CN111932321B - Method and device for pushing article information for user, electronic equipment and medium - Google Patents
Method and device for pushing article information for user, electronic equipment and medium Download PDFInfo
- Publication number
- CN111932321B CN111932321B CN202011004904.3A CN202011004904A CN111932321B CN 111932321 B CN111932321 B CN 111932321B CN 202011004904 A CN202011004904 A CN 202011004904A CN 111932321 B CN111932321 B CN 111932321B
- Authority
- CN
- China
- Prior art keywords
- article
- tag
- information
- user
- item
- 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.)
- Expired - Fee Related
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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The embodiment of the disclosure discloses a method, a device, an electronic device and a computer readable medium for pushing item information of a user. One embodiment of the method comprises: acquiring article label information of each article in an article group to be recommended for a user to obtain an article label information set; generating a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set; generating a distance information set based on the user tag name vector and the article tag name vector set; generating a relationship information set based on the distance information set, the user tag name vector and the article tag name vector set; and generating an article recommendation information table based on the relationship information set, the user label scoring values, the article label scoring values included in the article label information set and the article acquisition frequency values corresponding to the article label scoring values. The embodiment improves the shopping experience of the user.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for pushing article information for a user, electronic equipment and a computer readable medium.
Background
With the development of internet technology and the arrival of the e-commerce era, more and more shopping platforms appear. The shopping platform will generally push the item information of the higher sales items to the user to improve the user experience.
However, the method of pushing the item information of the high-volume items to the user has the following technical problems:
firstly, the item information of high-sales items is generally pushed to the user, the actual demand of the user is not considered, and the shopping experience of the user is reduced;
secondly, item information of high-sales items is generally pushed to a user, and the degree of contact between a user tag and an item tag is not considered, so that the accuracy of items recommended to the user is not high, the shopping experience of the user is reduced, and the reduction of the user and the reduction of the platform user traffic are caused;
thirdly, the item information of the high-sales items is generally pushed to the user, the influence of various factors on the item recommendation result cannot be considered comprehensively, the accuracy of the generated item recommendation score value is not high, the accuracy of the items recommended to the user is not high, the shopping experience of the user is reduced, and therefore the reduction of the user and the reduction of the platform user flow are caused.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose an item information pushing method, apparatus, electronic device and computer readable medium for a user to solve one or more of the technical problems mentioned in the above background section.
In a first aspect, some embodiments of the present disclosure provide an item information pushing method for a user, the method including: acquiring article tag information of each article in an article group to be recommended for a user based on a user information tag of the user to obtain an article tag information set, wherein the article tag information comprises an article tag name, an article tag score value corresponding to the article tag name and an article acquisition frequency value corresponding to the article tag score value, and the user information tag comprises a user tag name and a user tag score value corresponding to the user tag name; generating a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set; generating a distance information set based on the user tag name vector and the article tag name vector set; generating a relationship information set based on the distance information set, the user tag name vector, and the article tag name vector set; and generating an article recommendation information table based on the relationship information set, the user label scoring values, the article label scoring values included in the article label information set and the article acquisition frequency values corresponding to the article label scoring values.
In some embodiments, said generating distance information values based on said user tag name vector, said item tag name vector, said vector mean, said first dimension metric, said second dimension metric, and said first dimension sum comprises:
generating a distance information value by:
wherein the content of the first and second substances,
which represents the value of the distance information,
representing either the first dimension metric or the second dimension metric,
representing the second in the user tag name vector
The value of the dimension(s) is,
representing the second in the tag name vector of said item
The value of the dimension(s) is,
the mean value of the vector is represented by,
representing the first dimension sum.
In some embodiments, said determining relationship information between said user tag name vector and each target item tag name vector in said set of target item tag name vectors comprises:
respectively turning over data in each dimension in the user tag name vector and data in each dimension in the target object tag name vector to generate a turned-over user tag name vector and a turned-over target object tag name vector;
generating a relationship information value by:
wherein the content of the first and second substances,
a value representing the relationship information is indicated,
representing a number of dimensions included in the flipped user tag name vector or a number of dimensions included in the flipped article tag name vector,
representing the second in the flipped user tag name vector
The value of the dimension(s) is,
representing the second in the flipped target item tag name vector
The value of the dimension;
and determining the relation information value as the relation information.
In some embodiments, the generating an item recommendation score value based on the user tag score value, each target relationship information in the target relationship information set, a target item tag score value in the target item tag score value group corresponding to the relationship information, and an item acquisition frequency value corresponding to the target item tag score value, includes:
generating an item recommendation score value by:
wherein the content of the first and second substances,
a value of a recommendation score for the item is indicated,
a value representing the tag score of the target item,
representing the frequency of acquisition of said article,
representing a quantity of a target item tag score value comprised in the set of target item tag score values,
represents the second of the set of target item tag scores
The value of the tag score of the individual target item,
is shown as
The frequency value of the article corresponding to the label scoring value of each target article is obtained,
a value representing the user's tag score,
a target relationship information value representing the target relationship information.
In a second aspect, some embodiments of the present disclosure provide an item information pushing device for a user, the device including: an acquisition unit configured to acquire, based on a user information tag of a user, article tag information of each article in an article group to be recommended for the user, the article tag information including an article tag name, an article tag score value corresponding to the article tag name, and an article acquisition frequency value corresponding to the article tag score value, to obtain an article tag information set, the user information tag including a user tag name and a user tag score value corresponding to the user tag name; a first generating unit configured to generate a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set; a second generating unit configured to generate a set of distance information based on the user tag name vector and the set of article tag name vectors; a third generating unit configured to generate a set of relationship information based on the set of distance information, the user tag name vector, and the set of item tag name vectors; a fourth generating unit configured to generate an item recommendation information table based on the relationship information set, the user tag score value, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement the method as described in the first aspect.
In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in the first aspect.
The above embodiments of the present disclosure have the following advantages: first, based on a user information tag of a user, article tag information of each article in an article group to be recommended for the user is acquired, and an article tag information set is obtained. Therefore, the related information of the object to be recommended can be known, and a foundation is laid for generating an object recommendation information table. Next, a user tag name vector and an article tag name vector set may be generated based on the user tag name and the article tag information set. Therefore, a calculation foundation is laid for the distance between the subsequent calculation vectors and the relation information between the vectors. Next, a distance information set is generated based on the user tag name vector and the set of item tag name vectors. Therefore, the tightness degree between the two vectors can be preliminarily judged according to the distance between the vectors, so that the vectors meeting the conditions can be screened out, and a foundation is laid for calculating the relationship information between the vectors in the next step. Then, a relational information set is generated based on the distance information set, the user tag name vector, and the article tag name vector set. Therefore, the degree of association between the user tag name and the article tag name can be determined, and a foundation is further laid for recommending related article information to the user. Finally, an item recommendation information table may be generated based on the relationship information set, the user tag score value, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value. Therefore, good-quality articles can be recommended for the user, customized service is provided for the user, and the shopping experience of the user is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of one application scenario of an item information push method for a user, in accordance with some embodiments of the present disclosure;
FIG. 2 is a flow diagram of some embodiments of an item information push method for a user according to the present disclosure;
FIG. 3 is a flow diagram of further embodiments of an item information push method for a user according to the present disclosure;
FIG. 4 is a schematic structural diagram of some embodiments of an item information push device for a user according to the present disclosure;
FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of an item information pushing method for a user according to some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may obtain an item tag information set 103 based on the user tag information 102. Second, computing device 101 may generate user tag name vector 104 from user tag information 102. Next, the computing device 101 may generate an item tag name vector set 105 based on the item tag information set 103. The computing device 101 may then generate a set of distance information 106 from the user tag name vector 104 and the set of item tag name vectors 105. Then, the computing device 101 may generate a set of relationship information 107 based on the set of distance information 106. Finally, the computing device 101 may generate an item recommendation information table 108 based on the set of relationship information 107. Alternatively, the computing device 101 may output the item recommendation information table 108 for display on the display device 109.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.
With continued reference to fig. 2, a flow 200 of some embodiments of an item information push method for a user in accordance with the present disclosure is shown. The method may be performed by the computing device 101 of fig. 1. The item information pushing method for the user comprises the following steps:
In some embodiments, an executing entity (such as the computing device shown in fig. 1) of the item information pushing method for the user may obtain, based on the user information tag of the user, item tag information of each item in the item group to be recommended for the user from a terminal through a wired connection manner or a wireless connection manner, so as to obtain an item tag information set. The article tag information includes an article tag name, an article tag score value corresponding to the article tag name, and an article acquisition frequency value corresponding to the article tag score value. The user information tag includes a user tag name and a user tag score value corresponding to the user tag name. Here, the user information tag of the user may be a user information tag acquired in advance from the device terminal. Here, the user information tag may be a tag representing user-related behavior information. For example, the user information tag may be "cosmetics; 8 minutes. The user tag name may be "cosmetics". The user tag score value may be "8". Here, the article tag information may be tag information representing an article attribute. For example, the item information tag for item a may be "edi; 7 min; 10 times. Wherein the item tag name may be "didi". The item tag score value may be "7". The above item acquisition frequency value may be "10".
As an example, the user information tag may be "cosmetics; 8 minutes. The group of articles may be a "perfume; lipstick; foundation "foundation. The item tag information for the item "perfume" may be "didi; 7 min; 10 times. The item label information for the item "lipstick" may be "forest; 6 minutes; 12 times. The article label information for the article "foundation" may be "blue band; 9 minutes; 11 times.
In some embodiments, the execution body may generate the user tag name vector and the set of item tag name vectors in various ways.
In some optional implementations of some embodiments, the executing entity may generate the user tag name vector and the set of item tag name vectors by:
in the first step, vectorization processing is performed on the user tag name to generate a user tag name vector.
As an example, the user tag name may be "cosmetics". The "cosmetics" are subjected to a one-hot encoding process to generate a user tag name vector "[ 10001 ]".
And secondly, vectorizing the article tag name included in each article tag information in the article tag information set to generate an article tag name vector, so as to obtain an article tag name vector set.
As an example, the above item tag information set may be "{ didy; 7 min; 10 times }; { forest; 6 minutes; 12 times }; { a blue band; 9 minutes; 11 times } ". The unique heat encoding process is performed on "didi" to generate an item tag name vector "[ 01001 ]". The "forest" is subjected to a one-hot encoding process to generate an item tag name vector "[ 00101 ]". The "blue band" is subjected to a one-hot encoding process to generate an item tag name vector "[ 01010 ]". A product tag name vector set "[ 01001], [00101], [01010 ]".
In some embodiments, the execution subject may generate the distance information by:
first, the number of dimensions included in the user tag name vector is determined.
As an example, the above-mentioned user tag name vector may be "[ 10001 ]". The number of dimensions included in the above-described user tag name vector is "5".
And secondly, determining the number of dimensions included by each item tag name vector in the item tag name vector set as the number of item dimensions to obtain an item dimension number group.
As an example, the above item tag name vector set may be "[ 01001], [00101], [01010 ]". The number of dimensions included in the item tag name vector "[ 01001 ]" is "5". The number of dimensions included in the above article tag name vector "[ 00101 ]" is "5". The number of dimensions included in the above-mentioned item tag name vector "[ 01010 ]" is "5". The number of article dimensions group "5, 5, 5" is obtained.
A third step of inputting the number of each article dimension in the article dimension number group, an article tag name vector corresponding to the number of the article dimensions, the number of dimensions included in the user tag name vector, and the user tag name vector into the following formula to generate a distance information value:
wherein the content of the first and second substances,
indicating a distance information value.
The number of dimensions included in the user tag name vector or the number of dimensions of the object is represented.
Indicating the second in the user tag name vector
The value of the dimension.
Indicating the second in the label name vector of the article
The value of the dimension. Here, the distance information value may retain two significant digits after the decimal point.
As an example, the number of dimensions included in the user tag name vector or the number of dimensions of the item
May be "5". The user tag name vector may be "[ 10001]]". The item tag name vector may be "[ 01001]]". Generating a distance information value by:
as another example, the user tag name vector may be "[ 10001 ]". The above-mentioned item tag name vector set may be "[ 01001], [00101], [01010 ]". The distance information value between the article tag name vector "[ 00101 ]" and the user tag name vector "[ 10001 ]" is "1.41". The distance information value between the product tag name vector "[ 01010 ]" and the user tag name vector "[ 10001 ]" is "2".
And fourthly, determining the distance information value as distance information.
As an example, the above distance information value "1.41" may be determined as the distance information "distance information value: 1.41".
In some embodiments, the executing agent may generate the relationship information by:
first, selecting distance information larger than a preset threshold value from the distance information set as target distance information to obtain a target distance information group. Here, the predetermined threshold value may range between a minimum value and a maximum value of the distance information value.
As an example, the above distance information set may be "distance information value: 1.41, distance information value: 1.41, distance information value: 2". A distance information "distance information value greater than" 1.3 "may be selected from the above-mentioned distance information set: 1.41, distance information value: 1.41, distance information value: 2 "as the target distance information, a target distance information group" { target distance information value: 1.41 }; { target distance information value: 1.41 }; { target distance information value: 2}".
And secondly, determining the object tag name vector in the object tag name vector set corresponding to each object distance information in the object distance information group as an object tag name vector to obtain an object tag name vector set.
As an example, the above-described target distance information group may be "{ target distance information value: 1.41 }; { target distance information value: 1.41 }; { target distance information value: 2}". A target item tag name vector set "[ 01001], [00101], [01010 ]".
Thirdly, determining the direct relation information value of each target object tag name vector in the target object tag name vector set and the user tag name vector through the following formula:
wherein the content of the first and second substances,
representing a relationship information value.
The number of dimensions included in the user tag name vector or the number of dimensions included in the item tag name vector is indicated.
Indicating the second in the user tag name vector
The value of the dimension.
Indicating the second in the label name vector of the article
The value of the dimension. Here, the range of the relationship information value may retain two significant digits after the decimal point.
As an example, the user tag name vector may be "[ 10001]]". The number of dimensions included in the user tag name vector
Is "5". The target item tag name vector may be "[ 01001]]". Generating a relationship information value by a formula:
as another example, the above-mentioned target item tag name vector set may be "[ 01001], [00101], [01010 ]". The above-mentioned subscriber tag name vector may be "[ 10001 ]". The relationship information value of the target item tag name vector "[ 00101 ]" and the user tag name vector "[ 10001 ]" is "0.83". The relationship information value of the target item tag name vector "[ 01010 ]" and the user tag name vector "[ 10001 ]" is "1".
In some embodiments, the executing entity may generate the item recommendation information table by:
firstly, inputting the user tag score value, each relationship information in the relationship information set, an article tag score value in the article tag score value group corresponding to the relationship information, and an article acquisition score value corresponding to the article tag score value into the following formula to generate an article recommendation score value:
wherein the content of the first and second substances,
indicating an item recommendation score value.
Indicating the user tag score value.
Indicating the item label score value.
And representing the article acquisition frequency value.
A relationship information value representing the relationship information.
Indicating a rounding down operation.
As an example, the user tag score value described above
May be "8". Above item tag score value
May be "7". Frequency value of the above-mentioned article
May be "10". Relation information value of the above relation information
May be "0.83". Generating an item recommendation score value through a formula:
and secondly, combining the item recommendation score value and the item tag name corresponding to the item recommendation score value to generate a binary group.
As an example, the item recommendation score value may be "464". The item tag name corresponding to the item recommendation score value is "didy". Combine "464" with "didi" to generate a doublet (didi, 464).
And thirdly, establishing an empty table, and inputting the binary group into the empty table to generate an article recommendation information table.
As an example, the item recommendation information table may be:
| article tag name | Item recommendation score value |
| Didi (Didi) | 464 |
Optionally, the item recommendation information table is sent to a display device with a display function for display.
In some embodiments, the item recommendation information table "a" may be transmitted to the display device "001" having a display function for display.
Optionally, the related item ordering device is controlled to perform an ordering operation based on the item recommendation information table.
In some embodiments, the execution main body may select an article tag name corresponding to an article recommendation score value having a larger value in the article recommendation information table, and then control the related article ordering apparatus to purchase an article corresponding to the article tag name.
The above embodiments of the present disclosure have the following advantages: first, based on a user information tag of a user, article tag information of each article in an article group to be recommended for the user is acquired, and an article tag information set is obtained. Therefore, the related information of the object to be recommended can be known, and a foundation is laid for generating an object recommendation information table. Next, a user tag name vector and an article tag name vector set may be generated based on the user tag name and the article tag information set. Therefore, a calculation foundation is laid for the distance between the subsequent calculation vectors and the relation information between the vectors. Next, a distance information set is generated based on the user tag name vector and the set of item tag name vectors. Therefore, the tightness degree between the two vectors can be preliminarily judged according to the distance between the vectors, so that the vectors meeting the conditions can be screened out, and a foundation is laid for calculating the relationship information between the vectors in the next step. Then, a relational information set is generated based on the distance information set, the user tag name vector, and the article tag name vector set. Therefore, the degree of association between the user tag name and the article tag name can be determined, and a foundation is further laid for recommending related article information to the user. Finally, an item recommendation information table may be generated based on the relationship information set, the user tag score value, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value. Therefore, good-quality articles can be recommended for the user, customized service is provided for the user, and the shopping experience of the user is improved.
With further reference to fig. 3, a flow 300 of further embodiments of an item information push method for a user according to the present disclosure is shown. The method may be performed by the computing device 101 of fig. 1. The item information pushing method for the user comprises the following steps:
In some embodiments, the specific implementation manner and technical effects of the steps 301 and 302 can refer to the steps 201 and 202 in the embodiments corresponding to fig. 2, which are not described herein again.
In some embodiments, the execution subject may determine distance information between each item tag name vector in the set of item tag name vectors and the user tag name vector by:
in the first step, the number of dimensions included in the user tag name vector is determined as a first dimension measurement.
As an example, the above-mentioned user tag name vector may be "[ 10001 ]". The number of dimensions "5" included in the above-described user tag name vector is determined as a first dimension measure.
And secondly, determining the number of dimensions included in the label name vector of the object as a second dimension measurement.
As an example, the above-mentioned item tag name vector may be "[ 01001 ]". The number of dimensions "5" included in the above-mentioned item tag name vector is determined as the second dimension measure.
And thirdly, determining the sum of the first dimension measurement and the second dimension measurement as a first dimension sum.
As an example, the first dimension metric may be "5". The second dimension may be "5". The sum "10" of "5" and "5" is determined as the first dimensional sum.
And fourthly, determining the average value of each value in each dimension in the user tag name vector and each value in each dimension of the article tag name vector as a vector average value.
As an example, the above-mentioned user tag name vector may be "[ 10001 ]". The item tag name vector may be "[ 01001 ]". The average value of each value in each dimension of the user tag name vector and each value in each dimension of the article tag name vector is "0.4". "0.4" is determined as the vector mean.
A fifth step of generating a distance information value based on the user tag name vector, the item tag name vector, the vector mean, the first dimension metric, the second dimension metric, and the first dimension sum.
In some embodiments, the execution body may generate a distance information value based on the user tag name vector, the article tag name vector, the vector mean, the first dimension metric, the second dimension metric, and the first dimension sum in various ways.
In some optional implementations of some embodiments, the executing entity may generate the distance information value by:
wherein the content of the first and second substances,
indicating a distance information value.
Representing either the first dimension or the second dimension.
Indicating the second in the user tag name vector
The value of the dimension.
Indicating the second in the label name vector of the article
The value of the dimension.
Representing the vector mean.
Representing the first dimension sum. Here, the value of the distance information value may retain two significant digits after the decimal point.
As an example, the first dimension metric or the second dimension metric
May be "5". The user tag name vector may be "[ 10001]]". The item tag name vector may be "[ 01001]]". Mean value of the above vectors
Is "0.4". The first dimensional sum is "10". Generating a distance information value by a formula:
as another example, the user tag name vector may be "[ 10001 ]". The above-mentioned item tag name vector set may be "[ 01001], [00101], [01010 ]". The distance information value between the user tag name vector "[ 10001 ]" and the product tag name vector "[ 00101 ]" is "5.89". The distance information value between the user tag name vector "[ 10001 ]" and the product tag name vector "[ 01010 ]" is "8.33".
And sixthly, determining the distance information value as distance information.
As an example, the distance information value "5.89" may be determined as the distance information "distance information value: 5.89".
And 304, selecting the distance information meeting the first preset condition from the distance information set as target distance information to obtain a target distance information set.
In some embodiments, the execution subject may select, from the distance information sets, distance information meeting a first preset condition as target distance information, to obtain a target distance information set. Here, the first preset condition may be "a distance information value less than 7".
As an example, the above distance information set may be "distance information value: 5.89, distance information value: 5.89, distance information value: 8.33". Selecting distance information with a distance information value smaller than 7 from the distance information set as target distance information to obtain a target distance information set' distance information value: 5.89, distance information value: 5.89".
And 305, determining the object tag name vector corresponding to each piece of object distance information in the object distance information set as an object tag name vector based on the object tag name vector set to obtain an object tag name vector set.
In some embodiments, the execution subject may determine, as the target item tag name vector, an item tag name vector in the set of item tag name vectors corresponding to each of the sets of target distance information, resulting in a set of target item tag name vectors.
As an example, the above target distance information set may be "distance information value: 5.89, distance information value: 5.89". The above-mentioned item tag name vector set may be "[ 01001], [00101], [01010 ]". And determining the object tag name vector in the object tag name vector set corresponding to each object distance information in the object distance information set as an object tag name vector to obtain an object tag name vector set "[ 01001], [00101 ]".
In some embodiments, the execution body may determine the relationship information between the user tag name vector and each target item tag name vector in the set of target item tag name vectors by various methods, resulting in a set of relationship information.
In some optional implementations of some embodiments, the execution subject may determine the relationship information between the user tag name vector and each target item tag name vector in the set of target item tag name vectors by:
firstly, data in each dimension in the user tag name vector and data in each dimension in the target object tag name vector are respectively subjected to overturning processing to generate an overturned user tag name vector and an overturned target object tag name vector.
As an example, the above-described user tag name vector "[ 10001 ]" is subjected to flip processing to generate a flipped user tag name vector "[ 01110 ]". The above-described target item tag name vector "[ 01001 ]" is subjected to flip processing to generate a flipped target item tag name vector "[ 10110 ]".
Second, a relationship information value is generated by the following formula:
wherein the content of the first and second substances,
representing a relationship information value.
The number of dimensions included in the reversed user tag name vector or the number of dimensions included in the reversed article tag name vector.
Indicating the second in the reversed user tag name vector
The value of the dimension.
The second item in the label name vector representing the reversed target item
The value of the dimension.
As an example, the number of dimensions included in the user tag name vector or the number of dimensions included in the item tag name vector
Is "5". The flipped user tag name vector may be "[ 01110]". The above-mentioned reversed target item tag name vector may be "[ 10110]]". Generating a relationship information value by:
as another example, the flipped user tag name vector may be "[ 01110 ]". The above-mentioned reversed target item tag name vector may be "[ 11010 ]". The relationship information value between "[ 01110 ]" and "[ 11010 ]" is "0.98".
And thirdly, determining the relation information value as the relation information.
As an example, the above-described relationship information value "0.98" is determined as the relationship information "relationship information value: 0.98".
The formulas and related contents in steps 303 to 306 serve as an inventive point of the present disclosure, and solve the technical problem mentioned in the background art "generally push the item information of high-volume items to the user, without considering the degree of relation between the user tag and the item tag, resulting in low accuracy of items recommended to the user, and reducing the shopping experience of the user, thereby reducing the user and reducing platform user traffic". Factors that lead to inadequate accuracy of item recommendations tend to be as follows: the existing item recommendation method is used for recommending items to a user according to the hot selling degree of the items, and the degree of relation between a user label and an item label is not considered, so that the accuracy of recommending the items to the user is not high. If the factors are solved, the effect of improving the accuracy of recommending the articles can be achieved. To achieve this, the present disclosure introduces two factors, a distance information value and a relationship information value. First, a distance information value is generated by processing the first dimension metric, the vector mean, and the first dimension sum. Therefore, the distance information values meeting the preset conditions can be screened out, and the corresponding target object label name vectors are determined according to the target distance information values, so that a foundation is laid for further screening the objects to be recommended. Then, data under each dimension in the user tag name vector and the target object tag name vector are respectively turned over, and a foundation is laid for calculating a relation information value between the vectors. And finally, calculating a relation information value between the reversed user tag name vector and the reversed target object tag name vector. Therefore, vectors with the relation information values meeting preset conditions can be screened out, and the effect of accuracy of article recommendation can be preliminarily improved. Therefore, the user experience can be improved preliminarily. Therefore, the effect of improving the platform user flow can be achieved preliminarily.
In some embodiments, the execution subject may select, from the relationship information set, relationship information meeting a second preset condition as target relationship information, to obtain a target relationship information set. Here, the second preset condition may be "a relation information value greater than 0.8".
As an example, from the above-described relationship information set "relationship information value: 0.98, relationship information value: 0.98 ", selecting the relation information corresponding to the relation information value larger than 0.8 as the target relation information to obtain a target relation information set, namely a target relation information value: 0.98, target relationship information value: 0.98".
And 308, determining the item label information corresponding to each item relationship information in the target relationship information set as target item label information to obtain a target item label information set.
In some embodiments, the executing entity may directly determine, as the target article tag information, article tag information corresponding to each target relationship information in the target relationship information set, so as to obtain a target article tag information set.
As an example, the above target relationship information set may be "target relationship information value: 0.98, target relationship information value: 0.98". Determining the article label information in the article label information set corresponding to each piece of object relation information in the object relation information set as object article label information to obtain an object article label information set "{ didy; 7 min; 10 times }; { forest; 6 minutes; 12 times } ".
In some embodiments, the executing entity may directly determine, as the target item tag score value, an item tag score value included in each target item tag information in the target item tag information set, so as to obtain the target item tag score value group.
As an example, the target item tag information set described above may be "{ didy; 7 min; 10 times }; { forest; 6 minutes; 12 times } ". Determine "7" as the target item tag score value. Determine "6" as the target item tag score value. A set of target item tag scores "7, 6" is obtained.
In some embodiments, the executing entity may generate the item recommendation information table by:
the method comprises the steps of firstly, obtaining a frequency value based on the user label scoring value, each target relationship information in the target relationship information set, a target article label scoring value in the target article label scoring value set corresponding to the relationship information and an article corresponding to the target article label scoring value, generating an article recommendation scoring value, and obtaining an article recommendation scoring value set.
In some embodiments, the first step may generate the item recommendation score value by:
wherein the content of the first and second substances,
indicating an item recommendation score value.
And the label scoring value of the target item is represented.
And representing the article acquisition frequency value.
Representing the number of target item tag score values comprised in the set of target item tag score values.
Represents the second of the set of target item tag scores
Individual target item label score values.
Is shown as
And acquiring a frequency value of the article corresponding to the label scoring value of the target article.
Indicating the user tag score value.
Objects representing the above object relation informationA relationship information value. Here, the value of the item recommendation score value may retain two significant digits after the decimal point.
As an example, the above target item tag score value
May be "7". Frequency value of the above-mentioned article
May be "10". The number of the target item label scoring values included in the target item label scoring value group
Is "2". The user tag score value
May be "8". Target relation information value of the target relation information
May be "0.98". Generating an item recommendation score value by:
as another example, the target item tag score value may be "6". The item acquisition frequency value may be "12". The user tag score value may be "8". The target relationship information value of the above-mentioned target relationship information may be "0.98". By the formula, an item recommendation score value of "3.97" is generated.
And secondly, selecting an article recommendation score value meeting a third preset condition from the article recommendation score value group as a target article recommendation score value to obtain the target article recommendation score value group. Here, the third preset condition may be "an item recommendation score value greater than 3.5".
As an example, an item recommendation score value greater than 3.5 is selected from the above item recommendation score value group "3.86, 3.97" as a target item recommendation score value, resulting in a target item recommendation score value group "3.86, 3.97".
And thirdly, combining each target object recommendation score value in the target object recommendation score value group and the object label name corresponding to the target object recommendation score value to generate a binary group, so as to obtain a binary group set.
As an example, the set of target item recommendation scores described above may be "3.86, 3.97". The item tag name corresponding to "3.86" above is "didi". The article tag name corresponding to "3.97" above is "forest". The "3.86" is combined with "didi" to generate a binary "(didi, 3.86)". The "3.97" is combined with the "forest" to generate a binary "(forest, 3.97)". To give a binary set "(didi, 3.86); (forest, 3.97) ".
And fourthly, establishing an empty table, and inputting each binary group in the binary group set into the empty table to generate an article recommendation information table.
As an example, the above-mentioned binary set may be "(didi, 3.86); (forest, 3.97) ". Establishing an empty table, inputting each binary group in the binary group set into the empty table to generate an article recommendation information table:
| article tag name | Item recommendation score value |
| Didi (Didi) | 3.86 |
| Tree forest | 3.97 |
The formula in step 310 is used as an invention point of the disclosure, thereby solving the technical problems mentioned in the background art, namely, the third problem that the item information of the high-sales items is generally pushed to the user, the influence of various factors on the item recommendation result cannot be considered comprehensively, the accuracy of the generated item recommendation scoring value is not high, the accuracy of the items recommended to the user is not high, the shopping experience of the user is reduced, and the reduction of the user and the reduction of the platform user traffic are caused. Factors that lead to poor accuracy in item recommendations tend to be as follows: in the process of recommending the item to the user, the influence of various factors on the item recommendation result cannot be considered comprehensively due to various objective or subjective factors, so that the accuracy of the generated item recommendation score value is not high. If the above factors are solved, the effect of improving the accuracy of item recommendation can be achieved. In order to achieve the effect, the object recommendation method introduces four factors such as the label scoring value of the object, the frequency value of object acquisition, the label scoring value of the user and the object relation information value so as to improve the accuracy of object recommendation. Firstly, the importance degree of the item to be recommended can be preliminarily known by introducing the label scoring value of the target item. And secondly, the articles are quoted to obtain the frequency value, so that the practical degree of the articles to be recommended can be further expressed. Next, referring to the target relationship information value, the degree of association between the user tag name and the article tag name can be displayed. Here, the weight ratio of the item label score value of the item and the item acquisition frequency value is determined by a formula, so that the importance of the item in the item group can be preliminarily determined. Then, the weight, the user label scoring value and the relation information value are multiplied, and the item recommendation scoring value can be accurately generated. Therefore, the articles can be accurately recommended to the user, and the experience of the user is improved. Therefore, the effect of improving the flow of the platform user can be achieved.
The above embodiments of the present disclosure have the following advantages: first, a distance information value is generated by processing the first dimension metric, the vector mean, and the first dimension sum. Therefore, the distance information values meeting the preset conditions can be screened out, and the corresponding target object label name vectors are determined according to the target distance information values, so that a foundation is laid for further screening the objects to be recommended. And secondly, turning over data under each dimension in the user tag name vector and the target object tag name vector respectively, so that a foundation is laid for calculating a relation information value between the vectors. Next, a relationship information value between the reversed user tag name vector and the reversed target article tag name vector is calculated. Therefore, vectors with the relation information values meeting the preset conditions can be screened out. Thus, the effect of the accuracy of item recommendation can be preliminarily improved. Then, the target item label scoring value is introduced, so that the importance degree of the item to be recommended can be preliminarily known. Secondly, the articles are quoted to obtain the frequency value, so that the practical degree of the articles to be recommended can be further known. Finally, the generated target relationship information value may display the degree of association between the user tag name and the article tag name. Through a formula, the four factors are processed, and the item recommendation score value can be accurately generated. Therefore, the articles can be accurately recommended to the user, and the experience of the user is improved. Therefore, the effect of improving the flow of the platform user can be achieved.
With further reference to fig. 4, as an implementation of the methods shown in the above-mentioned figures, the present disclosure provides some embodiments of an article information pushing apparatus for users, which correspond to those of the method embodiments described above in fig. 2, and which can be applied in various electronic devices.
As shown in fig. 4, the item information pushing apparatus 400 for a user of some embodiments includes: an acquisition unit 401, a first generation unit 402, a second generation unit 403, a third generation unit 404, and a fourth generation unit 405. The acquiring unit 401 is configured to acquire, based on a user information tag of a user, article tag information of each article in an article group to be recommended for the user, to obtain an article tag information set, where the article tag information includes an article tag name, an article tag score value corresponding to the article tag name, and an article acquisition frequency value corresponding to the article tag score value, and the user information tag includes a user tag name and a user tag score value corresponding to the user tag name; a first generating unit 402 configured to generate a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set; a second generating unit 403 configured to generate a set of distance information based on the user tag name vector and the set of article tag name vectors; a third generating unit 404 configured to generate a set of relationship information based on the set of distance information, the user tag name vector, and the set of item tag name vectors; a fourth generating unit 405 configured to generate an item recommendation information table based on the relationship information set, the user tag score value, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value.
It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.
Referring now to FIG. 5, a block diagram of an electronic device (e.g., computing device 101 of FIG. 1) 500 suitable for use in implementing some embodiments of the present disclosure 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 disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some 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 some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described above in some embodiments of the present disclosure may 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 some embodiments of the disclosure, 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 some embodiments of the present disclosure, 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: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the apparatus; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring article tag information of each article in an article group to be recommended for a user based on a user information tag of the user to obtain an article tag information set, wherein the article tag information comprises an article tag name, an article tag score value corresponding to the article tag name and an article acquisition frequency value corresponding to the article tag score value, and the user information tag comprises a user tag name and a user tag score value corresponding to the user tag name; generating a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set; generating a distance information set based on the user tag name vector and the article tag name vector set; generating a relationship information set based on the distance information set, the user tag name vector, and the article tag name vector set; and generating an article recommendation information table based on the relationship information set, the user label scoring values, the article label scoring values included in the article label information set and article acquisition frequency values corresponding to the article label scoring values.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
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 disclosure. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a first generation unit, a second generation unit, a third generation unit, and a fourth generation unit. Where the names of these units do not in some cases constitute a limitation of the unit itself, for example, the first generating unit may also be described as "a unit that generates a set of user tag name vectors and item tag name vectors based on the above-mentioned user tag names and the above-mentioned set of item tag information".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (9)
1. An item information pushing method for a user, comprising:
acquiring article tag information of each article in an article group to be recommended for a user based on a user information tag of the user to obtain an article tag information set, wherein the article tag information comprises an article tag name, an article tag scoring value corresponding to the article tag name and an article acquisition frequency value corresponding to the article tag scoring value, and the user information tag comprises a user tag name and a user tag scoring value corresponding to the user tag name;
generating a user tag name vector and an article tag name vector set based on the user tag name and the article tag information set;
generating a set of distance information based on the user tag name vector and the set of item tag name vectors;
generating a set of relationship information based on the set of distance information, the user tag name vector, and the set of item tag name vectors;
generating an article recommendation information table based on the relationship information set, the user tag score values, each article tag score value included in each article tag information in the article tag information set and each article acquisition frequency value corresponding to each article tag score value, wherein distance information meeting a first preset condition is selected from the distance information set as target distance information to obtain a target distance information set;
determining an article tag name vector corresponding to each piece of target distance information in the target distance information set as a target article tag name vector based on the article tag name vector set to obtain a target article tag name vector set;
and determining the relationship information between the user tag name vector and each target object tag name vector in the target object tag name vector set to obtain a relationship information set.
2. The method of claim 1, wherein said generating a set of user tag name vectors and item tag name vectors based on said set of user tag names and said set of item tag information comprises:
vectorizing the user tag name to generate a user tag name vector;
and vectorizing the article tag name included in each article tag information in the article tag information set to generate an article tag name vector, so as to obtain an article tag name vector set.
3. The method of claim 1, wherein said generating a set of distance information based on said user tag name vector and said set of item tag name vectors comprises:
and determining distance information between each article tag name vector in the article tag name vector set and the user tag name vector based on the user tag name vectors to obtain a distance information set.
4. The method of claim 3, wherein said determining distance information between each item tag name vector in said set of item tag name vectors and said user tag name vector comprises:
determining a number of dimensions included in the user tag name vector as a first dimension metric;
determining a number of dimensions included in the item tag name vector as a second dimension metric;
determining a sum of the first dimension metric and the second dimension metric as a first dimension sum;
determining the average value of each value in each dimension in the user tag name vector and each value in each dimension of the article tag name vector as a vector average value;
generating a distance information value based on the user tag name vector, the item tag name vector, the vector mean, the first dimension metric, the second dimension metric, and the first dimension sum;
determining the distance information value as distance information.
5. The method according to claim 1, wherein the generating an item recommendation information table based on the relationship information set, the user tag score value, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value includes:
selecting relation information meeting a second preset condition from the relation information set as target relation information to obtain a target relation information set;
determining article label information corresponding to each target relationship information in the target relationship information set as target article label information to obtain a target article label information set;
determining an article label scoring value included in each piece of target article label information in the target article label information set as a target article label scoring value to obtain a target article label scoring value group;
and acquiring frequency values based on the target relationship information set, the user label scoring values, each target article label scoring value in the target article label scoring value set and each article corresponding to each target article label scoring value, and generating an article recommendation information table.
6. The method of claim 5, wherein generating an item recommendation information table based on the target relationship information set, the user tag score values, each target item tag score value in the set of target item tag score values, and each item acquisition frequency value corresponding to the each target item tag score value comprises:
generating an article recommendation score value based on the user tag score value, each target relationship information in the target relationship information set, a target article tag score value in the target article tag score value group corresponding to the relationship information, and an article acquisition frequency value corresponding to the target article tag score value, so as to obtain an article recommendation score value group;
selecting an article recommendation score value meeting a third preset condition from the article recommendation score value group as a target article recommendation score value to obtain a target article recommendation score value group;
combining each target article recommendation score value in the target article recommendation score value group and the article label name corresponding to the target article recommendation score value to generate a binary group, so as to obtain a binary group set;
establishing an empty table, and inputting each binary in the binary set into the empty table to generate an item recommendation information table.
7. An article information pushing device for a user, comprising:
an acquisition unit configured to acquire, based on a user information tag of a user, item tag information of each item in an item group to be recommended for the user, to obtain an item tag information set, wherein the item tag information includes an item tag name, an item tag score value corresponding to the item tag name, and an item acquisition frequency value corresponding to the item tag score value, and the user information tag includes a user tag name and a user tag score value corresponding to the user tag name;
a first generating unit configured to generate a user tag name vector and a set of item tag name vectors based on the user tag name and the set of item tag information;
a second generating unit configured to generate a set of distance information based on the user tag name vector and the set of item tag name vectors;
a third generating unit configured to generate a set of relationship information based on the set of distance information, the user tag name vector, and the set of item tag name vectors; the third generating unit is further configured to: selecting distance information meeting a first preset condition from the distance information set as target distance information to obtain a target distance information set;
determining an article tag name vector corresponding to each piece of target distance information in the target distance information set as a target article tag name vector based on the article tag name vector set to obtain a target article tag name vector set;
determining the relationship information between the user tag name vector and each target object tag name vector in the target object tag name vector set to obtain a relationship information set;
a fourth generating unit configured to generate an item recommendation information table based on the relationship information set, the user tag score values, each item tag score value included in each item tag information in the item tag information set, and each item acquisition frequency value corresponding to each item tag score value.
8. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
9. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011004904.3A CN111932321B (en) | 2020-09-23 | 2020-09-23 | Method and device for pushing article information for user, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011004904.3A CN111932321B (en) | 2020-09-23 | 2020-09-23 | Method and device for pushing article information for user, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932321A CN111932321A (en) | 2020-11-13 |
| CN111932321B true CN111932321B (en) | 2021-01-05 |
Family
ID=73334014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011004904.3A Expired - Fee Related CN111932321B (en) | 2020-09-23 | 2020-09-23 | Method and device for pushing article information for user, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932321B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446768B (en) * | 2021-02-01 | 2021-07-13 | 北京每日优鲜电子商务有限公司 | Item information recommendation method and device, electronic equipment and computer readable medium |
| CN112529672B (en) * | 2021-02-18 | 2021-06-11 | 北京每日优鲜电子商务有限公司 | Article information pushing method and device, electronic equipment and computer readable medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239993B (en) * | 2017-05-24 | 2020-11-24 | 海南大学 | Matrix decomposition recommendation method and system based on expansion label |
| CN107688984A (en) * | 2017-07-27 | 2018-02-13 | 上海壹账通金融科技有限公司 | Product information method for pushing, device, storage medium and computer equipment |
| CN107911448B (en) * | 2017-11-14 | 2021-10-29 | 北京金山安全软件有限公司 | Content pushing method and device |
| CN108053243A (en) * | 2017-12-12 | 2018-05-18 | 朱明君 | A kind of commercial product recommending system based on community network |
| CN110059271B (en) * | 2019-06-19 | 2020-01-10 | 达而观信息科技（上海）有限公司 | Searching method and device applying tag knowledge network |
-
2020
- 2020-09-23 CN CN202011004904.3A patent/CN111932321B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932321A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112035753B (en) | Recommendation page generation method and device, electronic equipment and computer readable medium | |
| CN111932321B (en) | Method and device for pushing article information for user, electronic equipment and medium | |
| CN112017013B (en) | Target item information display method and device, electronic equipment and computer readable medium | |
| CN112036990B (en) | Article information pushing method and device, electronic equipment and computer readable medium | |
| CN112102043B (en) | Item recommendation page generation method and device, electronic equipment and readable medium | |
| CN112365109B (en) | Distribution path information generation method and device, electronic equipment and readable medium | |
| CN110609783A (en) | Method and device for identifying abnormal behavior user | |
| CN112446768B (en) | Item information recommendation method and device, electronic equipment and computer readable medium | |
| CN111078636A (en) | Marketing data processing method and system and related equipment | |
| CN111737587B (en) | Device operation method, device, electronic device and computer readable medium | |
| CN112561606B (en) | Shelf placement method and device based on user behaviors, electronic equipment and medium | |
| CN113688133B (en) | Data processing method, system, device, medium and equipment based on compliance calculation | |
| CN112547569B (en) | Article sorting equipment control method, device, equipment and computer readable medium | |
| US20230053859A1 (en) | Method and apparatus for outputting information | |
| CN114926234A (en) | Article information pushing method and device, electronic equipment and computer readable medium | |
| CN111177582B (en) | Method, device, electronic equipment and storage medium for determining friend user | |
| CN113762876A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN112200643B (en) | Article information pushing method and device, electronic equipment and computer readable medium | |
| CN113554493A (en) | Interactive ordering method, device, electronic equipment and computer readable medium | |
| CN112085359A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN112529672B (en) | Article information pushing method and device, electronic equipment and computer readable medium | |
| CN113435960A (en) | Virtual article display method and device, electronic equipment and computer readable medium | |
| CN111932191A (en) | Shelf scheduling method and device, electronic equipment and computer readable medium | |
| CN111784377A (en) | Method and apparatus for generating information | |
| CN112381184A (en) | Image detection method, image detection device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211124 Address after: Room 084, No. 1-309, 3rd floor, commercial building, No. 9 Wangjing street, Chaoyang District, Beijing 100102 Patentee after: Beijing Daily Youxian Technology Co.,Ltd. Address before: 100102 room 801, 08 / F, building 7, yard 34, Chuangyuan Road, Chaoyang District, Beijing Patentee before: BEIJING MISSFRESH E-COMMERCE Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210105 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |