio corresponding to a characteristic category, a push duty ratio corresponding to a characteristic style, a push duty ratio corresponding to the style identification and a push duty ratio corresponding to the commodity category according to the user type and the recommended proportion table;
and completing pushing according to the pushing content and the pushing proportion corresponding to the pushing content.
5. The user demand recommendation method of claim 1, further comprising:
acquiring the characteristic style, characteristic browsing data of the characteristic category and the client liveness, wherein the characteristic browsing data comprises browsing time and browsing duration;
classifying the characteristic browsing data according to the browsing time;
acquiring the browsing sum of the browsing duration of each type of characteristic browsing data;
calculating a correlation coefficient of the client liveness and the browsing sum based on a preset correlation calculation rule;
and adjusting the push content and the push duty ratio corresponding to the push content according to the correlation coefficient and the push adjustment rule.
6. The user demand recommendation method of claim 5, wherein the adjusting the push content and the push duty cycle corresponding to the push content according to the correlation coefficient and the push adjustment rule comprises:
when the correlation coefficient is greater than zero;
judging whether the correlation coefficient is smaller than a correlation threshold value or not;
if yes, not adjusting the push duty ratio corresponding to the push content;
if not, based on the duty ratio adjustment table, increasing the push duty ratio corresponding to the push content.
7. The user demand recommendation method of claim 5, wherein the adjusting the push content and the push duty cycle corresponding to the push content according to the correlation coefficient and the push adjustment rule further comprises:
and when the correlation coefficient is smaller than zero, reducing the push duty ratio corresponding to the push content based on a duty ratio adjustment table.
8. A user demand recommendation system, comprising:
the data acquisition module (201) is used for acquiring user history data in preset time, wherein the user history data comprises a plurality of pieces of browsing data, and each piece of browsing data comprises commodity category and style identification;
the weight calculation module (202) is used for determining category weights and style weights corresponding to the user history data according to the user history data, a preset style category comparison table and a preset weight calculation rule;
a feature determining module (203) configured to determine a feature style and a feature category according to the commodity category, the style identification, and a style category comparison table based on a feature determining rule;
and the pushing determination module (204) is used for determining pushing content and pushing duty ratio corresponding to the pushing content according to the category weight, the style weight, the characteristic style, the characteristic category and a preset recommendation method.
9. An electronic device comprising a memory and a processor, wherein the memory has stored thereon a computer program, and wherein the processor implements the method of any of claims 1-7 when the program is executed.
10. A computer readable storage medium, characterized in that a computer program is stored thereon, which program, when being executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310282824.1A CN116029798B (en) | 2023-03-22 | 2023-03-22 | User demand recommendation method, system, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310282824.1A CN116029798B (en) | 2023-03-22 | 2023-03-22 | User demand recommendation method, system, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116029798A true CN116029798A (en) | 2023-04-28 |
| CN116029798B CN116029798B (en) | 2023-07-07 |
Family
ID=86072724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310282824.1A Active CN116029798B (en) | 2023-03-22 | 2023-03-22 | User demand recommendation method, system, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116029798B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180336281A1 (en) * | 2017-05-17 | 2018-11-22 | Adobe Systems Incorporated | Creator Aware and Diverse Recommendations of Digital Content |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN110648186A (en) * | 2018-06-26 | 2020-01-03 | 杭州海康威视数字技术股份有限公司 | Data analysis method, device, equipment and computer readable storage medium |
| CN111291217A (en) * | 2020-03-04 | 2020-06-16 | 北京奇艺世纪科技有限公司 | Content recommendation method and device, electronic equipment and computer readable medium |
| CN112085549A (en) * | 2019-06-14 | 2020-12-15 | 上海逸宅网络科技有限公司 | Commodity recommendation method for E-commerce platform based on data processing technology |
| CN113411379A (en) * | 2021-05-31 | 2021-09-17 | 《人民论坛》杂志社 | Information pushing method and device based on browsing habit and electronic equipment |
| CN113450178A (en) * | 2021-05-13 | 2021-09-28 | 孙昊盛 | Internet-based e-commerce accurate marketing system |
| CN115345656A (en) * | 2022-08-10 | 2022-11-15 | 江西省众灿互动科技股份有限公司 | Behavior data analysis method for refined marketing |
| CN115455280A (en) * | 2022-08-19 | 2022-12-09 | 青岛聚看云科技有限公司 | Recommendation list determining method and server |
-
2023
- 2023-03-22 CN CN202310282824.1A patent/CN116029798B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180336281A1 (en) * | 2017-05-17 | 2018-11-22 | Adobe Systems Incorporated | Creator Aware and Diverse Recommendations of Digital Content |
| CN110648186A (en) * | 2018-06-26 | 2020-01-03 | 杭州海康威视数字技术股份有限公司 | Data analysis method, device, equipment and computer readable storage medium |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN112085549A (en) * | 2019-06-14 | 2020-12-15 | 上海逸宅网络科技有限公司 | Commodity recommendation method for E-commerce platform based on data processing technology |
| CN111291217A (en) * | 2020-03-04 | 2020-06-16 | 北京奇艺世纪科技有限公司 | Content recommendation method and device, electronic equipment and computer readable medium |
| CN113450178A (en) * | 2021-05-13 | 2021-09-28 | 孙昊盛 | Internet-based e-commerce accurate marketing system |
| CN113411379A (en) * | 2021-05-31 | 2021-09-17 | 《人民论坛》杂志社 | Information pushing method and device based on browsing habit and electronic equipment |
| CN115345656A (en) * | 2022-08-10 | 2022-11-15 | 江西省众灿互动科技股份有限公司 | Behavior data analysis method for refined marketing |
| CN115455280A (en) * | 2022-08-19 | 2022-12-09 | 青岛聚看云科技有限公司 | Recommendation list determining method and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116029798B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080413A (en) | E-commerce platform commodity recommendation method and device, server and storage medium | |
| WO2019037391A1 (en) | Method and apparatus for predicting customer purchase intention, and electronic device and medium | |
| CN107679217B (en) | Associated content extraction method and device based on data mining | |
| CN108777701B (en) | Method and device for determining information audience | |
| CN110196904B (en) | Method and device for acquiring recommendation information and computer readable storage medium | |
| CN112184302A (en) | Product recommendation method and device, rule engine and storage medium | |
| CN108960923A (en) | A kind of method, apparatus and computer storage medium of price | |
| CN104572775A (en) | Advertisement classification method, device and server | |
| CN112966486A (en) | Intelligent engineering quantity list generation method and device, terminal and storage medium | |
| JP6551957B1 (en) | Matching support apparatus, matching support method and program | |
| CN116029798B (en) | User demand recommendation method, system, electronic equipment and readable storage medium | |
| CN113778979A (en) | Method and device for determining live broadcast click rate | |
| JPH09167152A (en) | Interactive model preparing method | |
| CN117132326A (en) | Advertisement pushing method and device, electronic equipment and storage medium | |
| CN115936764A (en) | Product promotion method and device | |
| CN110428286A (en) | A kind of Dynamic Pricing System and method based on consumption market big data resource | |
| CN111445263A (en) | Information processing method, device, computer system and medium | |
| CN112434140B (en) | Reply information processing method and system | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| CN114065725A (en) | Purchasing big data management system | |
| CN114066177A (en) | Supplier scoring method and storage medium | |
| CN113407827A (en) | Information recommendation method, device, equipment and medium based on user value classification | |
| CN115934775A (en) | Grouping rule recommendation method and device, electronic equipment and readable storage medium | |
| CN111738790A (en) | Business pushing method and pushing system | |
| CN111815204A (en) | Risk assessment method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A user requirement recommendation method, system, electronic device, and readable storage medium Effective date of registration: 20230829 Granted publication date: 20230707 Pledgee: Bank of Nanjing Limited by Share Ltd. Beijing branch Pledgor: Beijing Xinfadi Agricultural Products Network Distribution Center Co.,Ltd. Registration number: Y2023110000367 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |