CN113077321A - Article recommendation method and device, electronic equipment and storage medium - Google Patents

Article recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113077321A
CN113077321A CN202110430665.6A CN202110430665A CN113077321A CN 113077321 A CN113077321 A CN 113077321A CN 202110430665 A CN202110430665 A CN 202110430665A CN 113077321 A CN113077321 A CN 113077321A
Authority
CN
China
Prior art keywords
item
recommendation
target
time
value
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
Application number
CN202110430665.6A
Other languages
Chinese (zh)
Inventor
廖耀华
周东
沈俊杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Priority to CN202110430665.6A priority Critical patent/CN113077321A/en
Publication of CN113077321A publication Critical patent/CN113077321A/en
Pending legal-status Critical Current

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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
    • 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]
    • G06Q30/0605—Supply or demand aggregation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the invention discloses an article recommendation method, an article recommendation device, electronic equipment and a storage medium, wherein the article recommendation method comprises the following steps: determining whether a target user acquires a related article of a target article in a current article acquisition cycle; if the related item is obtained, determining that the recommended value of the target item is a first recommended value; if the related articles are not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value; and determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy. According to the embodiment of the invention, the recommendation accuracy and recommendation effect of the articles can be improved.

Description

Article recommendation method and device, electronic equipment and storage medium
Technical Field
The present invention relates to recommendation technologies, and in particular, to an article recommendation method and apparatus, an electronic device, and a storage medium.
Background
The conventional article recommendation is usually realized based on the browsing index of a user, and in the process of realizing the method, a finder finds that the recommendation method is not accurate enough and has a poor recommendation effect. For example, when we visit an associated website, such a situation may arise: the item X just browsed by the user on the website A can be taken as a recommended item to appear on a page of the associated website B, and actually, the user may just buy the item X and recommend the item X at the moment, so that the recommending effect is obviously poor.
Disclosure of Invention
The embodiment of the invention provides an article recommendation method and device, electronic equipment and a storage medium, which can improve the article recommendation accuracy and recommendation effect.
In a first aspect, an embodiment of the present invention provides an item recommendation method, including:
determining whether a target user acquires a related article of a target article in a current article acquisition cycle;
if the related item is obtained, determining that the recommended value of the target item is a first recommended value;
if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value;
and determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy.
In a second aspect, an embodiment of the present invention provides an article recommendation apparatus, where the apparatus includes:
the article determining module is used for determining whether the target user obtains the related article of the target article in the current article obtaining period;
a recommended value determining module, configured to determine that the recommended value of the target item is a first recommended value if the related item is obtained; if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value;
and the recommending module is used for determining a recommending strategy according to the first recommending value or the second recommending value and recommending the target article to the target user based on the recommending strategy.
In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the item recommendation method according to any one of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the item recommendation method according to any one of the embodiments of the present invention.
In the embodiment of the present invention, when recommending a target item to a target user, a recommended value of the target item may be determined according to an acquisition condition (e.g., a purchase condition) of the target user for a related item of the target item in a current item acquisition cycle (e.g., a re-purchase cycle) and historical operation information of the target user, that is, if the target user purchases the related item in the re-purchase cycle, it is considered that the target user has a small interest level in the target item, a small recommended value (a first recommended value) is determined for the target item, if the target user has not purchased the related item in the re-purchase cycle, it is indicated that the target user has a large interest level in the target item, a relatively large recommended value (a second recommended value) is determined for the target item according to the historical operation information, that is, when determining the recommended value of the target item, the re-purchase cycle and the interest condition are considered, therefore, the recommendation accuracy and recommendation effect of the articles can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of an item recommendation method according to an embodiment of the present invention.
Fig. 2 is another schematic flow chart of an item recommendation method according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an article recommendation device according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an item recommendation system according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
The article recommendation method provided by the embodiment of the invention can be realized based on the collected historical operation information of the user, and the historical operation information can be obtained by the following method:
for example, when a user acquires (e.g., places an order to purchase) an item (e.g., a commodity) through a network, the user may acquire information such as identification information of the user, an item code of the acquired item, an item type, and an acquisition time (e.g., time to place an order), and then store the user's order information in the form of a key-value pair by using the user's identification information, item code, and item type as keys (keys) and the acquisition time as a value (value). Meanwhile, other operation information of the article recorded before the order is placed at this time, such as browsing time, browsing times, shopping cart adding time and the like, can be deleted. In addition, when the user cancels the acquisition of the item (for example, cancels the order), the order placing information recorded this time may be deleted from the storage.
The identification information of the user may be a user name, a user account, an identification number (e.g., a mobile phone number, a mobile phone identification code) of a terminal used when the user acquires the article, and the like. The item code may be a Stock Keeping Unit (SKU) code of the item, and one SKU code may be used to uniquely identify a type of item; for example, the latest mobile phones manufactured by a certain manufacturer have blue, white and black, and the blue mobile phone, the white mobile phone and the black mobile phone have different SKU codes respectively. The categories of the articles, i.e. the article categories, can be classified into a primary category, a secondary category and a tertiary category according to the order from large to small, and in a specific embodiment, the categories are classified as shown in the following table 1:
Figure BDA0003031340460000041
Figure BDA0003031340460000051
TABLE 1
The categories shown in table 1 are merely examples, and do not limit actual categories.
Practice proves that the range and granularity of the three-level categories are suitable for the recommendation method of the embodiment of the invention, so that in concrete implementation, when the categories are stored, the three-level categories to which the articles belong can be stored, so that the recommendation effect is improved. The same three-level class may correspond to a plurality of different article codes, for example, the three-level class is a mobile phone, the mobile phone has blue, white and black codes, the blue mobile phone, the white mobile phone and the black mobile phone have different SKU codes respectively, and the three-level class of the mobile phone includes three SKU codes.
For example, when a user adds an item to a shopping cart, the identification information of the user, the item code of the item added to the shopping cart, and the time of adding to the shopping cart may be obtained, and then the information of the user added to the shopping cart may be stored in a key-value pair manner, with the identification information of the user and the item code as keys and the time of adding to the shopping cart as values. In addition, when the user cancels the operation of adding the shopping cart at this time, the information of adding the shopping cart recorded at this time can be deleted.
For example, when a user collects an item, the identification information of the user, the item code of the collected item, and the collection time may be obtained, and then the collection information of the user is stored in a key-value pair form with the identification information of the user and the item code as keys and the collection time as values. In addition, when the user cancels the collection operation at this time, the collection information recorded at this time can be deleted.
For example, when a user browses an article, the identification information of the user, the article code of the browsed article, and browsing time may be acquired and counted, and then browsing time and browsing time may be recorded respectively. For example, for the browsing time, the identification information of the user and the article code may be used as keys, and the browsing time may be recorded as a value, and if the user browses the article before, the old browsing time is covered by the latest browsing time; for the browsing times, the identification information and the article code of the user can be used as keys, and the browsing times can be used as values for recording.
That is, the historical operation information of the user recorded in the embodiment of the present invention may be as follows:
key: { identification information of a user }, { item code }, { item class }, value: { acquisition time };
key: { identification information of user }, { article code }, value: { time to join shopping cart };
key: { identification information of user }, { article code }, value: { stowage time };
key: { identification information of user }, { article code }, value: { browsing time };
key: { identification information of user }, { article code }, value: { number of views }.
Of course, in practical application, other operation information may also be recorded according to the service change, and is not specifically limited herein.
Referring to the following description of an item recommendation method provided by an embodiment of the present invention, fig. 1 is a flowchart of the item recommendation method provided by an embodiment of the present invention, and the method may be executed by an item recommendation apparatus provided by an embodiment of the present invention, and the apparatus may be implemented in a software and/or hardware manner. In a particular embodiment, the apparatus may be integrated in an electronic device, which may be, for example, a server. The following embodiments will be described by taking as an example that the apparatus is integrated in an electronic device, and referring to fig. 1, the method may specifically include the following steps:
step 101, determining whether the target user acquires the related item of the target item in the current item acquisition cycle, if so, executing step 102, and if not, executing step 103.
Specifically, the item acquisition cycle (e.g., a repurchase cycle) may refer to an acquisition cycle of a three-level category to which a target item belongs, where the target item may be an item to be recommended to a target user, the target item may include one or more items, and the acquisition cycles of the items of different three-level categories may be different; for example, the acquisition cycle of shampoo and shower gel may be three months, the acquisition cycle of chopsticks and bowls may be six months, and the acquisition cycle of the articles is related to the specification, attribute, function and the like of the articles. In specific implementation, the article acquisition period of the three-level class to which the target article belongs can be determined through big data statistics.
For example, the related item may include an item of the same category as that of the target item, such as the related item is an item of the same tertiary category as that to which the target item belongs, or the related item may include an item of the same item code as that of the target item.
For example, the target item is a dual-core white mobile phone, and its SKU code is CE0103001120000, and the naming rule of the SKU code is as follows: the first-level item (two capital english letter abbreviations) + the second-level item (two-digit code, indicating the sorting of the items) + the third-level item (two-digit code, indicating the sorting of the items) + the supplier code (three-digit code) + the color code (two-digit code) + the random code (four-digit code), then the related item may be an item with the third-level item being 03, or the related item may be an item with the SKU code being CE 0103001120000.
In specific implementation, the historical operation information may be queried according to the identification information of the target user, the item code of the target item, the item class, and the like, so as to obtain the latest acquisition time (for example, the latest order placing time) of the related item, and determine whether the target user acquires the related item of the target item in an item acquisition cycle (i.e., the current item acquisition cycle) after the latest acquisition time; if the target user acquires the related articles in the current article acquisition cycle, determining a smaller recommendation value, namely a first recommendation value, for the target article if the target user is low in current demand and low in interest on the target article; if the target user does not acquire the related item in the current item acquisition cycle, it is considered that the target user has a high demand and a high interest in the target item, step 103 may be performed to determine a relatively large recommended value, i.e., a second recommended value, for the target item.
Step 102, determining the recommended value of the target item as a first recommended value.
For example, the target item is a certain mobile phone, and if the target user has purchased the mobile phone in the current item acquisition period, the recommended value of the current mobile phone is determined to be the first recommended value. Illustratively, the first recommended value may be 0 or a numerical value close to 0.
Step 103, obtaining historical operation information of the target user, and calculating a recommended value of the target object based on the historical operation information to obtain a second recommended value, wherein the second recommended value is greater than the first recommended value.
For example, the historical operation information may include a plurality of operation information of the target user on the target item, such as: and calculating the recommended value of the target object according to the plurality of operation information to obtain a second recommended value. Specifically, the closer the browsing time, the collection time, the time for joining the shopping cart to the current time, or the more browsing times, the larger the obtained second recommendation value.
For example, the target item is a certain mobile phone, and if the target user has not purchased any mobile phone in the current item acquisition cycle, the recommended value of the current mobile phone can be determined according to the latest browsing time, browsing times, collection time, and time of joining a shopping cart of the target user to the current mobile phone, so as to obtain a second recommended value, where the second recommended value is greater than the first recommended value. In the embodiment of the present invention, the larger the recommendation value is, the higher the recommendation priority of the corresponding item is.
And 104, determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy.
Namely, if the determined recommendation value of the target item is the first recommendation value, determining the recommendation strategy of the target item according to the first recommendation value, and if the determined recommendation value of the target item is the second recommendation value, determining the recommendation strategy of the target item according to the second recommendation value.
In a specific embodiment, for example, a recommendation threshold may be set, and a recommendation policy may be determined according to the recommendation threshold. For example, if the calculated recommendation value of the target item is greater than the recommendation threshold, the target item is recommended to the target user, and if the recommendation value of the target item is not greater than the recommendation threshold, the target item is not recommended to the target user.
In a particular embodiment, the recommendation policy may also be determined according to the ranking. For example, when there are a plurality of target items, the recommended value of each target item may be calculated, all the target items may be sorted in the order from high to low according to the recommended values, the target item sorted in the top may be preferentially recommended to the target user, or only the target items sorted in the near preset number may be recommended to the target user.
Specifically, when recommending a target item to a target user, recommendation information of the target item may be sent to a terminal of the target user, where the recommendation information may include, but is not limited to, text, pictures, videos, and the like, and the terminal may be a terminal such as a mobile phone, a Personal Computer (PC), a tablet Computer, a notebook Computer, a desktop Computer, and the like.
In the embodiment of the present invention, when recommending a target item to a target user, a recommended value of the target item may be determined according to an acquisition condition (e.g., a purchase condition) of the target user for a related item of the target item in a current item acquisition cycle (e.g., a re-purchase cycle) and historical operation information of the target user, that is, if the target user purchases the related item in the re-purchase cycle, it is considered that the target user has a small interest level in the target item, a small recommended value (a first recommended value) is determined for the target item, if the target user has not purchased the related item in the re-purchase cycle, it is indicated that the target user has a large interest level in the target item, a relatively large recommended value (a second recommended value) is determined for the target item according to the historical operation information, that is, when determining the recommended value of the target item, the re-purchase cycle and the interest condition are considered, therefore, the recommendation accuracy and recommendation effect of the articles can be improved.
The method for recommending an item according to an embodiment of the present invention is further described below, and as shown in fig. 2, the method for recommending an item according to an embodiment of the present invention may specifically include the following steps:
step 201, determining whether the target user acquires the related item of the target item in the current item acquisition cycle, if so, executing step 202, and if not, executing step 203.
Specifically, the item acquisition cycle (e.g., a repurchase cycle) may refer to an acquisition cycle of a three-level category to which a target item belongs, where the target item may be an item to be recommended to a target user, the target item may include one or more items, and the acquisition cycles of the items of different three-level categories may be different; for example, the acquisition cycle of shampoo and shower gel may be three months, the acquisition cycle of chopsticks and bowls may be six months, and the acquisition cycle of the articles is related to the specification, attribute, function and the like of the articles. In specific implementation, the article acquisition period of the three-level class to which the target article belongs can be determined through big data statistics.
For example, the related item may include an item of the same category as that of the target item, such as the related item is an item of the same tertiary category as that to which the target item belongs, or the related item may include an item of the same item code as that of the target item.
In specific implementation, the historical operation information may be queried according to the identification information of the target user, the item code of the target item, the item class, and the like, so as to obtain the latest acquisition time (for example, the latest order placing time) of the related item, and determine whether the target user acquires the related item of the target item in an item acquisition cycle (i.e., the current item acquisition cycle) after the latest acquisition time; if the target user acquires the related articles in the current article acquisition cycle, determining a smaller recommendation value, namely a first recommendation value, for the target article if the target user is low in current demand and low in interest on the target article; if the target user does not acquire the related item in the current item acquisition cycle, it is considered that the target user has a high demand and a high interest in the target item, step 203 may be executed to determine a relatively large recommended value, that is, a second recommended value, for the target item.
Step 202, determining the recommended value of the target item as a first recommended value.
For example, the target item is a certain mobile phone, and if the target user has purchased the mobile phone in the current item acquisition period, the recommended value of the current mobile phone is determined to be the first recommended value. Illustratively, the first recommended value may be 0 or a numerical value close to 0.
Step 203, obtaining historical operation information of the target user, wherein the historical operation information comprises browsing time, browsing times, collecting time and shopping cart adding time.
For example, the historical operation records may be queried according to the identification information of the target user and the item code of the target item, so as to obtain information such as browsing time, browsing times, collection time, and time of joining a shopping cart of the target user to the target item.
And step 204, calculating the recommendation score of the browsing time according to the browsing time and the item acquisition period.
For example, with QaRecommendation score, T, representing browsing time1Indicating an article acquisition period, TnIndicating the current time, TaRepresenting the latest browsing time among the browsing times, then:
Figure BDA0003031340460000111
for ease of calculation, if Tn-TaGreater than T1Then get Tn-Ta＝T1Thus, the subsequently calculated recommended value will not exceed 1.
And step 205, calculating the recommendation score of the browsing times according to the browsing times and the threshold value of the browsing times.
For example, with QbRecommendation score indicating number of views, FbRepresenting the browsing times, F representing the threshold value of the browsing times, then:
Figure BDA0003031340460000112
wherein if FbIf greater than F, take FbThe browsing number threshold value F can be obtained according to actual experience or through big data statistical analysis. For example, through big data statistical analysis: if the number of times that most users browse the target item in the re-purchase period does not exceed 30 times, F may be set to 30.
Step 206, calculating a recommendation score for the collection time based on the collection time and the first time length threshold.
For example, with QcRecommendation score, T, representing the time of collection2Representing a first time length threshold, TcRepresenting the collection time, then:
Figure BDA0003031340460000121
wherein if Tn-TcGreater than T2Then get Tn-Tc＝T2First time length threshold value T2The first time length threshold value T can be obtained according to actual experience or through big data statistical analysis2May represent a decay period of user interest after collection of the target item. For example, through big data statistical analysis: 30 days after the target item is collected, the interest degree of the user for purchasing the target item is reduced to be low, and then T can be set2Set to 30.
And step 207, calculating a recommendation score of the shopping cart joining time according to the shopping cart joining time and the second duration threshold.
For example, with QdIdentifying a recommendation score, T, for joining a shopping cart time3Representing a second time duration threshold, TdIndicating the time to join the shopping cart, then:
Figure BDA0003031340460000122
wherein if Tn-TdGreater than T3Then get Tn-Td＝T3Second duration threshold T3The second duration threshold T can be obtained according to actual experience or through big data statistical analysis3May represent a period of decay in user interest after the target item is added to the shopping cart. For example, through big data statistical analysis: 45 days after the target item is added into the shopping cart, the interest degree of the user for purchasing the target item is reduced to be low, and T can be set3Set at 45.
And step 208, calculating the recommended value of the target object according to the recommended score of each kind of operation information and the weight of the corresponding operation information to obtain a second recommended value.
For example, the second recommended value, w, is represented by QaWeight, w, representing browsing timebWeight, w, representing the number of viewscWeight, w, representing the time of collectiondWeight, w, representing time of joining shopping carta、wb、wc、wdAll can take value according to actual conditions or experimental data, then:
Q＝Qa*wa+Qb*wb+Qc*wc+Qd*wd
it should be noted that the method for calculating the second recommended value provided in the embodiment of the present invention is only a preferred method, and is not limited to the specific method for calculating the second recommended value.
Step 209, determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy.
Namely, if the determined recommendation value of the target item is the first recommendation value, determining the recommendation strategy of the target item according to the first recommendation value, and if the determined recommendation value of the target item is the second recommendation value, determining the recommendation strategy of the target item according to the second recommendation value.
In a specific embodiment, for example, a recommendation threshold may be set, and a recommendation policy may be determined according to the recommendation threshold. For example, if the calculated recommendation value of the target item is greater than the recommendation threshold, the target item is recommended to the target user, and if the recommendation value of the target item is not greater than the recommendation threshold, the target item is not recommended to the target user.
In a particular embodiment, the recommendation policy may also be determined according to the ranking. For example, when there are a plurality of target items, the recommended value of each target item may be calculated, all the target items may be sorted in the order from high to low according to the recommended values, the target item sorted in the top may be preferentially recommended to the target user, or only the target items sorted in the near preset number may be recommended to the target user.
Specifically, when recommending a target item to a target user, recommendation information of the target item may be sent to a terminal of the target user, where the recommendation information may include, but is not limited to, text, pictures, videos, and the like, and the terminal may be a terminal such as a mobile phone, a Personal Computer (PC), a tablet Computer, a notebook Computer, a desktop Computer, and the like.
In the embodiment of the present invention, when recommending a target item to a target user, a recommended value of the target item may be determined according to an acquisition condition (e.g., a purchase condition) of the target user for a related item of the target item in a current item acquisition cycle (e.g., a re-purchase cycle) and historical operation information of the target user, that is, if the target user purchases the related item in the re-purchase cycle, it is considered that the target user has a small interest level in the target item, a small recommended value (a first recommended value) is determined for the target item, if the target user has not purchased the related item in the re-purchase cycle, it is indicated that the target user has a large interest level in the target item, a relatively large recommended value (a second recommended value) is determined for the target item according to the historical operation information, that is, when determining the recommended value of the target item, the re-purchase cycle and the interest condition are considered, therefore, the recommendation accuracy and recommendation effect of the articles can be improved.
Fig. 3 is a block diagram of an article recommendation apparatus according to an embodiment of the present invention, which is suitable for executing the article recommendation method according to the embodiment of the present invention. As shown in fig. 3, the apparatus may specifically include:
an item determining module 301, configured to determine whether a target user acquires an item related to a target item in a current item acquisition cycle;
a recommended value determining module 302, configured to determine that the recommended value of the target item is a first recommended value if the related item is obtained; if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value;
a recommending module 303, configured to determine a recommending policy according to the first recommended value or the second recommended value, and recommend the target item to the target user based on the recommending policy.
In one embodiment, the related item comprises an item of the same type as that of the target item, or the related item comprises an item of the same item code as that of the target item.
In an embodiment, the historical operation information includes a plurality of operation information of the target user on the target item, and the calculating, by the recommended value determining module 302, a recommended value of the target item based on the historical operation information, and obtaining a second recommended value includes:
calculating a recommendation score for each of the plurality of types of operation information;
and calculating the recommended value of the target object according to the recommended score of each kind of operation information and the weight of the corresponding operation information to obtain the second recommended value.
In one embodiment, the plurality of operation information includes browsing time, browsing times, collecting time and time of joining a shopping cart.
In one embodiment, the recommendation value determining module 302 calculates a recommendation score for each of the plurality of operation information, including:
calculating a recommendation score of the browsing time according to the browsing time and the item acquisition period;
calculating the recommendation score of the browsing times according to the browsing times and the threshold value of the browsing times;
calculating a recommendation score of the collection time according to the collection time and a first time length threshold value; and
and calculating the recommendation score of the shopping cart joining time according to the shopping cart joining time and a second duration threshold.
In an embodiment, the recommendation value determining module 302 processes the browsing time and the item obtaining period according to the following formula to obtain the recommendation score of the browsing time:
Figure BDA0003031340460000151
wherein Q isaA recommendation score, T, representing the browsing time1Representing said article acquisition period, TnIndicating the current time, TaRepresenting a latest browsing time among the browsing times;
and processing the browsing times and the browsing time threshold value according to the following formula to obtain the recommendation score of the browsing times:
Figure BDA0003031340460000161
wherein Q isbA recommendation score representing said number of views, FbRepresenting the browsing times, and F representing the threshold value of the browsing times;
processing the collection time and the first time threshold value according to the following formula to obtain the recommendation score of the collection time:
Figure BDA0003031340460000162
wherein Q iscA recommendation score, T, representing the collection time2Representing said first time threshold, TcRepresenting the collection time; and
processing the shopping cart joining time and the second duration threshold according to the following formula to obtain the recommendation score of the shopping cart joining time:
Figure BDA0003031340460000163
wherein Q isdThe recommendation score for the time to join the shopping cart, T3Representing said second duration threshold, TdIndicating the time to join the shopping cart.
In an embodiment, the recommended value determining module 302 processes the recommended score of each type of operation information and the weight of the corresponding operation information according to the following formula to obtain the second recommended value:
Q＝Qa*wa+Qb*wb+Qc*wc+Qd*wd
wherein Q represents the second recommended value, waWeight, w, representing the browsing timebWeight, w, representing the number of viewscWeight, w, representing said collection timedA weight representing the time of joining the shopping cart.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the functional module, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
When recommending a target item to a target user, the apparatus of the embodiment of the present invention may determine a recommended value of the target item according to an acquisition condition (e.g., a purchase condition) of the target item by the target user within a current item acquisition cycle (e.g., a re-purchase cycle) and historical operation information of the target user, that is, if the target user purchases the related item within the re-purchase cycle, it is considered that the target user has a small interest level in the target item, a small recommended value (a first recommended value) is determined for the target item, if the target user has not purchased the related item within the re-purchase cycle, it is considered that the target user has a large interest level in the target item, a relatively large recommended value (a second recommended value) is determined for the target item according to the historical operation information, that is, when determining the recommended value of the target item, the re-purchase cycle and the interest condition of the item are considered, therefore, the recommendation accuracy and recommendation effect of the articles can be improved.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the article recommendation method provided by any one of the embodiments is realized.
The embodiment of the invention also provides a computer readable medium, wherein a computer program is stored on the computer readable medium, and when the computer program is executed by a processor, the computer program realizes the item recommendation method provided by any one of the above embodiments.
An embodiment of the present invention further provides an article recommendation system, as shown in fig. 4, including a terminal 401 and an electronic device 402. The electronic device 402 is configured to execute the item recommendation method according to any embodiment of the present invention, and recommend the target item to the terminal 402 of the target user, where the specific recommendation method may refer to the description of the foregoing embodiment, and details are not described here.
Turning now to FIG. 5, a block diagram of a computer system 500 suitable for use in implementing an electronic device of an embodiment of the present invention is shown. The electronic device shown in fig. 5 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. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 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 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
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 and/or units described in the embodiments of the present invention may be implemented by software, and may also be implemented by hardware. The described modules and/or units may also be provided in a processor, and may be described as: a processor includes an item determination module, a recommendation value determination module, and a recommendation module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself.
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 comprise: determining whether a target user acquires a related article of a target article in a current article acquisition cycle; if the related item is obtained, determining that the recommended value of the target item is a first recommended value; if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value; and determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy.
According to the technical scheme of the embodiment of the invention, when recommending a target item to a target user, a recommendation value of the target item can be determined according to an acquisition condition (for example, a purchase condition) of the target user for a related item of the target item in a current item acquisition cycle (for example, a re-purchase cycle) and historical operation information of the target user, that is, if the target user purchases the related item in the re-purchase cycle, it is considered that the interest degree of the target user for the target item is small, a small recommendation value (a first recommendation value) is determined for the target item, if the target user does not purchase the related item in the re-purchase cycle yet, it is indicated that the interest degree of the target user for the target item is large, a relatively large recommendation value (a second recommendation value) is determined for the target item according to the historical operation information, that is when determining the recommendation value of the target item, the re-purchase cycle and the interest condition of the item are considered, therefore, the recommendation accuracy and recommendation effect of the articles can be improved.
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 (10)

1. An item recommendation method, comprising:
determining whether a target user acquires a related article of a target article in a current article acquisition cycle;
if the related item is obtained, determining that the recommended value of the target item is a first recommended value;
if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value;
and determining a recommendation strategy according to the first recommendation value or the second recommendation value, and recommending the target item to the target user based on the recommendation strategy.
2. The item recommendation method according to claim 1, wherein the related item comprises an item of the same type as that of the target item, or the related item comprises an item of the same item code as that of the target item.
3. The item recommendation method according to claim 1 or 2, wherein the historical operation information includes a plurality of kinds of operation information of the target user on the target item, and the calculating of the recommendation value of the target item based on the historical operation information to obtain a second recommendation value includes:
calculating a recommendation score for each of the plurality of types of operation information;
and calculating the recommended value of the target object according to the recommended score of each kind of operation information and the weight of the corresponding operation information to obtain the second recommended value.
4. The item recommendation method according to claim 3, wherein the plurality of operation information includes browsing time, browsing times, collection time, and time of joining a shopping cart.
5. The item recommendation method according to claim 4, wherein said calculating a recommendation score for each of the plurality of operation information comprises:
calculating a recommendation score of the browsing time according to the browsing time and the item acquisition period;
calculating the recommendation score of the browsing times according to the browsing times and the threshold value of the browsing times;
calculating a recommendation score of the collection time according to the collection time and a first time length threshold value; and
and calculating the recommendation score of the shopping cart joining time according to the shopping cart joining time and a second duration threshold.
6. The item recommendation method according to claim 5, wherein said browsing time and said item acquisition period are processed according to the following formula to obtain a recommendation score of said browsing time:
Figure FDA0003031340450000021
wherein Q isaA recommendation score, T, representing the browsing time1Representing said article acquisition period, TnIndicating the current time, TaRepresenting a latest browsing time among the browsing times;
and processing the browsing times and the browsing time threshold value according to the following formula to obtain the recommendation score of the browsing times:
Figure FDA0003031340450000022
wherein Q isbA recommendation score representing said number of views, FbRepresenting the browsing times, and F representing the threshold value of the browsing times;
processing the collection time and the first time threshold value according to the following formula to obtain the recommendation score of the collection time:
Figure FDA0003031340450000023
wherein Q iscA recommendation score, T, representing the collection time2Representing said first time threshold, TcRepresenting the collection time; and
processing the shopping cart joining time and the second duration threshold according to the following formula to obtain the recommendation score of the shopping cart joining time:
Figure FDA0003031340450000031
wherein Q isdThe recommendation score for the time to join the shopping cart, T3To representThe second duration threshold, TdIndicating the time to join the shopping cart.
7. The item recommendation method according to claim 6, wherein the recommendation score of each type of operation information and the weight of the corresponding operation information are processed according to the following formula to obtain the second recommendation value:
Q＝Qa*wa+Qb*wb+Qc*wc+Qd*wd
wherein Q represents the second recommended value, waWeight, w, representing the browsing timebWeight, w, representing the number of viewscWeight, w, representing said collection timedA weight representing the time of joining the shopping cart.
8. An item recommendation device, comprising:
the article determining module is used for determining whether the target user obtains the related article of the target article in the current article obtaining period;
a recommended value determining module, configured to determine that the recommended value of the target item is a first recommended value if the related item is obtained; if the related article is not obtained, obtaining historical operation information of the target user, and calculating a recommended value of the target article based on the historical operation information to obtain a second recommended value, wherein the second recommended value is larger than the first recommended value;
and the recommending module is used for determining a recommending strategy according to the first recommending value or the second recommending value and recommending the target article to the target user based on the recommending strategy.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the item recommendation method of any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the item recommendation method according to any one of claims 1 to 7.
CN202110430665.6A 2021-04-21 2021-04-21 Article recommendation method and device, electronic equipment and storage medium Pending CN113077321A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110430665.6A CN113077321A (en) 2021-04-21 2021-04-21 Article recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110430665.6A CN113077321A (en) 2021-04-21 2021-04-21 Article recommendation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113077321A true CN113077321A (en) 2021-07-06

Family

ID=76618294

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110430665.6A Pending CN113077321A (en) 2021-04-21 2021-04-21 Article recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113077321A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657971A (en) * 2021-08-31 2021-11-16 卓尔智联(武汉)研究院有限公司 Article recommendation method and device and electronic equipment
CN113781171A (en) * 2021-09-10 2021-12-10 未鲲(上海)科技服务有限公司 Information pushing method, device, equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
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
WO2020001096A1 (en) * 2018-06-29 2020-01-02 京东方科技集团股份有限公司 Commodity recommendation method and commodity recommendation device
CN111325609A (en) * 2020-02-28 2020-06-23 京东数字科技控股有限公司 Commodity recommendation list determining method and device, electronic equipment and storage medium
CN111523976A (en) * 2020-04-23 2020-08-11 京东数字科技控股有限公司 Commodity recommendation method and device, electronic equipment and storage medium
CN111612560A (en) * 2019-02-26 2020-09-01 北京京东尚科信息技术有限公司 Promotion object recommendation method and system, storage medium and electronic device

Patent Citations (5)

* Cited by examiner, † Cited by third party
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
WO2020001096A1 (en) * 2018-06-29 2020-01-02 京东方科技集团股份有限公司 Commodity recommendation method and commodity recommendation device
CN111612560A (en) * 2019-02-26 2020-09-01 北京京东尚科信息技术有限公司 Promotion object recommendation method and system, storage medium and electronic device
CN111325609A (en) * 2020-02-28 2020-06-23 京东数字科技控股有限公司 Commodity recommendation list determining method and device, electronic equipment and storage medium
CN111523976A (en) * 2020-04-23 2020-08-11 京东数字科技控股有限公司 Commodity recommendation method and device, electronic equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657971A (en) * 2021-08-31 2021-11-16 卓尔智联(武汉)研究院有限公司 Article recommendation method and device and electronic equipment
CN113657971B (en) * 2021-08-31 2023-12-01 卓尔智联(武汉)研究院有限公司 Article recommendation method and device and electronic equipment
CN113781171A (en) * 2021-09-10 2021-12-10 未鲲(上海)科技服务有限公司 Information pushing method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
US9208437B2 (en) Personalized information pushing method and device
CN108664513B (en) Method, device and equipment for pushing keywords
EP2862105A1 (en) Ranking search results based on click through rates
CN110111167A (en) A kind of method and apparatus of determining recommended
US20150221023A1 (en) Information providing device, information providing method, information providing program, and computer-readable storage medium storing the program
CN105205188A (en) Method and device for recommending purchase material suppliers
CN110825977A (en) Data recommendation method and related equipment
CN113077321A (en) Article recommendation method and device, electronic equipment and storage medium
CN112102031A (en) Recommendation method, recommendation device and terminal equipment
CN110827112A (en) Deep learning commodity recommendation method and device, computer equipment and storage medium
CN110766486A (en) Method and device for determining item category
CN107679916A (en) For obtaining the method and device of user interest degree
CN113077317A (en) Item recommendation method, device and equipment based on user data and storage medium
CN109727047A (en) A kind of method and apparatus, data recommendation method and the device of determining data correlation degree
WO2014110950A1 (en) Method and device for pushing information
CN111612560A (en) Promotion object recommendation method and system, storage medium and electronic device
CN111078997B (en) Information recommendation method and device
CN110020171A (en) Data processing method, device, equipment and computer readable storage medium
CN113177154A (en) Search term recommendation method and device, electronic equipment and storage medium
CN107766537A (en) A kind of position search ordering method and computing device
CN112561636A (en) Recommendation method, recommendation device, terminal equipment and medium
US20180165741A1 (en) Information providing device, information providing method, information providing program, and computer-readable storage medium storing the program
CN103218726A (en) Information item recommendation method and system
CN110659919A (en) Data matching method, device, medium and electronic equipment
CN110827044A (en) Method and device for extracting user interest mode

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