CN110634040A - Information recommendation method and device - Google Patents
Information recommendation method and device Download PDFInfo
- Publication number
- CN110634040A CN110634040A CN201810653926.9A CN201810653926A CN110634040A CN 110634040 A CN110634040 A CN 110634040A CN 201810653926 A CN201810653926 A CN 201810653926A CN 110634040 A CN110634040 A CN 110634040A
- Authority
- CN
- China
- Prior art keywords
- feature
- user
- commodities
- information
- commodity
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an information recommendation method and device, and relates to the technical field of computers. Wherein, the method comprises the following steps: inquiring a characteristic database according to the user identification to obtain characteristic data of the corresponding user; determining the weight proportion of each feature in the feature data of the user; according to the weight ratio, acquiring information of commodities with corresponding quantity ratios from the commodity list associated with each feature, and then generating a commodity recommendation list according to the information of the commodities; the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page. Through the steps, the commodity information can be accurately recommended for different users, the recommendation conversion rate is improved, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an information recommendation method and device.
Background
In the prior art, there are mainly the following commodity recommendation methods: firstly, recommending commodities purchased or browsed by a user to the user; secondly, recommending commodities related to merchant activities (such as recent second kills held by merchants, sales promotion, new product online activities and the like) to users; thirdly, recommending commodities with particularly good recent sales conditions to users; and fourthly, recommending the commodities matched with the consumption capacity of the user to the user.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: although the existing commodity recommendation modes can provide shopping choices for a large number of users to different degrees, the existing commodity recommendation modes cannot meet the real requirements of the users, cannot carry out accurate recommendation aiming at different users, and are low in recommendation conversion rate and poor in user experience.
Disclosure of Invention
In view of this, the invention provides an information recommendation method and apparatus, which can perform accurate recommendation of information of commodities for different users, improve recommendation conversion rate, and improve user experience.
To achieve the above object, according to one aspect of the present invention, an information recommendation method is provided.
The information recommendation method comprises the following steps: inquiring a characteristic database according to the user identification to obtain characteristic data of the corresponding user; determining the weight proportion of each feature in the feature data of the user; according to the weight ratio, acquiring information of commodities with corresponding quantity ratios from the commodity list associated with each feature, and then generating a commodity recommendation list according to the information of the commodities; the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page.
Optionally, the feature data comprises: feature identification, a feature value of each feature; the method further comprises the following steps: determining the weight proportion of each feature in the feature data of the user according to the following formula:
wherein, CWViTo representWeight ratio, CV, of ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
Optionally, the method further comprises: judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not; if yes, directly executing the step of generating a commodity recommendation list according to the information of the commodities; if the total information of the obtained commodities is larger than a specific numerical value, deleting the information of the commodities according to the proportion of the specific numerical value in the total information of the commodities, and then executing the step of generating a commodity recommendation list according to the information of the commodities; and if the total number of the acquired information of the commodities is less than a specific numerical value, supplementing the information of the commodities, and then executing the step of generating a commodity recommendation list according to the information of the commodities.
Optionally, the method further comprises: before the step of judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not is executed, the acquired information of the commodities is subjected to a deduplication operation.
Optionally, the method further comprises: after a user operates a commodity on a client page or a website page, all characteristics related to the commodity in the characteristic data of the user are updated.
Optionally, the step of updating all the features associated with the commodity in the feature data of the user includes: acquiring characteristics associated with the commodity, and then querying a characteristic database according to the characteristics associated with the commodity; and if the feature associated with the commodity exists in the feature data of the user, updating the feature value of the feature according to the operation type of the user, and if the feature associated with the commodity does not exist in the feature data of the user, adding the feature to the feature data of the user and updating the feature value of the feature according to the operation type of the user.
Optionally, the operation type of the user includes at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest.
To achieve the above object, according to another aspect of the present invention, an information recommendation apparatus is provided.
The information recommendation device of the present invention includes: the query module is used for querying the feature database according to the user identification so as to obtain feature data of the corresponding user; the determining module is used for determining the weight proportion of each feature in the feature data of the user; the acquisition module is used for acquiring the information of the commodities with corresponding quantity proportion from the commodity list associated with each feature according to the weight proportion; the generation module is used for generating a commodity recommendation list according to the information of the commodities; the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page.
Optionally, the feature data comprises: feature identification, a feature value of each feature; the determination module determines the weight proportion of each feature in the feature data of the user according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
Optionally, the apparatus further comprises: the judging module is used for judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not; if yes, the generation module directly executes the operation of generating the commodity recommendation list according to the information of the commodities; if the total information of the obtained commodities is larger than a specific numerical value, the generation module is further used for deleting the information of the commodities according to the proportion of the specific numerical value in the total information of the commodities, and then executing the operation of generating a commodity recommendation list according to the information of the commodities; if the total number of the acquired information of the commodities is less than a specific numerical value, the generation module is further used for supplementing the information of the commodities and then executing the operation of generating the commodity recommendation list according to the information of the commodities.
Optionally, the apparatus further comprises: and the duplication eliminating module is used for carrying out duplication eliminating operation on the acquired information of the commodity before the judging module carries out the operation of judging whether the total number of the acquired information of the commodity is equal to a specific numerical value or not.
Optionally, the apparatus further comprises: and the updating module is used for updating all characteristics related to the commodity in the characteristic data of the user after the user operates the commodity on the client page or the website page.
Optionally, the updating, by the updating module, all the features associated with the commodity in the feature data of the user includes: the updating module acquires the characteristics associated with the commodity and then queries a characteristic database according to the characteristics associated with the commodity; if the feature associated with the commodity exists in the feature data of the user, the updating module updates the feature value of the feature according to the operation type of the user, and if the feature associated with the commodity does not exist in the feature data of the user, the updating module adds the feature to the feature data of the user and updates the feature value of the feature according to the operation type of the user.
To achieve the above object, according to still another aspect of the present invention, there is provided an electronic apparatus.
The electronic device of the present invention includes: one or more processors; and storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the information recommendation method of the present invention.
To achieve the above object, according to still another aspect of the present invention, there is provided a computer-readable medium.
The computer-readable medium of the present invention has stored thereon a computer program which, when executed by a processor, implements the information recommendation method of the present invention.
One embodiment of the above invention has the following advantages or benefits: the method has the advantages that the characteristic data of the user are constructed in advance according to the characteristics associated with the commodities operated by the user on the client page and/or the website page, so that the commodities can be associated with the user, and the real requirements of the user can be better reflected; further, the characteristic database is queried according to the user identification to obtain the characteristic data of the corresponding user, the information of the commodities with the corresponding quantity proportion is obtained from the commodity list associated with each characteristic according to the weight proportion of each characteristic in the characteristic data, then the commodity recommendation list is generated according to the information of the commodities, and the like, so that the information of the commodities can be accurately recommended for different users, the recommendation conversion rate is improved, and the user experience is improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of an information recommendation method according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of the main steps of an information recommendation method according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of the main blocks of an information recommendation device according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of the main modules of an information recommendation device according to another embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
FIG. 6 is a schematic block diagram of a computer system suitable for use with the electronic device to implement an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic diagram of main steps of an information recommendation method according to an embodiment of the present invention. As shown in fig. 1, the information recommendation method according to the embodiment of the present invention includes:
and S101, querying a feature database according to the user identification to obtain feature data of the corresponding user.
The characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page. The characteristic data of the user may include: user identification, feature value of each feature.
Specifically, the user's actions on the merchandise include, but are not limited to, at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. For example, assuming that a user triggers an operation of "view a certain cleaner" and an operation of "share a certain woman's clothing" on a client page, features "fashion", "science and technology" associated with the cleaner and features "popular", "fairy model" associated with the woman's clothing are taken as features of the user.
In the embodiment of the invention, the commodity is associated with the user by endowing the commodity with the visual human characteristic and constructing the user characteristic data through the characteristic associated with the commodity, so that accurate commodity recommendation can be performed according to the user characteristic data subsequently.
And S102, determining the weight ratio of each feature in the feature data of the user.
Specifically, in this step, the weight proportion of each feature in the feature data of the user can be determined according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
And S103, acquiring information of commodities with corresponding quantity proportions from the commodity list associated with each feature according to the weight proportion, and then generating a commodity recommendation list according to the information of the commodities.
For example, suppose that the feature data of a certain user has 5 features in total: the weight ratio of the characteristics of fashion, science and technology, cleanness, fairy home and patrinian feeling is respectively as follows: 50%, 30%, 10%, 7%, 3%, information on commodities whose number is 50% of the total number of the table commodities is acquired from the commodity list associated with "fashion", information on commodities whose number is 30% of the total number of the table commodities is acquired from the commodity list associated with "science and technology", information on commodities whose number is 10% of the total number of the table commodities is acquired from the commodity list associated with "clean", information on commodities whose number is 7% of the total number of the table commodities is acquired from the commodity list associated with "fairy home", and information on commodities whose number is 3% of the total number of the table commodities is acquired from the commodity list associated with "patriotic feeling". In specific implementation, if the number of the commodities determined according to the weight ratio is a decimal, rounding-up or rounding-down can be performed.
In the embodiment of the invention, the information of the commodities can be accurately recommended for different users through the steps, so that the recommendation conversion rate is improved, and the user experience is improved.
Fig. 2 is a schematic diagram of main steps of an information recommendation method according to another embodiment of the present invention. As shown in fig. 2, the information recommendation method according to the embodiment of the present invention includes:
step S201, inquiring the characteristic database according to the user identification to obtain the characteristic data of the corresponding user.
The characteristic data is constructed according to the characteristics related to the commodities operated on the client page by the user. The characteristic data of the user may include: user identification, feature value of each feature, feature name, and last operation time of the feature. For example, the characteristic data of a certain user is shown in table 1:
TABLE 1
| user_ID | feature_ID | feature_name | CV | T_L |
| Zhang three | 10000001 | Fashion style | 5 | 2018.03.30 |
| Zhang three | 10000005 | Science and technology | 8 | 2018.05.20 |
| Zhang three | 10000031 | Clean and clean | 3 | 2018.05.20 |
| Zhang three | 10000052 | Patriotic feelings | 10 | 2018.06.01 |
In table 1, "user _ ID" represents a user identification, "feature _ ID" represents a feature identification, "feature _ name" represents a feature name, "CV" represents a feature value of each feature, and "T _ L" represents a last operation time of a feature, or may be understood as a last operation time of a user on a client page and/or a website page for a commodity associated with the feature.
Specifically, the user's actions on the merchandise include, but are not limited to, at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. For example, if a user triggers an operation of "view a certain cleaner" and an operation of "share a certain woman's clothing" on a client page, features "fashion", "science" associated with the cleaner and features "popular", "fairy model" associated with the woman's clothing can be used as features of the user. Further, the method of the embodiment of the present invention may further include: the associated features are configured in advance for the items on the client page. In specific implementation, the operator can configure the associated features for each commodity to obtain the feature set of the commodity. For example, the operator may configure a certain type of purifier with the following features: "clean", "science and technology", and "fashion". After the configuration is completed, the feature data of the user can be constructed according to the features associated with the commodities operated by the user on the client page.
In the embodiment of the invention, the commodity is associated with the user by endowing the commodity with the visual human characteristic and constructing the user characteristic data through the characteristic associated with the commodity, so that accurate commodity recommendation can be performed according to the user characteristic data subsequently.
Step S202, calculating the weight ratio of each feature in the feature data of the user.
Specifically, in this step, the weight proportion of each feature in the feature data of the user can be determined according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
And S203, acquiring information of the commodities with corresponding quantity proportions from the commodity list associated with each feature according to the weight proportion.
For example, suppose that the feature data of a certain user has 5 features in total: the weight ratio of the characteristics of fashion, science and technology, cleanness, fairy home and patrinian feeling is respectively as follows: 50%, 30%, 10%, 7%, 3%, information on commodities whose number is 50% of the total number of the table commodities is acquired from the commodity list associated with "fashion", information on commodities whose number is 30% of the total number of the table commodities is acquired from the commodity list associated with "science and technology", information on commodities whose number is 10% of the total number of the table commodities is acquired from the commodity list associated with "clean", information on commodities whose number is 7% of the total number of the table commodities is acquired from the commodity list associated with "fairy home", and information on commodities whose number is 3% of the total number of the table commodities is acquired from the commodity list associated with "patriotic feeling". In specific implementation, if the number of the commodities determined according to the weight ratio is a decimal, rounding-up or rounding-down can be performed.
And step S204, carrying out duplication elimination operation on the acquired information of the commodity.
Since there is a many-to-many relationship between the goods and the features, that is, one feature may correspond to a plurality of goods and one goods may correspond to a plurality of features, the goods obtained according to step S203 may be repeated. For example, the items (or "information on items") obtained from the item list associated with the item by the feature of "fashion" are "brand a cleaner" and "brand B suit", and the items obtained by the feature of "technology" are "brand a cleaner" and "brand C phone". Although four pieces of merchandise were acquired, since the "brand a cleaner" was the merchandise repeatedly acquired, the following three pieces of merchandise (or "information on merchandise") were obtained through the past repeat operation: "brand a purifiers", "brand B women's clothing" and "brand C cell phone".
Step S205, determining whether the total number of the acquired information of the commodity is equal to a specific value. If yes, go to step S208; if the total information of the obtained commodities is larger than the specific numerical value, executing a step S206; if the total number of the acquired information of the product is smaller than the specific value, step S207 is executed.
Wherein, the specific value can be flexibly set according to actual requirements. For example, the specific value is set to 10, 20 or other values. If the total number of the commodities after the deduplication processing is equal to the specific value, step S208 may be executed, if the total number of the commodities after the deduplication processing is greater than the specific value, step S206 may be executed, and if the total number of the commodities after the deduplication processing is less than the specific value, step S207 may be executed.
And S206, deleting the information of the commodity according to the proportion of the specific numerical value in the total information of the commodity. After step S206, step S208 is performed.
Specifically, in this step, the number of commodities (or information called "commodities") obtained from the commodity list associated with each feature may be redetermined based on the ratio of the specific numerical value in the total number of information of the commodities, which ratio may be represented by "WV 1", to delete the obtained commodities. In an alternative example, the weighted ratio of each feature of the user obtained in step S202 may be multiplied by WV1, and then the number of items to be obtained from the item list associated therewith may be determined according to the updated weighted ratio of each feature. For example, assuming that the total number of commodities after the weight removal processing is 100 and the specific value is 20, WV1 is 0.2, assuming that the weight ratios of the respective features previously determined in step S202 are 50%, 30%, 10%, 7%, 3%, the updated weight ratios are 10%, 6%, 2%, 1.4%, 0.6%,
and step S207, supplementing the information of the commodity. After step S207, step S208 is executed.
In this step, if the number of commodities acquired according to step S203 is too small, the commodities may be supplemented according to the activity of the merchant, the sales situation of the commodities, or the like.
And step S208, generating a commodity recommendation list according to the commodity information.
In this step, the commodity information may be sorted in combination with other strategies, and then the sorted commodity information is used as a commodity recommendation list. For example, the items are sorted according to the recent sales quantity of each item from high to low, or the items are sorted according to the promotion degree from high to low, and so on.
And S209, outputting the commodity recommendation list to a client.
Further, in addition to the above steps, the method of an embodiment of the present invention may further include the steps of: after a user operates a commodity on a client page or a website page, all characteristics related to the commodity in the characteristic data of the user are updated.
In an optional embodiment, the step of updating all the characteristics associated with the commodity in the characteristic data of the user includes: acquiring characteristics associated with the commodity, and then querying a characteristic database according to the characteristics associated with the commodity; and if the feature associated with the commodity exists in the feature data of the user, updating the feature value of the feature according to the operation type of the user, and if the feature associated with the commodity does not exist in the feature data of the user, adding the feature to the feature data of the user and updating the feature value of the feature according to the operation type of the user.
Wherein the operation type of the user includes but is not limited to at least one of the following: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. In specific implementation, different weights can be set for different operation types, so that after a user performs a certain operation on a commodity, the weight of the operation type is superposed on an original characteristic value of a characteristic associated with the commodity, and the characteristic value is updated. Illustratively, the weights for the various operation types are shown in table 2:
TABLE 2
For example, if the features associated with a certain type of scrubber searched by a user are "fashion", "clean", and "technology", the user may first query the feature data for the three features. If the feature data of the user has the three features, respectively adding 3 to the feature values of the three features (i.e. superposing the searched weight values on the feature values); if one or more of the three features are not present in the feature data of the user, the absent features may be added to the feature data of the user, and 3 may be added to the feature values of the three features, respectively.
It should be noted that table 2 is an exemplary illustration of weight setting for operation types. In specific implementation, the weight of each operation type and the required operation type can be flexibly adjusted according to specific conditions.
In addition, when implemented, the method of the embodiment of the present invention may further include the steps of: when the features of the user in the feature database are excessive, the features of the user can be deleted according to the following strategies: firstly, deleting the features with feature values smaller than a preset threshold (such as 0 or 1); second, features whose feature values are not updated for a certain time (e.g., three years, two years, or other optional time period) are deleted.
In the embodiment of the invention, the information of the commodities can be accurately recommended for different users through the steps, so that the recommendation conversion rate is improved, and the user experience is improved. Compared with the traditional recommendation strategy, the embodiment of the invention integrates the characteristics of 'people' in the commodities, optimizes the previously recommended similar products into the recommended products according with the characteristics of the user, improves the shopping experience of the user and increases the viscosity of the user.
Fig. 3 is a schematic diagram of main blocks of an information recommendation apparatus according to an embodiment of the present invention. As shown in fig. 3, an information recommendation apparatus 300 according to an embodiment of the present invention includes: the device comprises a query module 301, a determination module 302, an acquisition module 303 and a generation module 304.
The query module 301 is configured to query the feature database according to the user identifier to obtain feature data of the corresponding user.
The characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page. The characteristic data of the user may include: user identification, feature value of each feature.
Specifically, the user's actions on the merchandise include, but are not limited to, at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. For example, assuming that a user triggers an operation of "view a certain cleaner" and an operation of "share a certain woman's clothing" on a client page, features "fashion", "science and technology" associated with the cleaner and features "popular", "fairy model" associated with the woman's clothing are taken as features of the user.
In the embodiment of the invention, the commodity is associated with the user by endowing the commodity with the visual human characteristic and constructing the user characteristic data through the characteristic associated with the commodity, so that accurate commodity recommendation can be performed according to the user characteristic data subsequently.
A determining module 302, configured to determine a weight fraction of each feature in the feature data of the user.
Specifically, the determining module 302 may determine the weight proportion of each feature in the feature data of the user according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
An obtaining module 303, configured to obtain information of the commodities in a corresponding quantity ratio from the commodity list associated with each feature according to the weight ratio.
For example, suppose that the feature data of a certain user has 5 features in total: the weight ratio of the characteristics of fashion, science and technology, cleanness, fairy home and patrinian feeling is respectively as follows: 50%, 30%, 10%, 7%, 3%, information on commodities whose number is 50% of the total number of the table commodities is acquired from the commodity list associated with "fashion", information on commodities whose number is 30% of the total number of the table commodities is acquired from the commodity list associated with "science and technology", information on commodities whose number is 10% of the total number of the table commodities is acquired from the commodity list associated with "clean", information on commodities whose number is 7% of the total number of the table commodities is acquired from the commodity list associated with "fairy home", and information on commodities whose number is 3% of the total number of the table commodities is acquired from the commodity list associated with "patriotic feeling". In specific implementation, if the number of the commodities determined according to the weight ratio is a decimal, rounding-up or rounding-down can be performed.
The generating module 304 is configured to generate a commodity recommendation list according to the information of the commodity.
In the embodiment of the invention, the device can be used for accurately recommending the information of the commodities for different users, so that the recommendation conversion rate is improved, and the user experience is improved.
Fig. 4 is a schematic diagram of main blocks of an information recommendation apparatus according to another embodiment of the present invention. As shown in fig. 4, an information recommendation apparatus 400 according to an embodiment of the present invention includes: the device comprises a query module 401, a determination module 402, an acquisition module 403, a deduplication module 404, a judgment module 405, a generation module 406 and an update module 407.
The query module 401 is configured to query the feature database according to the user identifier to obtain feature data of the corresponding user.
The characteristic data is constructed according to the characteristics related to the commodities operated on the client page by the user. The characteristic data of the user may include: user identification, feature value of each feature, feature name, and last operation time of the feature.
Specifically, the user's actions on the merchandise include, but are not limited to, at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. For example, if a user triggers an operation of "view a certain cleaner" and an operation of "share a certain woman's clothing" on a client page, features "fashion", "science" associated with the cleaner and features "popular", "fairy model" associated with the woman's clothing can be used as features of the user. Further, the method of the embodiment of the present invention may further include: the associated features are configured in advance for the items on the client page. In specific implementation, the operator can configure the associated features for each commodity to obtain the feature set of the commodity. For example, the operator may configure a certain type of purifier with the following features: "clean", "science and technology", and "fashion". After the configuration is completed, the feature data of the user can be constructed according to the features associated with the commodities operated by the user on the client page.
In the embodiment of the invention, the commodity is associated with the user by endowing the commodity with the visual human characteristic and constructing the user characteristic data through the characteristic associated with the commodity, so that accurate commodity recommendation can be performed according to the user characteristic data subsequently.
A determining module 402, configured to determine a weight fraction of each feature in the feature data of the user.
Specifically, the determining module 402 may calculate the weight ratio of each feature in the feature data of the user according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
An obtaining module 403, configured to obtain information of the commodities in a corresponding quantity ratio from the commodity list associated with each feature according to the weight ratio.
For example, suppose that the feature data of a certain user has 5 features in total: the weight ratio of the characteristics of fashion, science and technology, cleanness, fairy home and patrinian feeling is respectively as follows: 50%, 30%, 10%, 7%, 3%, information on commodities whose number is 50% of the total number of the table commodities is acquired from the commodity list associated with "fashion", information on commodities whose number is 30% of the total number of the table commodities is acquired from the commodity list associated with "science and technology", information on commodities whose number is 10% of the total number of the table commodities is acquired from the commodity list associated with "clean", information on commodities whose number is 7% of the total number of the table commodities is acquired from the commodity list associated with "fairy home", and information on commodities whose number is 3% of the total number of the table commodities is acquired from the commodity list associated with "patriotic feeling". In specific implementation, if the number of the commodities determined according to the weight ratio is a decimal, rounding-up or rounding-down can be performed.
And a duplicate removal module 404, configured to perform a duplicate removal operation on the obtained information of the commodity.
For example, the items (or "information on items") obtained from the item list associated with the item by the feature of "fashion" are "brand a cleaner" and "brand B suit", and the items obtained by the feature of "technology" are "brand a cleaner" and "brand C phone". Although four items are acquired, since the "brand a purifier" is a repeatedly acquired item, the following three items (or "information of the item") are obtained through the deduplication operation of the deduplication module 404: "brand a purifiers", "brand B women's clothing" and "brand C cell phone".
The determining module 405 is configured to determine whether the total number of the acquired information of the commodity is equal to a specific value. Wherein, the specific value can be flexibly set according to actual requirements. For example, the specific value is set to 10, 20 or other values.
A generating module 406, configured to generate an operation of a commodity recommendation list according to the information of the commodity when the total information of the obtained commodity is equal to a specific numerical value; the generating module 406 is further configured to, when the total information of the obtained goods is greater than a specific value, delete the information of the goods according to a ratio of the specific value in the total information of the goods, and then generate a goods recommendation list according to the information of the goods; the generating module 406 is further configured to supplement the information of the commodity when the total number of the obtained information of the commodity is smaller than a specific value, and then generate a commodity recommendation list according to the information of the commodity.
Specifically, when the total information of the acquired commodities is larger than a specific value, the generation module 406 may redetermine the number of commodities (or information called "commodities") acquired from the commodity list associated with each feature according to a proportion of the specific value in the total information of the commodities (the proportion may be represented by "WV 1") to delete the acquired commodities. In an alternative example, the weighted ratio of each feature of the user may be multiplied by WV1, and then the quantity of items to be obtained from the item list associated therewith may be determined according to the updated weighted ratio of each feature. For example, assuming that the total number of commodities after the deduplication processing is 100 and the specific value is 20, WV1 is 0.2, and assuming that the weight ratio of each feature specified previously is 50%, 30%, 10%, 7%, 3%, the updated weight ratio is 10%, 6%, 2%, 1.4%, 0.6%. In addition, when the total number of the acquired information of the commodity is less than a specific value, the generation module 406 may also supplement the commodity according to the activity of the merchant or the sales condition of the commodity.
The updating module 407 is configured to update all features associated with the commodity in the feature data of the user after the user operates the commodity on the client page or the website page.
In an optional embodiment, the updating module 407 updates all the characteristics associated with the product in the characteristic data of the user includes: the update module 407 obtains the characteristics associated with the good, and then queries a characteristic database according to the characteristics associated with the good; if the feature associated with the product exists in the feature data of the user, the updating module 407 updates the feature value of the feature according to the operation type of the user, and if the feature associated with the product does not exist in the feature data of the user, the updating module 407 adds the feature to the feature data of the user and updates the feature value of the feature according to the operation type of the user.
Wherein the operation type of the user includes but is not limited to at least one of the following: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest. In specific implementation, different weights can be set for different operation types, so that after a user performs a certain operation on a commodity, the weight of the operation type is superposed on an original characteristic value of a characteristic associated with the commodity, and the characteristic value is updated.
For example, if the features associated with a certain type of scrubber searched by a user are "fashion", "clean", and "technology", the user may first query the feature data for the three features. If the feature data of the user has the three features, respectively adding 3 to the feature values of the three features (assuming that the weight value of the search is 3); if one or more of the three features are not present in the feature data of the user, the absent features may be added to the feature data of the user, and 3 may be added to the feature values of the three features, respectively.
Further, the update module 407 may be further configured to: when the characteristics of the user in the characteristic database are excessive, the characteristics of the user are deleted. For example, it may be pruned according to the following policy: firstly, deleting the features with feature values smaller than a preset threshold (such as 0 or 1); second, features whose feature values are not updated for a certain time (e.g., three years, two years, or other optional time period) are deleted.
In the embodiment of the invention, the device can be used for accurately recommending the information of the commodities for different users, so that the recommendation conversion rate is improved, and the user experience is improved. Compared with the traditional recommendation strategy, the embodiment of the invention integrates the characteristics of 'people' in the commodities, optimizes the previously recommended similar products into the recommended products according with the characteristics of the user, improves the shopping experience of the user and increases the viscosity of the user.
Fig. 5 shows an exemplary system architecture 500 to which the information recommendation method or the information recommendation apparatus according to the embodiment of the present invention can be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have various communication client applications installed thereon, such as a shopping application, a web browser application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server that provides various services, such as a background management server that supports shopping websites browsed by users using the terminal devices 501, 502, 503. The background management server can generate a commodity recommendation list by querying the feature database according to the user identification and the like, and output the commodity recommendation list to the terminal device.
The information recommendation method provided by the present invention is generally executed by the server 505, and accordingly, the information recommendation apparatus is generally provided in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
FIG. 6 illustrates a schematic block diagram of a computer system 600 suitable for use with the electronic device to implement an embodiment of the invention. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination 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 present invention, 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 invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. 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 flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a query module, a determination module, and a generation module. Where the names of these modules do not in some cases constitute a limitation on the module itself, for example, a query module may also be described as a "module that queries a database of features according to a user identification".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to perform the following: inquiring a characteristic database according to the user identification to obtain characteristic data of the corresponding user; determining the weight proportion of each feature in the feature data of the user; according to the weight ratio, acquiring information of commodities with corresponding quantity ratios from the commodity list associated with each feature, and then generating a commodity recommendation list according to the information of the commodities; the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (15)
1. An information recommendation method, characterized in that the method comprises:
inquiring a characteristic database according to the user identification to obtain characteristic data of the corresponding user;
determining the weight proportion of each feature in the feature data of the user;
according to the weight ratio, acquiring information of commodities with corresponding quantity ratios from the commodity list associated with each feature, and then generating a commodity recommendation list according to the information of the commodities;
the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page.
2. The method of claim 1, wherein the characterization data comprises: feature identification, a feature value of each feature; the method further comprises the following steps: determining the weight proportion of each feature in the feature data of the user according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
3. The method of claim 1, further comprising:
judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not; if yes, directly executing the step of generating a commodity recommendation list according to the information of the commodities; if the total information of the obtained commodities is larger than a specific numerical value, deleting the information of the commodities according to the proportion of the specific numerical value in the total information of the commodities, and then executing the step of generating a commodity recommendation list according to the information of the commodities; and if the total number of the acquired information of the commodities is less than a specific numerical value, supplementing the information of the commodities, and then executing the step of generating a commodity recommendation list according to the information of the commodities.
4. The method of claim 3, further comprising:
before the step of judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not is executed, the acquired information of the commodities is subjected to a deduplication operation.
5. The method of claim 1, further comprising:
after a user operates a commodity on a client page or a website page, all characteristics related to the commodity in the characteristic data of the user are updated.
6. The method of claim 5, wherein the step of updating all of the characteristics associated with the item in the user's characteristic data comprises:
acquiring characteristics associated with the commodity, and then querying a characteristic database according to the characteristics associated with the commodity; and if the feature associated with the commodity exists in the feature data of the user, updating the feature value of the feature according to the operation type of the user, and if the feature associated with the commodity does not exist in the feature data of the user, adding the feature to the feature data of the user and updating the feature value of the feature according to the operation type of the user.
7. The method of claim 1, wherein the type of operation of the user comprises at least one of: searching, collecting, sharing, viewing, car purchasing, repurchasing, goods returning and exchanging, and no interest.
8. An information recommendation apparatus, characterized in that the apparatus comprises:
the query module is used for querying the feature database according to the user identification so as to obtain feature data of the corresponding user;
the determining module is used for determining the weight proportion of each feature in the feature data of the user;
the acquisition module is used for acquiring the information of the commodities with corresponding quantity proportion from the commodity list associated with each feature according to the weight proportion;
the generation module is used for generating a commodity recommendation list according to the information of the commodities;
the characteristic data is constructed according to the characteristics related to the commodities operated by the user on the client page and/or the website page.
9. The apparatus of claim 8, wherein the characterization data comprises: feature identification, a feature value of each feature; the determination module determines the weight proportion of each feature in the feature data of the user according to the following formula:
wherein, CWViWeight ratio, CV, representing the ith featureiA feature value representing the ith feature,
the sum of the feature values representing all features of the user, and n represents the total number of features of the user.
10. The apparatus of claim 8, further comprising:
the judging module is used for judging whether the total number of the acquired information of the commodities is equal to a specific numerical value or not; if yes, the generation module directly executes the operation of generating the commodity recommendation list according to the information of the commodities; if the total information of the obtained commodities is larger than a specific numerical value, the generation module is further used for deleting the information of the commodities according to the proportion of the specific numerical value in the total information of the commodities, and then executing the operation of generating a commodity recommendation list according to the information of the commodities; if the total number of the acquired information of the commodities is less than a specific numerical value, the generation module is further used for supplementing the information of the commodities and then executing the operation of generating the commodity recommendation list according to the information of the commodities.
11. The apparatus of claim 10, further comprising:
and the duplication eliminating module is used for carrying out duplication eliminating operation on the acquired information of the commodity before the judging module carries out the operation of judging whether the total number of the acquired information of the commodity is equal to a specific numerical value or not.
12. The apparatus of claim 8, further comprising:
and the updating module is used for updating all characteristics related to the commodity in the characteristic data of the user after the user operates the commodity on the client page or the website page.
13. The apparatus of claim 12, wherein the update module updating all of the features associated with the item in the feature data of the user comprises:
the updating module acquires the characteristics associated with the commodity and then queries a characteristic database according to the characteristics associated with the commodity; if the feature associated with the commodity exists in the feature data of the user, the updating module updates the feature value of the feature according to the operation type of the user, and if the feature associated with the commodity does not exist in the feature data of the user, the updating module adds the feature to the feature data of the user and updates the feature value of the feature according to the operation type of the user.
14. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
15. A computer-readable medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810653926.9A CN110634040A (en) | 2018-06-22 | 2018-06-22 | Information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810653926.9A CN110634040A (en) | 2018-06-22 | 2018-06-22 | Information recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110634040A true CN110634040A (en) | 2019-12-31 |
Family
ID=68967939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810653926.9A Pending CN110634040A (en) | 2018-06-22 | 2018-06-22 | Information recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110634040A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345695A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Commodity recommendation method and device |
| CN105335365A (en) * | 2014-05-30 | 2016-02-17 | 小米科技有限责任公司 | Method and apparatus for placing order, server and terminal |
| CN107045700A (en) * | 2017-04-13 | 2017-08-15 | 中国联合网络通信集团有限公司 | Product method for pushing and device based on streaming user behavioural analysis |
| CN108022152A (en) * | 2017-11-30 | 2018-05-11 | 北京长城华冠汽车技术开发有限公司 | The automatic commending system of user's commodity and recommendation method based on image recognition |
| CN108109056A (en) * | 2018-01-10 | 2018-06-01 | 北京思特奇信息技术股份有限公司 | A kind of recommendation method and system of commodity |
-
2018
- 2018-06-22 CN CN201810653926.9A patent/CN110634040A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345695A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Commodity recommendation method and device |
| CN105335365A (en) * | 2014-05-30 | 2016-02-17 | 小米科技有限责任公司 | Method and apparatus for placing order, server and terminal |
| CN107045700A (en) * | 2017-04-13 | 2017-08-15 | 中国联合网络通信集团有限公司 | Product method for pushing and device based on streaming user behavioural analysis |
| CN108022152A (en) * | 2017-11-30 | 2018-05-11 | 北京长城华冠汽车技术开发有限公司 | The automatic commending system of user's commodity and recommendation method based on image recognition |
| CN108109056A (en) * | 2018-01-10 | 2018-06-01 | 北京思特奇信息技术股份有限公司 | A kind of recommendation method and system of commodity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363604B (en) | Page generation method and device | |
| CN109711917B (en) | Information pushing method and device | |
| CN107291779B (en) | Cache data management method and device | |
| CN110084658B (en) | Method and device for matching articles | |
| CN107908662B (en) | Method and device for realizing search system | |
| CN112884405A (en) | Inquiry system and scheduling method thereof | |
| CN109087138A (en) | Data processing method and system, computer system and readable storage medium storing program for executing | |
| CN112347147A (en) | Information pushing method and device based on user association relationship and electronic equipment | |
| CN112182370A (en) | Method and device for pushing item category information, electronic equipment and medium | |
| CN112116426A (en) | Method and device for pushing article information | |
| CN109255563B (en) | Method and device for determining storage area of article | |
| CN107291923B (en) | Information processing method and device | |
| CN112308477A (en) | Inventory positioning method and device | |
| CN110826948B (en) | Warehouse selecting method and device | |
| CN112667770A (en) | Method and device for classifying articles | |
| CN107679096B (en) | Method and device for sharing indexes among data marts | |
| CN110807095A (en) | Article matching method and device | |
| CN110766431A (en) | Method and device for judging whether user is sensitive to coupon | |
| CN110838019A (en) | Method and device for determining trial supply distribution crowd | |
| CN110634040A (en) | Information recommendation method and device | |
| CN110019531A (en) | A kind of method and apparatus obtaining analogical object set | |
| CN113762876A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN109961304B (en) | Method and apparatus for generating information | |
| CN113191840A (en) | Article information display method and device, electronic equipment and computer readable medium | |
| CN113742564A (en) | Target resource pushing method and device |
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 |