CN113434660A - Product recommendation method, device, equipment and storage medium based on multi-domain classification - Google Patents
Product recommendation method, device, equipment and storage medium based on multi-domain classification Download PDFInfo
- Publication number
- CN113434660A CN113434660A CN202110719411.6A CN202110719411A CN113434660A CN 113434660 A CN113434660 A CN 113434660A CN 202110719411 A CN202110719411 A CN 202110719411A CN 113434660 A CN113434660 A CN 113434660A
- Authority
- CN
- China
- Prior art keywords
- product
- products
- recommended
- user
- field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims description 59
- 238000004422 calculation algorithm Methods 0.000 claims description 31
- 230000014509 gene expression Effects 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a data analysis technology, and discloses a product recommendation method based on multi-field classification, which comprises the following steps: analyzing the browsing duration of a user on products belonging to different product fields according to product browsing data, analyzing the intention of the user on different product fields, determining the number of products needing to be pushed to the user in each product field according to the intention and the total recommended number of the products, matching the user with the products in each product field, selecting the products of the number of the products needing to be pushed in the product field according to the matching result, calculating the association degree between the selected products and the user, and recommending the products to the user according to the sequence of the association degrees from large to small. In addition, the invention also relates to a block chain technology, and the product browsing data can be stored in the nodes of the block chain. The invention also provides a product recommendation device, electronic equipment and a storage medium based on multi-domain classification. The invention can improve the diversity of products when recommending the products.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a product recommendation method and device based on multi-domain classification, electronic equipment and a computer-readable storage medium.
Background
Product recommendation is an effective scheme for solving the problem of excessive products in the era of product quantity explosion, and in the era of product quantity explosion, along with the on-line deep development of each industry, products are recommended to users in each different product field, so that for a product supplier integrating multi-field products, how to realize the recommendation of the multi-field products to the users becomes a problem to be solved urgently.
Most of traditional product recommendation methods focus on product recommendation in a single field, namely modeling is performed by using data in the single field, and then product recommendation of a user is achieved.
Disclosure of Invention
The invention provides a product recommendation method and device based on multi-domain classification and a computer readable storage medium, and mainly aims to solve the problem of low product diversity during product recommendation.
In order to achieve the above object, the present invention provides a product recommendation method based on multi-domain classification, which comprises:
the method comprises the steps of obtaining product browsing data of a user, and extracting a plurality of products in the product browsing data and browsing duration of each product;
selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
calculating the intention degree of the user to each product field of the multiple product fields according to the browsing duration and the product field of each product of the multiple products, and collecting the product field of which the intention degree is greater than a preset intention degree threshold value as a field to be recommended;
calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to a preset total recommended quantity of the products and the intention of the user to each product field in the fields to be recommended;
obtaining products to be recommended in each product field in the fields to be recommended, calculating a matching value of a user portrait of the user and the products to be recommended, and selecting products of the recommended number of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and calculating the association degree of each selected product and the user by using a preset association degree algorithm, and pushing the products to the user according to the sequence of the association degrees from large to small.
Optionally, the extracting a plurality of products in the product browsing data and the browsing duration of each product includes:
acquiring a preset time field data format and a product name data format;
identifying the data type of the product browsing data, compiling preset characters into a first regular expression according to the product name data format and compiling the preset characters into a second regular expression according to the time field data format by utilizing a compiler corresponding to the data type;
and extracting the product name in the product browsing data by using the first regular expression, and extracting the browsing duration of each product in the product browsing data by using the second regular expression.
Optionally, the calculating a distance value between the target product and each of a plurality of preset product fields includes:
obtaining product description data of the target product, extracting product keywords of the product description data, and converting the product keywords into product vectors;
acquiring a field vector label corresponding to each preset product field in a plurality of product fields;
and calculating the distance value of the product vector and the field vector label corresponding to each product field by using a preset distance value algorithm.
Optionally, the extracting the product keyword of the product description data includes:
acquiring product description data of each product in the plurality of products, and performing word segmentation processing on the product description data of each product to obtain a product word segmentation set corresponding to the plurality of products;
performing word segmentation processing on the product description data of the target product to obtain a plurality of target words;
selecting one target participle from the target participles one by one, counting a first frequency of the selected target participle in the target participles, and counting a second frequency of the selected target participle in the product participle set;
calculating the criticality of the selected target word segmentation according to the first frequency and the second frequency;
and selecting the target word with the keyword degree larger than a preset key threshold value from the target words as the keyword of the target product.
Optionally, the calculating, according to a preset total recommended number of products and an intention of the user to each product field in the to-be-recommended field, a recommended number of products corresponding to each product field in the to-be-recommended field includes:
summing up the intention degrees of all product fields in the field to be recommended by the user to obtain a total intention degree;
selecting one product field from the fields to be recommended one by one as a target field;
calculating the occupation ratio of the user's intention degree to the target field in the total intention degree;
and multiplying the ratio by the total recommended number of the products to obtain the recommended number of the products in the target field.
Optionally, the calculating a matching value between the pre-constructed user portrait of the user and the product to be recommended includes:
obtaining a product label corresponding to each product in the products to be recommended;
converting the user representation into a user vector and converting the product label into a label vector;
and calculating a matching value between the user vector and a label vector corresponding to the product label of each product by using a preset matching value algorithm.
Optionally, the calculating, by using a preset matching value algorithm, a matching value between the user vector and a tag vector corresponding to a product tag of each product includes:
calculating a matching value between the user vector and a label vector corresponding to a product label of each product by using a matching value algorithm as follows:
wherein P is the match value, x is the user vector, ymAnd the label vector corresponding to the product label of the mth product in the products to be recommended.
In order to solve the above problems, the present invention also provides a product recommendation device based on multi-domain classification, the device comprising:
the data extraction module is used for acquiring product browsing data of a user, extracting a plurality of products in the product browsing data and browsing duration of each product;
the product dividing module is used for selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
the domain screening module is used for calculating the intention of the user to each of the plurality of product domains according to the browsing duration and the product domain of each of the plurality of products, and collecting the product domains with the intention being larger than a preset intention threshold value as the domains to be recommended;
the product quantity calculation module is used for calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to the preset total recommended quantity of the products and the intention degree of the user to each product field in the fields to be recommended;
the product screening module is used for acquiring products to be recommended in each product field in the fields to be recommended, calculating a matching value between a user portrait of the user and the products to be recommended, and selecting products of the recommended quantity of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and the product recommendation module is used for calculating the association degree of each selected product and the user by using a preset association degree algorithm and pushing the products to the user according to the sequence of the association degrees from large to small.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the multi-domain classification-based product recommendation method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the multi-domain classification-based product recommendation method described above.
According to the method and the device for recommending the products, the product fields which are interesting to the user can be analyzed according to the product browsing data of the user, a certain number of products are selected from the product fields which are interesting to the user respectively according to the pre-constructed user portrait, the degree of similarity between the products and the user is considered when the products are recommended to the user, the degree of association between the products and the user is also referred, the products are sorted according to the degree of association, the products in the product fields which are interesting to the user are recommended to the user according to the sorting, and the orderliness and the diversity of product recommendation to the user are improved. Therefore, the product recommendation method, the product recommendation device, the electronic equipment and the computer readable storage medium based on multi-domain classification can solve the problem of low product diversity during product recommendation.
Drawings
Fig. 1 is a schematic flowchart of a product recommendation method based on multi-domain classification according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating the process of extracting a plurality of products and the browsing duration of each product according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating calculation of a recommended quantity of products corresponding to each product field in a to-be-recommended field according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a multi-domain classification-based product recommendation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing the multi-domain classification-based product recommendation method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a product recommendation method based on multi-domain classification. The executing body of the product recommendation method based on multi-domain classification includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiments of the present application. In other words, the multi-domain classification based product recommendation method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flowchart of a product recommendation method based on multi-domain classification according to an embodiment of the present invention is shown. In this embodiment, the method for recommending a product based on multi-domain classification includes:
s1, obtaining product browsing data of the user, and extracting a plurality of products in the product browsing data and browsing duration of each product.
In the embodiment of the invention, the product browsing data of the user comprises browsing time, browsing times, product names and other data when the user browses any product.
For example, the browsing data of the user on the security products, the browsing data of the user on the insurance products, the browsing data of the user on the mobile phone products, the browsing data of the user on the commodity house products, and the like.
The embodiment of the invention can utilize computer sentences (java sentences, python sentences and the like) with data grabbing functions to grab the product browsing data which can be obtained by user authorization from a pre-constructed storage area, wherein the storage area comprises but is not limited to a database, a block chain node and a network cache.
In one practical application scenario of the invention, since the product browsing data of the user contains a large amount of data, if the product browsing data is directly analyzed, a large amount of computing resources are occupied, and the product recommendation efficiency is reduced, therefore, the embodiment of the invention can process the product browsing data to extract a plurality of products in the product browsing data and the browsing duration corresponding to each product, thereby reducing the data size to be analyzed when subsequently recommending the product, and improving the product recommendation efficiency.
In the embodiment of the present invention, referring to fig. 2, the extracting a plurality of products in the product browsing data and the browsing duration of each product includes:
s21, acquiring a preset time field data format and a product name data format;
s22, identifying the data type of the product browsing data, compiling preset characters into a first regular expression according to the product name data format and compiling the preset characters into a second regular expression according to the time field data format by utilizing a compiler corresponding to the data type;
s23, extracting product names in the product browsing data by using the first regular expression, and extracting browsing duration of each product in the product browsing data by using the second regular expression.
In detail, in the product browsing data, the data format of the product name and the product browsing duration is often preset by the supplier, the agent, and the like of the product, so the data format is generally fixed.
For example, the browsing duration of the product is expressed in a format of "xx hours xx minutes xx seconds", and further, the embodiment of the present invention may acquire a product name data format for expressing a product name provided by a supplier or an agent, and a time field data format for expressing the browsing duration of the product.
Specifically, since the obtained product browsing data may be expressed in multiple data types, a java statement with a data type detection function may be used to identify the data type of the product browsing data, and then a compiler corresponding to the data type of the product browsing data is selected to compile preset characters into a first regular expression according to the product name data format, and a second regular expression according to the time field data format, and a compiler corresponding to the data type of the product browsing data is selected to compile the preset characters, so that the availability of the compiled regular expressions can be improved.
According to the embodiment of the invention, the product name in the product browsing data and the browsing duration of each product in the product browsing data are extracted by using the first regular expression and the second regular expression, so that the content of the product browsing data can be prevented from being analyzed, and the efficiency of extracting a plurality of products in the product browsing data and the browsing duration of each product can be improved.
S2, one of the products is selected from the multiple products one by one to serve as a target product, the distance value between the target product and each of the multiple preset product fields is calculated, and the product field with the distance value smaller than a preset distance threshold value is determined to serve as the product field of the target product.
In the embodiment of the invention, in order to realize the combined product recommendation of multiple product fields for a user and improve the comprehensiveness of the product recommendation for the user, one product can be selected from the extracted multiple products one by one as a target product, the distance value between the target product and each preset product field in the multiple product fields is calculated, and then the product field of the target product is judged according to the distance value until the product field of each product in the multiple products is determined.
In an embodiment of the present invention, the calculating a distance value between the target product and each of a plurality of preset product fields includes:
obtaining product description data of the target product, extracting product keywords of the product description data, and converting the product keywords into product vectors;
acquiring a field vector label corresponding to each preset product field in a plurality of product fields;
and calculating the distance value of the product vector and the field vector label corresponding to each product field by using a preset distance value algorithm.
In detail, the product description data may be provided in advance by a supplier or an agent of the target product.
In an embodiment of the present invention, the extracting the product keyword of the product description data includes:
acquiring product description data of each product in the plurality of products, and performing word segmentation processing on the product description data of each product to obtain a product word segmentation set corresponding to the plurality of products;
performing word segmentation processing on the product description data of the target product to obtain a plurality of target words;
selecting one target participle from the target participles one by one, counting a first frequency of the selected target participle in the target participles, and counting a second frequency of the selected target participle in the product participle set;
calculating the criticality of the selected target word segmentation according to the first frequency and the second frequency;
and selecting the target word with the keyword degree larger than a preset key threshold value from the target words as the keyword of the target product.
In detail, the first frequency refers to the number of times that the selected target participle appears in the plurality of target participles, and the second frequency refers to the number of times that the selected target participles appear in the product participle set.
Specifically, the calculating the criticality of the selected target word segmentation according to the first frequency and the second frequency includes:
calculating the criticality of the selected target word segmentation by using a criticality algorithm as follows:
K＝W+f1-f2
wherein K is the criticality, W is a preset coefficient, f1Is said first frequency, f2Is the second frequency.
In the embodiment of the invention, the keyword can be converted into the product vector by using a preset vector conversion model, the vector conversion model comprises but is not limited to a word2vec model and a bert model, and the keyword can be digitalized by converting the keyword into the product vector, so that the efficiency of performing data analysis according to the keyword subsequently can be improved.
In the embodiment of the invention, the field vector label is a vector constructed by keywords, hot words and the like of different product fields in advance.
Further, the calculating the distance value of the product vector and the field vector label corresponding to each product field by using a preset distance value algorithm includes:
calculating the distance value of the product vector and the field vector label corresponding to each product field by using the following distance value algorithm:
wherein D is the distance value, a is the product vector, biAnd the field vector label corresponds to the ith product field in the plurality of product fields.
In other embodiments of the present invention, the distance value between the product vector and the field vector tag corresponding to each product field may be calculated by using algorithms having a distance value calculation function, such as an euclidean distance algorithm, a cosine distance algorithm, and the like.
In the embodiment of the present invention, after calculating the distance value between the target product and each of the preset plurality of product fields, it is determined that the product field in which the distance value is smaller than the preset distance threshold is the product field of the target product.
For example, there are product a and product B in the plurality of products, and the predetermined plurality of product fields include product field X and product field Y; sequentially selecting the products A from the plurality of products one by one as target products, calculating to obtain that the distance value between the product A and the product field X is 80, calculating to obtain that the distance value between the product A and the product field Y is 20, and when the preset distance threshold value is 70, determining that the product field of the product A is the product field X;
similarly, sequentially selecting the products B from the plurality of products one by one as target products, calculating to obtain that the distance value between the product B and the product field X is 40, calculating to obtain that the distance value between the product B and the product field Y is 75, and when the preset distance threshold is 70, determining that the product field of the product B is the product field Y.
S3, according to the browsing duration and the product field of each product in the multiple products, calculating the intention of the user to each product field in the multiple product fields, and collecting the product fields with the intention larger than a preset intention threshold value as fields to be recommended.
In the embodiment of the invention, when the browsing time length of the user to the products in a certain product field is longer, the user can be confirmed to be more interested in the products in the product field, that is, the intention degree of the user to the product field is larger, so the intention degree of the user to each product field can be calculated according to the browsing time length of the user to the products in each product field.
In an embodiment of the present invention, the calculating an intention degree of the user to each of the plurality of product fields according to the browsing duration includes:
according to the user's intention for each of the plurality of product areas using an intention algorithm as follows:
wherein, YkFor the user's intention, X, for the kth one of the plurality of product fieldsnAnd N is the product quantity of the products belonging to the kth product field in the plurality of products.
Further, the product fields with the intention degree larger than the preset intention degree threshold value in the multiple product fields are collected to obtain the field to be recommended.
For example, the plurality of product fields include a product field a, a product field B, a product field C, and a product field D, and it is calculated that the intention of the user to the product field a is 10, the intention of the user to the product field B is 70, the intention of the user to the product field C is 50, the intention of the user to the product field D is 90, and when the preset intention threshold is 60, the product field B and the product field D are collected as the to-be-recommended field.
S4, calculating the product recommendation quantity corresponding to each product field in the to-be-recommended field according to the preset product recommendation total number and the user intention degree to each product field in the to-be-recommended field.
In the embodiment of the invention, because the intention degrees of the users to different product fields in the fields to be recommended are different, when the users recommend products in multiple fields, the quantity of the products to be recommended in each product field can be confirmed according to the intention degree of the users to each product field when the users recommend the products, so that the reasonable distribution of the products in different product fields can be ensured when the users recommend the products.
In the embodiment of the present invention, referring to fig. 3, calculating the recommended quantity of products corresponding to each product field in the to-be-recommended field according to a preset total recommended quantity of products and an intention of the user to each product field in the to-be-recommended field includes:
s31, summing the intention degrees of all product fields in the field to be recommended by the user to obtain a total intention degree;
s32, selecting one of the product fields as a target field one by one from the fields to be recommended;
s33, calculating the ratio of the user' S intention degree to the target field in the total intention degree;
and S34, multiplying the ratio by the total recommended number of the products to obtain the recommended number of the products in the target field.
For example, the domain to be recommended includes a domain a, a domain B, and a domain C, where the user's intention to the domain a is 20, the user's intention to the domain B is 30, and the user's intention to the domain C is 50, it is known that the total intention of the user to all product domains in the domain to be recommended is 100, the ratio of the user's intention to the domain a in the total intention is 20%, the ratio of the user's intention to the domain B in the total intention is 30%, the ratio of the user's intention to the domain C in the total intention is 50%, and when the preset total number of product recommendations is 10, the number of product recommendations corresponding to the domain a is determined as: 10 by 20 ═ 2, the recommended number of products corresponding to domain B is: 10 × 30% ═ 3, the recommended number of products corresponding to domain C is: 10 × 50% ═ 5 pieces.
S5, obtaining products to be recommended in each product field in the fields to be recommended, calculating a matching value of the user portrait of the user and the products to be recommended, and selecting products of the recommended quantity of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value.
In the embodiment of the invention, the product to be recommended in each product field in the field to be recommended can be preset by a supplier of the product, for example, if the field to be recommended includes an electronic product field, an insurance product field and a security investment product field, a plurality of electronic products such as mobile phones, computers and cameras in the electronic product field can be obtained as the product to be recommended in the electronic product field; acquiring various insurance products such as property insurance, disease insurance, travel insurance and the like in the field of insurance products as products to be recommended in the field of the insurance products; and acquiring a plurality of stock investment products such as stocks, funds, futures and the like in the field of the stock investment products as products to be recommended in the field of the stock investment products.
In the embodiment of the invention, the matching value of the pre-constructed user portrait and the products to be recommended can be calculated, and then the products with the recommended quantity of the products corresponding to each product field in the fields to be recommended are selected from the products to be recommended in each product field in the fields to be recommended according to the matching value.
Specifically, the user image is a data image that is generated in advance based on information such as the age, occupation, and asset condition of the user and that identifies the characteristics of the user.
In the embodiment of the present invention, the calculating a matching value between the pre-constructed user portrait of the user and the product to be recommended includes:
obtaining a product label corresponding to each product in the products to be recommended;
converting the user representation into a user vector and converting the product label into a label vector;
and calculating a matching value between the user vector and a label vector corresponding to the product label of each product by using a preset matching value algorithm.
In detail, the product label is a label which is generated by data such as a name of a product, a product field, a product description and the like in advance and is used for marking the content of the product.
Specifically, the step of converting the user representation into a user vector and the step of converting the product label into a label vector are the same as the step of converting the product keyword into a product vector in S2, which is not repeated herein.
In the embodiment of the present invention, the calculating, by using a preset matching value algorithm, a matching value between the user vector and a tag vector corresponding to a product tag of each product includes:
calculating a matching value between the user vector and a label vector corresponding to a product label of each product by using a matching value algorithm as follows:
wherein P is the match value, x is the user vector, ymAnd the label vector corresponding to the product label of the mth product in the products to be recommended.
Further, the recommended number of products corresponding to each product field in the field to be recommended can be selected from the products to be recommended in each product field in the field to be recommended according to the matching value.
For example, there are a domain A and a domain B in the domain to be recommended, wherein the product to be recommended corresponding to the domain A includes a product a1、a2、a3Wherein, the product a1Matching value with user's picture is 10, product a2Match value with user's picture is 20, product a3The matching value with the user image is 30; the product to be recommended corresponding to the field B comprises B1、b2、b3、b4、b5Wherein, product b1Match value with user's picture is 22, product b2Matching value with user's picture 33, product b3Match value with user's picture is 44, product b4Match value with user image is 55, product b5The matching value with the user image is 66; when the recommended quantity of the products corresponding to the field A is as follows: 2, when the recommended number of the products corresponding to the field B is 3, selecting the product a from the products to be recommended corresponding to the field A according to the sequence of the matching values from large to small2And a3Selecting a product B from the products to be recommended corresponding to the field B3、b4And b5。
In the embodiment of the invention, the product is selected from the products to be recommended in each field to be recommended according to the matching value, so that the adaptability of the selected product to the user can be improved, and the product recommendation accuracy of the user is further improved.
S6, calculating the association degree of each selected product and the user by using a preset association degree algorithm, and pushing the products to the user according to the sequence of the association degrees from large to small.
In one practical application scenario of the invention, a plurality of products in a plurality of product fields need to be used for recommending products to a user, in order to better recommend products to the user and improve the accuracy of product recommendation, a plurality of products need to be sorted, but if the products are sorted only by using the matching degree of the products and the user, the products with higher association degree with the user may be arranged behind, therefore, the embodiment of the invention uses a preset association degree algorithm to calculate the association degree of each selected product with the user, and recommends the products to the user according to the sequence of the association degrees from large to small.
In detail, the calculating the association degree of each selected product with the user by using a preset association degree algorithm includes:
calculating the relevance of each selected product to the user by using the following relevance algorithm:
MMR＝arg[α*(sim1(Di,Q)),(1-α)*(sim2(Di,Dj))]i,j∈R
wherein MMR is the degree of association, R is the set of all selected products, DiIs the ith product in R, DjSet of all products selected, DiFor the jth product in R, Q is the user portrait, sim1(DiQ) is DjAnd similarity between Q, sim2(Di,Dj) Is DiAnd DjThe similarity between the two is alpha, which is a preset weight coefficient, and arg is the averaging operation.
In the embodiment of the invention, after the association degree between each selected product and the user is obtained through calculation, the selected products can be arranged according to the sequence from the big to the small of the association degree, and the products are recommended to the user according to the arranged sequence.
Fig. 4 is a functional block diagram of a product recommendation apparatus based on multi-domain classification according to an embodiment of the present invention.
The multi-domain classification-based product recommendation device 100 of the present invention may be installed in an electronic device. According to the implemented functions, the multi-domain classification-based product recommendation apparatus 100 may include a data extraction module 101, a product division module 102, a domain screening module 103, a product quantity calculation module 104, a product screening module 105, and a product recommendation module 106. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the data extraction module 101 is configured to obtain product browsing data of a user, extract a plurality of products in the product browsing data, and extract a browsing duration of each product;
the product dividing module 102 is configured to select one of the products one by one from the multiple products as a target product, calculate a distance value between the target product and each of multiple preset product fields, and determine a product field of which the distance value is smaller than a preset distance threshold as a product field of the target product;
the domain screening module 103 is configured to calculate an intention degree of the user for each of the plurality of product domains according to the browsing duration and the product domain of each of the plurality of products, and collect the product domain with the intention degree larger than a preset intention degree threshold as a domain to be recommended;
the product quantity calculation module 104 is configured to calculate a product recommendation quantity corresponding to each product field in the to-be-recommended field according to a preset product recommendation total number and an intention degree of the user to each product field in the to-be-recommended field;
the product screening module 105 is configured to obtain a product to be recommended in each product field in the field to be recommended, calculate a matching value between a user image of the user and the product to be recommended, and select, according to the matching value, a product recommended amount corresponding to each product field in the field to be recommended from the products to be recommended in each product field in the field to be recommended;
the product recommendation module 106 is configured to calculate the association degree between each selected product and the user by using a preset association degree algorithm, and push the products to the user according to a sequence of the association degrees from large to small.
In detail, when the modules in the multi-domain classification-based product recommendation apparatus 100 according to the embodiment of the present invention are used, the same technical means as the multi-domain classification-based product recommendation method described in fig. 1 to 3 are adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 5 is a schematic structural diagram of an electronic device implementing a multi-domain classification-based product recommendation method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a multi-domain classification based product recommendation program, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory 11 (for example, executing a product recommendation program based on multi-domain classification, etc.), and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of product recommendation programs based on multi-domain classification, etc., but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The multi-domain classification based product recommendation program stored in the memory 11 of the electronic device 1 is a combination of instructions, which when executed in the processor 10, can implement:
the method comprises the steps of obtaining product browsing data of a user, and extracting a plurality of products in the product browsing data and browsing duration of each product;
selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
calculating the intention degree of the user to each product field of the multiple product fields according to the browsing duration and the product field of each product of the multiple products, and collecting the product field of which the intention degree is greater than a preset intention degree threshold value as a field to be recommended;
calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to a preset total recommended quantity of the products and the intention of the user to each product field in the fields to be recommended;
obtaining products to be recommended in each product field in the fields to be recommended, calculating a matching value of a user portrait of the user and the products to be recommended, and selecting products of the recommended number of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and calculating the association degree of each selected product and the user by using a preset association degree algorithm, and pushing the products to the user according to the sequence of the association degrees from large to small.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
the method comprises the steps of obtaining product browsing data of a user, and extracting a plurality of products in the product browsing data and browsing duration of each product;
selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
calculating the intention degree of the user to each product field of the multiple product fields according to the browsing duration and the product field of each product of the multiple products, and collecting the product field of which the intention degree is greater than a preset intention degree threshold value as a field to be recommended;
calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to a preset total recommended quantity of the products and the intention of the user to each product field in the fields to be recommended;
obtaining products to be recommended in each product field in the fields to be recommended, calculating a matching value of a user portrait of the user and the products to be recommended, and selecting products of the recommended number of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and calculating the association degree of each selected product and the user by using a preset association degree algorithm, and pushing the products to the user according to the sequence of the association degrees from large to small.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A product recommendation method based on multi-domain classification is characterized by comprising the following steps:
the method comprises the steps of obtaining product browsing data of a user, and extracting a plurality of products in the product browsing data and browsing duration of each product;
selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
calculating the intention degree of the user to each product field of the multiple product fields according to the browsing duration and the product field of each product of the multiple products, and collecting the product field of which the intention degree is greater than a preset intention degree threshold value as a field to be recommended;
calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to a preset total recommended quantity of the products and the intention of the user to each product field in the fields to be recommended;
obtaining products to be recommended in each product field in the fields to be recommended, calculating a matching value of a user portrait of the user and the products to be recommended, and selecting products of the recommended number of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and calculating the association degree of each selected product and the user by using a preset association degree algorithm, and pushing the products to the user according to the sequence of the association degrees from large to small.
2. The method for recommending products based on multi-domain classification according to claim 1, wherein said extracting a plurality of products in said product browsing data and a browsing duration of each product comprises:
acquiring a preset time field data format and a product name data format;
identifying the data type of the product browsing data, compiling preset characters into a first regular expression according to the product name data format and compiling the preset characters into a second regular expression according to the time field data format by utilizing a compiler corresponding to the data type;
and extracting the product name in the product browsing data by using the first regular expression, and extracting the browsing duration of each product in the product browsing data by using the second regular expression.
3. The method of claim 1, wherein the calculating the distance value between the target product and each of the predetermined product fields comprises:
obtaining product description data of the target product, extracting product keywords of the product description data, and converting the product keywords into product vectors;
acquiring a field vector label corresponding to each preset product field in a plurality of product fields;
and calculating the distance value of the product vector and the field vector label corresponding to each product field by using a preset distance value algorithm.
4. The multi-domain classification-based product recommendation method according to claim 3, wherein the extracting the product keywords of the product description data comprises:
acquiring product description data of each product in the plurality of products, and performing word segmentation processing on the product description data of each product to obtain a product word segmentation set corresponding to the plurality of products;
performing word segmentation processing on the product description data of the target product to obtain a plurality of target words;
selecting one target participle from the target participles one by one, counting a first frequency of the selected target participle in the target participles, and counting a second frequency of the selected target participle in the product participle set;
calculating the criticality of the selected target word segmentation according to the first frequency and the second frequency;
and selecting the target word with the keyword degree larger than a preset key threshold value from the target words as the keyword of the target product.
5. The multi-domain classification-based product recommendation method according to claim 1, wherein the calculating of the product recommendation number corresponding to each product domain in the to-be-recommended domain according to a preset product recommendation total number and the user's intention degree for each product domain in the to-be-recommended domain comprises:
summing up the intention degrees of all product fields in the field to be recommended by the user to obtain a total intention degree;
selecting one product field from the fields to be recommended one by one as a target field;
calculating the occupation ratio of the user's intention degree to the target field in the total intention degree;
and multiplying the ratio by the total recommended number of the products to obtain the recommended number of the products in the target field.
6. The multi-domain classification-based product recommendation method according to any one of claims 1 to 5, wherein the calculating a matching value of the pre-constructed user representation of the user and the product to be recommended comprises:
obtaining a product label corresponding to each product in the products to be recommended;
converting the user representation into a user vector and converting the product label into a label vector;
and calculating a matching value between the user vector and a label vector corresponding to the product label of each product by using a preset matching value algorithm.
7. The multi-domain classification-based product recommendation method according to claim 6, wherein the calculating the matching value between the user vector and the tag vector corresponding to the product tag of each product by using a preset matching value algorithm comprises:
calculating a matching value between the user vector and a label vector corresponding to a product label of each product by using a matching value algorithm as follows:
wherein P is the match value, x is the user vector, ymAnd the label vector corresponding to the product label of the mth product in the products to be recommended.
8. A product recommendation device based on multi-domain classification, the device comprising:
the data extraction module is used for acquiring product browsing data of a user, extracting a plurality of products in the product browsing data and browsing duration of each product;
the product dividing module is used for selecting one of the products one by one from the products as a target product, calculating a distance value between the target product and each of a plurality of preset product fields, and determining the product field with the distance value smaller than a preset distance threshold value as the product field of the target product;
the domain screening module is used for calculating the intention of the user to each of the plurality of product domains according to the browsing duration and the product domain of each of the plurality of products, and collecting the product domains with the intention being larger than a preset intention threshold value as the domains to be recommended;
the product quantity calculation module is used for calculating the recommended quantity of products corresponding to each product field in the fields to be recommended according to the preset total recommended quantity of the products and the intention degree of the user to each product field in the fields to be recommended;
the product screening module is used for acquiring products to be recommended in each product field in the fields to be recommended, calculating a matching value between a user portrait of the user and the products to be recommended, and selecting products of the recommended quantity of the products corresponding to each product field in the fields to be recommended from the products to be recommended in each product field in the fields to be recommended according to the matching value;
and the product recommendation module is used for calculating the association degree of each selected product and the user by using a preset association degree algorithm and pushing the products to the user according to the sequence of the association degrees from large to small.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for multi-domain classification based product recommendation of any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the multi-domain classification-based product recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110719411.6A CN113434660A (en) | 2021-06-28 | 2021-06-28 | Product recommendation method, device, equipment and storage medium based on multi-domain classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110719411.6A CN113434660A (en) | 2021-06-28 | 2021-06-28 | Product recommendation method, device, equipment and storage medium based on multi-domain classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113434660A true CN113434660A (en) | 2021-09-24 |
Family
ID=77754990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110719411.6A Pending CN113434660A (en) | 2021-06-28 | 2021-06-28 | Product recommendation method, device, equipment and storage medium based on multi-domain classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113434660A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113886708A (en) * | 2021-10-26 | 2022-01-04 | 平安银行股份有限公司 | Product recommendation method, device, equipment and storage medium based on user information |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243638A1 (en) * | 2007-03-30 | 2008-10-02 | Chan James D | Cluster-based categorization and presentation of item recommendations |
| US20130166564A1 (en) * | 2011-12-27 | 2013-06-27 | Alibaba Group Holding Limited | Providing information recommendations based on determined user groups |
| CN105719163A (en) * | 2016-01-20 | 2016-06-29 | 四川长虹电器股份有限公司 | Commodity recommending method based on user browsing records |
| USRE46973E1 (en) * | 2001-05-07 | 2018-07-31 | Ureveal, Inc. | Method, system, and computer program product for concept-based multi-dimensional analysis of unstructured information |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| US20190018900A1 (en) * | 2017-07-14 | 2019-01-17 | Alibaba Group Holding Limited | Method and Apparatus for Displaying Search Results |
| CN109522345A (en) * | 2018-11-19 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | For showing the method and device of information |
| CN109886772A (en) * | 2019-01-16 | 2019-06-14 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| WO2019134274A1 (en) * | 2018-01-05 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Interest exploration method, storage medium, electronic device and system |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | E-commerce platform commodity recommendation method and system based on user dynamic classification |
| CN112348629A (en) * | 2020-10-26 | 2021-02-09 | 邦道科技有限公司 | Commodity information pushing method and device |
| CN112559923A (en) * | 2020-12-16 | 2021-03-26 | 平安银行股份有限公司 | Website resource recommendation method and device, electronic equipment and computer storage medium |
-
2021
- 2021-06-28 CN CN202110719411.6A patent/CN113434660A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| USRE46973E1 (en) * | 2001-05-07 | 2018-07-31 | Ureveal, Inc. | Method, system, and computer program product for concept-based multi-dimensional analysis of unstructured information |
| US20080243638A1 (en) * | 2007-03-30 | 2008-10-02 | Chan James D | Cluster-based categorization and presentation of item recommendations |
| US20130166564A1 (en) * | 2011-12-27 | 2013-06-27 | Alibaba Group Holding Limited | Providing information recommendations based on determined user groups |
| CN105719163A (en) * | 2016-01-20 | 2016-06-29 | 四川长虹电器股份有限公司 | Commodity recommending method based on user browsing records |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| US20190018900A1 (en) * | 2017-07-14 | 2019-01-17 | Alibaba Group Holding Limited | Method and Apparatus for Displaying Search Results |
| WO2019134274A1 (en) * | 2018-01-05 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Interest exploration method, storage medium, electronic device and system |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| CN109522345A (en) * | 2018-11-19 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | For showing the method and device of information |
| CN109886772A (en) * | 2019-01-16 | 2019-06-14 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | E-commerce platform commodity recommendation method and system based on user dynamic classification |
| CN112348629A (en) * | 2020-10-26 | 2021-02-09 | 邦道科技有限公司 | Commodity information pushing method and device |
| CN112559923A (en) * | 2020-12-16 | 2021-03-26 | 平安银行股份有限公司 | Website resource recommendation method and device, electronic equipment and computer storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113886708A (en) * | 2021-10-26 | 2022-01-04 | 平安银行股份有限公司 | Product recommendation method, device, equipment and storage medium based on user information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
| CN112732915A (en) | Emotion classification method and device, electronic equipment and storage medium | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN114912948B (en) | Cloud service-based cross-border e-commerce big data intelligent processing method, device and equipment | |
| CN112883190A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113435202A (en) | Product recommendation method and device based on user portrait, electronic equipment and medium | |
| CN113592605B (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN113360768A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN112528616A (en) | Business form generation method and device, electronic equipment and computer storage medium | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113362162A (en) | Wind control identification method and device based on network behavior data, electronic equipment and medium | |
| CN113868528A (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN113656690A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN114398557A (en) | Information recommendation method and device based on double portraits, electronic equipment and storage medium | |
| CN112507230A (en) | Webpage recommendation method and device based on browser, electronic equipment and storage medium | |
| CN113868529A (en) | Knowledge recommendation method and device, electronic equipment and readable storage medium | |
| CN116362684A (en) | Library cluster-based book management method, library cluster-based book management device, library cluster-based book management equipment and storage medium | |
| CN113850643A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113343102A (en) | Data recommendation method and device based on feature screening, electronic equipment and medium | |
| CN113434660A (en) | Product recommendation method, device, equipment and storage medium based on multi-domain classification | |
| CN114708073B (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN115238179A (en) | Project pushing method and device, electronic equipment and computer readable storage 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |