CN113886708A - Product recommendation method, device, equipment and storage medium based on user information - Google Patents
Product recommendation method, device, equipment and storage medium based on user information Download PDFInfo
- Publication number
- CN113886708A CN113886708A CN202111250134.5A CN202111250134A CN113886708A CN 113886708 A CN113886708 A CN 113886708A CN 202111250134 A CN202111250134 A CN 202111250134A CN 113886708 A CN113886708 A CN 113886708A
- Authority
- CN
- China
- Prior art keywords
- user
- product
- keywords
- information
- subset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention relates to a data analysis technology, and discloses a product recommendation method based on user information, which comprises the following steps: extracting user keywords of user group information; similar words are amplified for the user keywords, and a keyword subset of the user keywords is constructed; acquiring product information, and extracting product keywords in the product information; respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each product information, and collecting products corresponding to the product keywords with the association degrees larger than a preset first threshold value as products to be screened; and calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a second threshold value to the users corresponding to the user group information. In addition, the invention also relates to a block chain technology, and the user group information can be stored in the nodes of the block chain. The invention also provides a product recommendation device, equipment and a medium based on the user information. The invention can improve the diversity of product recommendation.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a product recommendation method and device based on user information, electronic equipment and a computer-readable storage medium.
Background
With the diversification of the demands of people, product suppliers provide more and more products on the market, but in order to provide better consumer experience for users and improve the popularization degree of products, users who accord with the products need to be screened from massive users so as to recommend the products.
The existing product recommendation technology is mostly based on single characteristics to realize the matching of users and products, and further carries out product recommendation on the users. For example, applicable products are recommended to users of different age groups based on age attributes. In practical application, the coverage of the product characteristics on the whole product information is not comprehensive enough, and the product characteristics cannot cover all the information of the product, so that product recommendation is performed on a user only by means of a single characteristic, and the product diversity is low during product recommendation.
Disclosure of Invention
The invention provides a product recommendation method and device based on user information and a computer readable storage medium, and mainly aims to solve the problem that the product diversity is low when product recommendation is carried out.
In order to achieve the above object, the present invention provides a product recommendation method based on user information, comprising:
acquiring user group information, and extracting user keywords of the user group information;
similar word amplification is carried out on the user keywords, and a keyword subset of the user keywords after similar word amplification is constructed;
the method comprises the steps of obtaining product information of a plurality of products, and extracting product keywords of each product information in the product information;
respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by using a pre-constructed relation analysis model, and collecting the products corresponding to the product keywords with the association degree larger than a preset first threshold value as products to be screened;
and calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
Optionally, the extracting the user keyword of the user group information includes:
carrying out nonsense word deletion on the user group information to obtain standard user information;
performing word segmentation processing on the standard user information by using a preset dictionary to obtain user word segmentation;
selecting one word from the user words as a target word one by one, and counting the position information of the target word in the user group information and the frequency of the target word in the user words;
and calculating key values of the target word segmentation according to the position information and the frequency, and collecting the target word segmentation with the key value larger than a preset key threshold value as a user keyword.
Optionally, the performing similar word amplification on the user keyword includes:
performing vector conversion on the user keywords to obtain a keyword vector corresponding to each user keyword;
selecting one word vector from the keyword vectors one by one as a target vector;
respectively calculating distance values between the target vector and word vectors corresponding to a plurality of standard words in a preset standard word list;
selecting the standard words with the distance values smaller than a preset distance threshold value in the standard word list as similar words of the user keywords corresponding to the target vector, and collecting the similar words and the user keywords.
Optionally, the constructing a keyword subset of the user keywords after similar word amplification includes:
selecting one of the user keywords as a target keyword one by one from the user keywords amplified by the similar words;
selecting a preset number of user keywords from the user keywords after similar word amplification and collecting the user keywords and the target keywords to obtain a target subset until the target subset corresponding to all the keywords in the user keywords is generated;
and calculating the contact ratio between every two target subsets corresponding to all the keywords, and performing repeated subset deletion on the target subsets corresponding to all the keywords according to the contact ratio to obtain the keyword subsets.
Optionally, the calculating the coincidence degree between each subset in the target subset includes:
calculating the overlap ratio between each subset in the target subset by using an overlap ratio algorithm as follows:
wherein f (k, h) is the degree of coincidence between the kth target subset and the h target subset in the target subsets, MkIs the number of keywords in the kth target subset, NhThe number of repeated keywords in the h-th target subset and the k-th target subset.
Optionally, the analyzing the association degree between each subset of the keyword subsets and the product keyword corresponding to each product information respectively includes:
selecting one subset from the keyword subsets one by one as a subset to be analyzed, and selecting a product keyword corresponding to one product from the plurality of products one by one as a keyword to be analyzed;
performing convolution and pooling on the subset to be analyzed and the keywords to be analyzed by using a pre-constructed relational analysis model to obtain subset characteristics of the subset to be analyzed and word characteristics of the keywords to be analyzed;
and calculating the similarity between the subset characteristics and the word characteristics, and taking the similarity as the association degree between the subset to be analyzed and the keywords to be analyzed.
Optionally, the calculating a matching value between the user group information and the product information of each of the products to be screened includes:
counting symbol position information of a preset sentence break symbol in the user group information and the product information of each product of the products to be screened;
according to the symbol position information, performing clause processing on the user group information to obtain user clauses, and performing clause processing on the product information of each product of the products to be screened to obtain product clauses of each product;
converting the user clauses into user vectors, and collecting the user vectors as a user matrix;
converting the product clauses into product vectors, and collecting the product vectors as a product matrix;
and calculating the matching value of the user matrix and the product matrix by using a preset matching value algorithm.
In order to solve the above problem, the present invention further provides a product recommendation apparatus based on user information, the apparatus comprising:
the first keyword extraction module is used for acquiring user group information and extracting user keywords of the user group information;
the similar word amplification module is used for performing similar word amplification on the user keywords and constructing a keyword subset of the user keywords after similar word amplification;
the second keyword extraction module is used for acquiring product information of a plurality of products and extracting a product keyword of each product information in the product information;
the relevancy analysis module is used for respectively analyzing the relevancy of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by utilizing a pre-constructed relationship analysis model, and collecting the products corresponding to the product keywords with the relevancy greater than a preset first threshold as the products to be screened;
and the product recommending module is used for calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
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 product recommendation method based on the user information.
In order to solve the above problem, the present invention further provides a computer-readable storage medium having at least one instruction stored therein, where the at least one instruction is executed by a processor in an electronic device to implement the user information based product recommendation method described above.
The embodiment of the invention can extract the user keywords from the user information, amplify the similar words of the user keywords to extract the potential or related semantic information of the user keywords, match the amplified keywords with the product, and is beneficial to improving the diversity of the matched product. Therefore, the product recommendation method, the product recommendation device, the electronic equipment and the computer readable storage medium based on the user information can solve the problem of low product diversity during product recommendation.
Drawings
Fig. 1 is a flowchart illustrating a product recommendation method based on user information according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for analyzing relevance according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a process of calculating a matching value according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a product recommendation device based on user information according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing the product recommendation method based on user information 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 user information. The execution subject of the product recommendation method based on the user information 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 embodiment of the present application. In other words, the product recommendation method based on user information may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain 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 user information according to an embodiment of the present invention is shown. In this embodiment, the product recommendation method based on user information includes:
s1, obtaining user group information, and extracting the user keywords of the user group information.
In the embodiment of the invention, the user group information comprises product purchase records of the user group, user age, occupation and other information of each user in the user group.
In detail, the user group information can be crawled from a pre-constructed storage area for storing the user group information, which includes but is not limited to a database, a block chain node, a network cache, using a computer sentence (java sentence, python sentence, etc.) with a data crawling function.
In the embodiment of the invention, because the user group information contains a large amount of data, in order to improve the efficiency of recommending products to the user group information, the keyword extraction can be carried out on the user group information, so that the user group information containing a large amount of data is prevented from being directly processed, and the efficiency of recommending products is improved.
In the embodiment of the present invention, the extracting the user keywords of the user group information includes:
carrying out nonsense word deletion on the user group information to obtain standard user information;
performing word segmentation processing on the standard user information by using a preset dictionary to obtain user word segmentation;
selecting one word from the user words as a target word one by one, and counting the position information of the target word in the user group information and the frequency of the target word in the user words;
and calculating key values of the target word segmentation according to the position information and the frequency, and collecting the target word segmentation with the key value larger than a preset key threshold value as a user keyword.
In detail, the removing of the nonsense word from the user group information is to remove a word having no actual meaning from the user group information, for example: conjunctive words, mood words, structural aid words, etc. By deleting the nonsense words from the user group information, the information amount in the user group information can be reduced, and the efficiency of analyzing the user group information is improved.
Specifically, the dictionary includes a plurality of participles, the data in the standard user information is used for searching in the dictionary, and if the same participle can be searched, the searched participle is determined to be the user participle of the standard user information.
In the implementation of the present invention, the position information refers to information before and after the position of the target word segmentation in the user group information, and the frequency refers to the number of times that the target word segmentation appears in the user word segmentation.
In detail, the calculating a key value of the target participle according to the position information and the frequency includes:
calculating a key value of the target participle by using the following key value algorithm:
K＝α*A+β*B
and K is the key value, A is the position information of the target word segmentation, B is the frequency of the target word segmentation appearing in the user word segmentation, and alpha and beta are preset weight coefficients.
The target word segmentation method and the device collect the target word segmentation with the key value larger than the preset key threshold value to obtain the user keyword.
S2, similar words are amplified for the user keywords, and a keyword subset of the user keywords after similar words are amplified is constructed.
In one embodiment of the invention, the user keywords are extracted only according to the acquired user group information, but the acquired user group information may have the situations of insufficient information, low coverage of user characteristics and the like, so that the embodiment of the invention can perform similar word amplification on the user keywords to enrich the content of the keywords, thereby improving the accuracy of product recommendation on the user.
In the embodiment of the present invention, the performing similar word amplification on the user keyword includes:
performing vector conversion on the user keywords to obtain a keyword vector corresponding to each user keyword;
selecting one word vector from the keyword vectors one by one as a target vector;
respectively calculating distance values between the target vector and word vectors corresponding to a plurality of standard words in a preset standard word list;
selecting the standard words with the distance values smaller than a preset distance threshold value in the standard word list as similar words of the user keywords corresponding to the target vector, and collecting the similar words and the user keywords.
In detail, vector conversion can be performed on the user keywords by using a pre-constructed word vector model with a word vector conversion function to obtain keyword vectors, wherein the word vector model includes but is not limited to a word2vec model and a bert model.
Specifically, the calculating distance values between the target vector and word vectors corresponding to a plurality of standard words in a preset standard word list respectively includes:
calculating the distance value between the target vector and the word vector corresponding to a plurality of standard words in a preset standard word list by using the following distance value algorithm:
wherein D is the distance value, x is the target vector, yiAnd the word vector corresponding to the ith standard word in the standard word list.
In other embodiments of the present invention, the distance value between the target vector and the word vector corresponding to the plurality of standard words in the preset standard word list may be calculated by using an algorithm having a distance value calculation function, such as a cosine distance algorithm, an euclidean distance algorithm, or the like.
In the embodiment of the invention, the standard words with the distance value smaller than the preset distance threshold value in the standard word list can be selected as the similar words of the user keywords corresponding to the target vector, and the similar words and the user keywords are collected to complete similar word amplification of the user keywords.
Further, the embodiment of the invention constructs the keyword subsets of the user keywords after similar words are amplified, so that product recommendation is performed on the user by using different subsets subsequently, and the coverage rate of products retrieved according to the user keywords is improved.
In the embodiment of the present invention, the first and second substrates,
the constructing of the keyword subset of the user keywords after similar word amplification comprises:
selecting one of the user keywords as a target keyword one by one from the user keywords amplified by the similar words;
selecting a preset number of user keywords from the user keywords after similar word amplification and collecting the user keywords and the target keywords to obtain a target subset until the target subset corresponding to all the keywords in the user keywords is generated;
and calculating the contact ratio between every two target subsets corresponding to all the keywords, and performing repeated subset deletion on the target subsets corresponding to all the keywords according to the contact ratio to obtain the keyword subsets.
In detail, the preset number range is [0, j-1], where j is the number of keywords included in the user keywords after similar words are amplified.
For example, the user keywords after similar word amplification include a keyword a, a keyword B and a keyword C, the keyword a is selected as a target keyword, and a preset number (0, 1 and 2) of user keywords are selected from the user keywords after similar word amplification and collected with the keyword a to obtain a target subset { keyword a }, { keyword a, keyword B }, { keyword a, keyword C }, { keyword a, keyword B, keyword C }; similarly, selecting the keyword B as a target keyword, selecting a preset number (0, 1 and 2) of user keywords from the user keywords after similar word amplification and collecting the user keywords and the keyword A to obtain a target subset { keyword B }, { keyword B, keyword A }, { keyword B, keyword C }, { B, keyword A and keyword C }, and similarly, when the keyword C is selected as the target keyword, obtaining the target subset { keyword C }, { C, keyword A }, { C, keyword B }, { C, keyword A and keyword B }.
Specifically, since there are repeated subsets in the generated target subsets, the embodiment of the present invention may calculate the overlap ratio between the target subsets corresponding to all the target keywords, and delete the repeated subsets in the target subsets according to the overlap ratio.
In this embodiment of the present invention, the calculating the coincidence degree between each subset in the target subset includes:
calculating the overlap ratio between each subset in the target subset by using an overlap ratio algorithm as follows:
wherein f (k, h) is the degree of coincidence between the kth target subset and the h target subset in the target subsets, MkIs the number of keywords in the kth target subset, NhThe number of repeated keywords in the h-th target subset and the k-th target subset.
In detail, when Mk-NhWhen the number of the repeated keywords in the h-th target subset and the k-th target subset is equal to the number of the keywords in the k-th target subset, that is, the keywords in the k-th target subset and the h-th target subset are all repeated, and the k-th target subset and the h-th target subset are the same subset, so that any one of the k-th target subset and the h-th target subset can be deleted to implement deduplication of the target subset, and obtain the keyword subset.
S3, obtaining product information of a plurality of products, and extracting product keywords of each product information in the product information.
In the embodiment of the invention, the product information comprises information such as product name, product price, product efficacy, product structure, product components and the like.
In detail, the step of obtaining the product information of the plurality of products and extracting the product keyword of each product information in the product information is consistent with the step of obtaining the user group information and extracting the user keyword of the user group information in S1, and details are not repeated here.
And S4, respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by using a pre-constructed relation analysis model, and collecting the products corresponding to the product keywords with the association degree larger than a preset first threshold value as the products to be screened.
In an embodiment of the present invention, the preset relationship Analysis model may be a model with a text Semantic Analysis function based on an NLP (Natural Language Processing) model, an LSA (Latent Semantic Analysis) model, an LDA (Latent Dirichlet Allocation) model, and the like, and analyze the association between each subset of the keyword subset and each product keyword corresponding to the product information.
In detail, referring to fig. 2, the analyzing the association degree between each subset of the keyword subsets and the product keyword corresponding to each product information respectively includes:
s21, selecting one subset from the keyword subsets one by one as a subset to be analyzed, and selecting a product keyword corresponding to one product from the products one by one as a keyword to be analyzed;
s22, carrying out convolution and pooling on the subset to be analyzed and the keywords to be analyzed by utilizing a pre-constructed relational analysis model to obtain subset characteristics of the subset to be analyzed and word characteristics of the keywords to be analyzed;
s23, calculating the similarity between the subset features and the word features, and taking the similarity as the association degree between the subset to be analyzed and the keywords to be analyzed.
In detail, the subset to be analyzed and the keyword to be analyzed are convolved and pooled by using a pre-established relational analysis model, and the characteristics corresponding to the subset to be analyzed and the keyword to be analyzed can be extracted, so that the accuracy of the calculation of the association degree of the subset to be analyzed and the keyword to be analyzed can be improved.
Specifically, the similarity between the subset feature and the word feature may be calculated by using a preset activation function, and the similarity is used as the association degree between the subset to be analyzed and the keyword to be analyzed, where the activation function includes, but is not limited to, a sigmoid activation function, a relu activation function, and a softmax activation function.
In the embodiment of the invention, the products corresponding to the product keywords with the association degree larger than the preset first threshold value are gathered as the products to be screened, for example, the keyword subset includes a subset a and a subset B, the plurality of products includes a product X, a product Y, and a product Z, and it can be known from analysis by using the relational analysis model that the degree of association between the subset a and the to-be-analyzed keywords corresponding to the product X is 30, the degree of association between the subset a and the to-be-analyzed keywords corresponding to the product Y is 70, the degree of association between the subset a and the to-be-analyzed keywords corresponding to the product Z is 40, the degree of association between the subset B and the to-be-analyzed keywords corresponding to the product X is 90, the degree of association between the subset B and the to-be-analyzed keywords corresponding to the product Y is 30, and the degree of association between the subset B and the to-be-analyzed keywords corresponding to the product Z is 20, then the product X and the product Y can be collected as the product to be screened.
According to the embodiment of the invention, the product to be screened is selected from the multiple products through the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information, so that the rough screening of the multiple products is realized, and the overall efficiency of product recommendation for users is improved.
S5, calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products with the matching values larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
In one practical application scenario of the invention, after the plurality of products are screened by using the user keywords and the product keywords, because the semantics contained in the keywords are not complete enough, the precision of screening the products by using the keywords still does not meet the refined recommendation requirement of the user, so that the product information of the products to be screened and the user group information are analyzed, refined content matching is realized, and the precision of product recommendation of the user is improved.
In the embodiment of the present invention, referring to fig. 3, the calculating a matching value between the user group information and the product information of each product in the products to be screened includes:
s31, counting symbol position information of a preset sentence break symbol in the user group information and the product information of each product of the products to be screened;
s32, according to the symbolic position information, sentence splitting processing is carried out on the user group information to obtain user sentences, and sentence splitting processing is carried out on the product information of each product of the products to be screened to obtain product sentences of each product;
s33, converting the user clauses into user vectors, and collecting the user vectors as a user matrix;
s34, converting the product clauses into product vectors, and collecting the product vectors as a product matrix;
and S35, calculating the matching value of the user matrix and the product matrix by using a preset matching value algorithm.
In detail, the punctuation mark may be predefined by a user, for example, a comma mark, a pause mark, a period mark, and the like, and according to the symbolic position information of the punctuation mark in the user group information and the product information, the user group information and the product information are subjected to sentence splitting processing to obtain a user sentence corresponding to the user group information and a product sentence corresponding to the product information.
Specifically, the step of converting the user clause into a user vector and the step of converting the product clause into a product vector are the same as the step of performing vector conversion on the user keyword in S2, and are not described herein again.
In the embodiment of the present invention, the calculating the matching value between the user matrix and the product matrix by using a preset matching value algorithm includes:
calculating the matching value of the user matrix and the product matrix by using the following matching value algorithm:
wherein P is the matching value, [ m ]]For the user matrix, [ m ]]TIs a transposed matrix of the user matrix, [ n ]t]A product matrix for the t-th product of the plurality of products, [ n ]t]TIs the transpose of the product matrix for the T-th product, and T is the transpose of the matrix.
In the embodiment of the invention, the products with the matching value larger than the preset second threshold value in the products to be screened are recommended to the users corresponding to the user group information.
The embodiment of the invention can extract the user keywords from the user information, amplify the similar words of the user keywords to extract the potential or related semantic information of the user keywords, match the amplified keywords with the product, and is beneficial to improving the diversity of the matched product. Therefore, the product recommendation method, the product recommendation device, the electronic equipment and the computer readable storage medium based on the user information can solve the problem of low product diversity during product recommendation.
Fig. 4 is a functional block diagram of a product recommendation apparatus based on user information according to an embodiment of the present invention.
The product recommendation device 100 based on user information according to the present invention may be installed in an electronic device. According to the realized functions, the product recommendation device 100 based on user information may include a first keyword extraction module 101, a similar word augmentation module 102, a second keyword extraction module 103, an association analysis module 104, and a product recommendation module 105. 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 first keyword extraction module 101 is configured to obtain user group information and extract a user keyword of the user group information;
the similar word amplification module 102 is configured to perform similar word amplification on the user keyword, and construct a keyword subset of the user keyword after similar word amplification;
the second keyword extraction module 103 is configured to obtain product information of a plurality of products, and extract a product keyword of each product information in the product information;
the association degree analysis module 104 is configured to analyze, by using a pre-established relationship analysis model, association degrees of each subset of the keyword subsets and product keywords corresponding to each piece of the product information, and collect products corresponding to the product keywords with the association degrees greater than a preset first threshold as products to be screened;
the product recommending module 105 is configured to calculate a matching value between the user group information and product information of each product in the products to be screened, and recommend a product, of which the matching value is greater than a preset second threshold, in the products to be screened to a user corresponding to the user group information.
In detail, when the modules in the product recommendation device 100 based on user information according to the embodiment of the present invention are used, the same technical means as the product recommendation method based on user information 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 product recommendation method based on user information 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 product recommendation program based on user information, 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 user information, 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 a product recommendation program based on user information, 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 product recommendation program based on user information stored in the memory 11 of the electronic device 1 is a combination of instructions, which when executed in the processor 10, can realize:
acquiring user group information, and extracting user keywords of the user group information;
similar word amplification is carried out on the user keywords, and a keyword subset of the user keywords after similar word amplification is constructed;
the method comprises the steps of obtaining product information of a plurality of products, and extracting product keywords of each product information in the product information;
respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by using a pre-constructed relation analysis model, and collecting the products corresponding to the product keywords with the association degree larger than a preset first threshold value as products to be screened;
and calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
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:
acquiring user group information, and extracting user keywords of the user group information;
similar word amplification is carried out on the user keywords, and a keyword subset of the user keywords after similar word amplification is constructed;
the method comprises the steps of obtaining product information of a plurality of products, and extracting product keywords of each product information in the product information;
respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by using a pre-constructed relation analysis model, and collecting the products corresponding to the product keywords with the association degree larger than a preset first threshold value as products to be screened;
and calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
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 user information, the method comprising:
acquiring user group information, and extracting user keywords of the user group information;
similar word amplification is carried out on the user keywords, and a keyword subset of the user keywords after similar word amplification is constructed;
the method comprises the steps of obtaining product information of a plurality of products, and extracting product keywords of each product information in the product information;
respectively analyzing the association degree of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by using a pre-constructed relation analysis model, and collecting the products corresponding to the product keywords with the association degree larger than a preset first threshold value as products to be screened;
and calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
2. The product recommendation method based on user information as claimed in claim 1, wherein said extracting the user keywords of the user group information comprises:
carrying out nonsense word deletion on the user group information to obtain standard user information;
performing word segmentation processing on the standard user information by using a preset dictionary to obtain user word segmentation;
selecting one word from the user words as a target word one by one, and counting the position information of the target word in the user group information and the frequency of the target word in the user words;
and calculating key values of the target word segmentation according to the position information and the frequency, and collecting the target word segmentation with the key value larger than a preset key threshold value as a user keyword.
3. The product recommendation method based on user information as claimed in claim 1, wherein said performing similar word augmentation on said user keywords comprises:
performing vector conversion on the user keywords to obtain a keyword vector corresponding to each user keyword;
selecting one word vector from the keyword vectors one by one as a target vector;
respectively calculating distance values between the target vector and word vectors corresponding to a plurality of standard words in a preset standard word list;
selecting the standard words with the distance values smaller than a preset distance threshold value in the standard word list as similar words of the user keywords corresponding to the target vector, and collecting the similar words and the user keywords.
4. The product recommendation method based on user information as claimed in claim 1, wherein said constructing the keyword subset of the user keywords after similar words are augmented comprises:
selecting one of the user keywords as a target keyword one by one from the user keywords amplified by the similar words;
selecting a preset number of user keywords from the user keywords after similar word amplification and collecting the user keywords and the target keywords to obtain a target subset until the target subset corresponding to all the keywords in the user keywords is generated;
and calculating the contact ratio between every two target subsets corresponding to all the keywords, and performing repeated subset deletion on the target subsets corresponding to all the keywords according to the contact ratio to obtain the keyword subsets.
5. The method of claim 4, wherein the calculating the degree of overlap between each of the target subsets comprises:
calculating the overlap ratio between each subset in the target subset by using an overlap ratio algorithm as follows:
wherein f (k, h) is the degree of coincidence between the kth target subset and the h target subset in the target subsets, MkIs the number of keywords in the kth target subset, NhThe number of repeated keywords in the h-th target subset and the k-th target subset.
6. The method of any one of claims 1 to 5, wherein the analyzing the association degree of each subset of the keyword subsets with the product keyword corresponding to each product information comprises:
selecting one subset from the keyword subsets one by one as a subset to be analyzed, and selecting a product keyword corresponding to one product from the plurality of products one by one as a keyword to be analyzed;
performing convolution and pooling on the subset to be analyzed and the keywords to be analyzed by using a pre-constructed relational analysis model to obtain subset characteristics of the subset to be analyzed and word characteristics of the keywords to be analyzed;
and calculating the similarity between the subset characteristics and the word characteristics, and taking the similarity as the association degree between the subset to be analyzed and the keywords to be analyzed.
7. The product recommendation method based on user information according to any one of claims 1 to 5, wherein the calculating the matching value of the user group information and the product information of each product in the products to be screened comprises:
counting symbol position information of a preset sentence break symbol in the user group information and the product information of each product of the products to be screened;
according to the symbol position information, performing clause processing on the user group information to obtain user clauses, and performing clause processing on the product information of each product of the products to be screened to obtain product clauses of each product;
converting the user clauses into user vectors, and collecting the user vectors as a user matrix;
converting the product clauses into product vectors, and collecting the product vectors as a product matrix;
and calculating the matching value of the user matrix and the product matrix by using a preset matching value algorithm.
8. A product recommendation apparatus based on user information, the apparatus comprising:
the first keyword extraction module is used for acquiring user group information and extracting user keywords of the user group information;
the similar word amplification module is used for performing similar word amplification on the user keywords and constructing a keyword subset of the user keywords after similar word amplification;
the second keyword extraction module is used for acquiring product information of a plurality of products and extracting a product keyword of each product information in the product information;
the relevancy analysis module is used for respectively analyzing the relevancy of each subset in the keyword subsets and the product keywords corresponding to each piece of product information by utilizing a pre-constructed relationship analysis model, and collecting the products corresponding to the product keywords with the relevancy greater than a preset first threshold as the products to be screened;
and the product recommending module is used for calculating a matching value of the user group information and the product information of each product in the products to be screened, and recommending the products of which the matching values are larger than a preset second threshold value in the products to be screened to the users corresponding to the user group information.
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 content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the user information based product recommendation method of any 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 method for product recommendation based on user information according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111250134.5A CN113886708A (en) | 2021-10-26 | 2021-10-26 | Product recommendation method, device, equipment and storage medium based on user information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111250134.5A CN113886708A (en) | 2021-10-26 | 2021-10-26 | Product recommendation method, device, equipment and storage medium based on user information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113886708A true CN113886708A (en) | 2022-01-04 |
Family
ID=79014548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111250134.5A Pending CN113886708A (en) | 2021-10-26 | 2021-10-26 | Product recommendation method, device, equipment and storage medium based on user information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113886708A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723523A (en) * | 2022-04-06 | 2022-07-08 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability portrait |
| CN115204971A (en) * | 2022-06-23 | 2022-10-18 | 平安科技（深圳）有限公司 | Product recommendation method and device, electronic equipment and computer-readable storage medium |
| CN117541275A (en) * | 2024-01-09 | 2024-02-09 | 深圳市微购科技有限公司 | Intelligent terminal commodity sales management system based on cloud technology |
-
2021
- 2021-10-26 CN CN202111250134.5A patent/CN113886708A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723523A (en) * | 2022-04-06 | 2022-07-08 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability portrait |
| CN114723523B (en) * | 2022-04-06 | 2023-05-30 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability image |
| CN115204971A (en) * | 2022-06-23 | 2022-10-18 | 平安科技（深圳）有限公司 | Product recommendation method and device, electronic equipment and computer-readable storage medium |
| CN115204971B (en) * | 2022-06-23 | 2024-02-02 | 平安科技（深圳）有限公司 | Product recommendation method, device, electronic equipment and computer readable storage medium |
| CN117541275A (en) * | 2024-01-09 | 2024-02-09 | 深圳市微购科技有限公司 | Intelligent terminal commodity sales management system based on cloud technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN112541338A (en) | Similar text matching method and device, electronic equipment and computer storage medium | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN115002200B (en) | Message pushing method, device, equipment and storage medium based on user portrait | |
| CN113836131B (en) | Big data cleaning method and device, computer equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN113592605B (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN112883730B (en) | Similar text matching method and device, electronic equipment and storage medium | |
| CN112507230A (en) | Webpage recommendation method and device based on browser, electronic equipment and storage medium | |
| CN112667775A (en) | Keyword prompt-based retrieval method and device, electronic equipment and storage medium | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN115238670A (en) | Information text extraction method, device, equipment and storage medium | |
| CN113360654B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN114138784A (en) | Information tracing method and device based on storage library, electronic equipment and medium | |
| CN114066533A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN113706322A (en) | Service distribution method, device, equipment and storage medium based on data analysis | |
| CN112633988A (en) | User product recommendation method and device, electronic equipment and readable storage medium | |
| CN115186188A (en) | Product recommendation method, device and equipment based on behavior analysis and storage medium | |
| CN115438048A (en) | Table searching method, device, equipment and storage medium | |
| CN113344674A (en) | Product recommendation method, device, equipment and storage medium based on user purchasing power | |
| CN113707302A (en) | Service recommendation method, device, equipment and storage medium based on associated information | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN113505117A (en) | Data quality evaluation method, device, equipment and medium based on data indexes |
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 |