CN115249164A - Commodity recommendation method and device, electronic equipment and storage medium - Google Patents
Commodity recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115249164A CN115249164A CN202110460447.7A CN202110460447A CN115249164A CN 115249164 A CN115249164 A CN 115249164A CN 202110460447 A CN202110460447 A CN 202110460447A CN 115249164 A CN115249164 A CN 115249164A
- Authority
- CN
- China
- Prior art keywords
- commodity
- score
- recommended
- recommending
- obtaining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium, wherein the commodity recommendation method comprises the following steps: acquiring multi-dimensional scores of commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score; obtaining an optimal weight coefficient corresponding to the multidimensional grading, wherein the optimal weight coefficient is obtained through fitting; and obtaining the recommendation score of the to-be-recommended commodity based on the multi-dimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score. According to the embodiment of the invention, the accuracy of commodity recommendation can be effectively improved, so that the recommended commodities are more in line with the consumption will of consumers.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a commodity recommendation method and device, electronic equipment and a storage medium.
Background
The rapid development of the e-commerce industry promotes a new consumption scenario to appear: the user wants to find out the interested commodities in a large amount of commodity information and find out the commodities associated with the target purchased commodities. The current recommendation methods include: collaborative filtering recommendations based on users, collaborative filtering recommendations based on items, and content-based recommendations.
In the above recommendation manners, the adopted recommendation strategy usually only considers a single factor, such as recommendation of related name goods based on text similarity or recommendation of related goods based on matrix decomposition, and the final recommendation result lacks accuracy and pertinence. Even if there is a recommendation manner considering a plurality of factors, the weight parameter assigned to each factor is usually set manually according to experience, and the objectivity and rationality are lacked, so that the final recommendation result is not reasonable enough.
Disclosure of Invention
Based on the problems in the prior art, embodiments of the present invention provide a method and an apparatus for recommending a commodity, an electronic device, and a storage medium.
In a first aspect, an embodiment of the present invention provides a method for recommending a commodity, including:
acquiring multi-dimensional scores of commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score;
obtaining an optimal weight coefficient corresponding to the multidimensional score, wherein the optimal weight coefficient is obtained by fitting;
and obtaining the recommendation score of the to-be-recommended commodity based on the multi-dimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score.
Further, the obtaining of the multidimensional score of the to-be-recommended commodity includes:
obtaining a commodity to be recommended based on a target commodity and a pre-obtained purchase similarity matrix, wherein the purchase similarity matrix is obtained by pre-training through an ALS matrix decomposition model based on historical purchase records of all commodities;
and obtaining cosine similarity between the to-be-recommended commodity and the target commodity, and taking the cosine similarity as a purchase similarity score of the to-be-recommended commodity.
Further, the obtaining of the multidimensional score of the to-be-recommended commodity includes:
obtaining a TF-IDF value of the commodity to be recommended;
and taking the TF-IDF value as the name similarity score of the to-be-recommended commodity.
Further, the acquiring the multi-dimensional score of the to-be-recommended commodity comprises:
determining the heat degree of the commodity to be recommended according to the commodity requirement;
and normalizing the heat to obtain a commodity normalized heat score of the commodity to be recommended.
Further, the obtaining an optimal weight coefficient corresponding to the multidimensional score includes:
and fitting each group of weight coefficients corresponding to the multidimensional scores by using the logistic regression model and the prediction result of the purchase condition of the commodity to be recommended to determine a group of optimal weight coefficients.
Further, the optimal weight coefficient correspondingly predicts the most accurate purchase condition of the to-be-recommended commodity.
Further, the obtaining of the recommendation score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient and recommending the commodity based on the recommendation score include:
and based on the optimal weight coefficient, carrying out weighted summation on the multidimensional scores to obtain the recommendation scores of the commodities to be recommended, and recommending the commodities based on the recommendation scores.
In a second aspect, an embodiment of the present invention provides a recommendation apparatus for a commodity, including:
the multi-dimensional score acquisition module is used for acquiring multi-dimensional scores of the commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score;
the optimal weight coefficient acquisition module is used for acquiring an optimal weight coefficient corresponding to the multidimensional score, wherein the optimal weight coefficient is obtained by fitting;
and the recommending module is used for obtaining the recommending score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient, and recommending the commodity based on the recommending score.
In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for recommending a product according to the first aspect.
In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for recommending an article according to the first aspect.
According to the technical scheme, the commodity recommendation device, the electronic equipment and the storage medium provided by the embodiment of the invention comprehensively consider three factors of commodity text similarity, commodity popularity and commodity purchase history when recommending commodities, namely: the method gives consideration to several dimensional factors such as recommendation accuracy, sales service requirements, model efficiency and the like, so that the commodity recommendation is more accurate and the purchase intention of the consumer is better met. In addition, the weight parameters obtained by fitting are used for replacing the weight parameters appointed according to manual experience in the prior art, so that the values of the weight parameters are determined in a more scientific and reasonable mode, commodity recommendation is more reasonable and accurate, and the use experience of a user is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is also possible for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a method for recommending merchandise according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an optimal weight parameter fitting process of a commodity recommendation method according to an embodiment of the present invention;
fig. 3 is a block diagram showing a structure of a commodity recommendation apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
A method, an apparatus, an electronic device, and a storage medium for recommending a product according to embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for recommending a product according to an embodiment of the present invention. As shown in fig. 1 and in conjunction with fig. 2, a method for recommending a commodity according to an embodiment of the present invention includes the following steps:
s101: and acquiring multi-dimensional scores of the commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score.
The acquisition processes of the purchase similarity score, the name similarity score and the commodity normalized heat score are described by taking the purchase similarity score, the name similarity score and the commodity normalized heat score as examples respectively.
In a specific example, obtaining a purchase similarity score of a to-be-recommended commodity includes: obtaining a commodity to be recommended based on a target commodity and a pre-obtained purchase similarity matrix, wherein the purchase similarity matrix is obtained by pre-training through an ALS matrix decomposition model based on historical purchase records of all commodities; and obtaining cosine similarity between the to-be-recommended commodity and the target commodity, and taking the cosine similarity as a purchase similarity score of the to-be-recommended commodity.
In particular, the purchase similarity score is determined from a purchase similarity matrix. The purchase similarity matrix refers to a purchase similarity matrix of the training articles and the articles based on the ALS matrix decomposition model by using the purchase records.
The first step of matrix decomposition is to construct an item preference matrix U1, where the value in the matrix U1 is the number of purchases of a commodity by each user, and the dimension of the matrix is U × i, where U is the number of users and i is the number of commodities (also referred to as items), for example: for a shopping platform, the number of users is 1 hundred million, the number of commodities is 5000, and the dimension of the matrix is 1 hundred million by 5000. And (4) transmitting all historical purchase records into an ALS matrix decomposition model, and selecting an implicit feedback data training mode. The matrix U1 is decomposed to obtain two matrices, a U × k dimensional matrix representing the users and an i × k dimensional matrix characterizing the items, which are also referred to as factor matrices. The matrix U2, which is the product of these two factor matrices, is an approximation of the matrix U1. The commodities in the matrix U2 may be commodities to be recommended, and the commodities in the matrix U2 use cosine similarity to calculate the similarity with the target commodity. Therefore, the purchase similarity score of the to-be-recommended commodity can be obtained.
In the above description, the target product is, for example, a certain product that the user is browsing on the shopping platform, such as: entering a detailed interface of the commodity A, and browsing the commodity A, wherein the commodity A is a target commodity.
Obtaining the name similarity score of the to-be-recommended commodity, comprising the following steps: obtaining a TF-IDF value of the commodity to be recommended; and taking the TF-IDF value as the name similarity score of the to-be-recommended commodity.
Specifically, the TF-IDF value is TF-IDF, where TF is Term Frequency (Term Frequency) and IDF is Inverse text Frequency index (Inverse Document Frequency) in TF-IDF (Term Frequency-Inverse Document Frequency), and the main ideas of TF-IDF are: if a word or phrase appears frequently in one article and rarely appears in other articles, TF is high, the word or phrase is considered to have a good classification capability and is suitable for classification. TF-IDF is actually: TF, IDF, TF Term Frequency (Term Frequency), IDF Inverse file Frequency (Inverse Document Frequency). TF represents the frequency of occurrence of the term in the document d. The main idea of IDF is: if the documents containing the entry t are fewer, that is, the n is smaller, and the IDF is larger, the entry t has good category distinguishing capability. If the number of documents containing the entry t in a certain class of documents C is m, and the total number of documents containing the entry t in other classes is k, it is obvious that the number of documents containing t n = m + k, when m is large, n is also large, and the IDF value obtained according to the IDF formula is small, which means that the category distinguishing capability of the entry t is not strong.
Therefore, in the above manner, the TF-IDF value of a word in the product name of the target product for a certain product to be recommended can be calculated, that is: and the TF-IDF value is used as the name similarity score of the to-be-recommended commodity.
The method for acquiring the commodity normalized heat score of the to-be-recommended commodity comprises the following steps: determining the heat degree of the commodity to be recommended according to the commodity requirement; and normalizing the heat to obtain a commodity normalized heat score of the commodity to be recommended. For example: the service requirement and the merchant delivery are taken as the basis, the score is given in a manual grading mode, and after the score is normalized, the normalized heat of the commodity can be obtained, namely: and (4) evaluating the normalized heat of the commodities.
S102: and obtaining an optimal weight coefficient corresponding to the multidimensional score, wherein the optimal weight coefficient is obtained by fitting.
In one embodiment of the present invention, the optimal weight coefficient may be obtained by logistic regression model fitting. For example: obtaining an optimal weight coefficient corresponding to the multidimensional score, including: and fitting each group of weight coefficients corresponding to the multidimensional scores by using the logistic regression model and the prediction result of the purchase condition of the commodity to be recommended to determine a group of optimal weight coefficients.
It can be understood that the optimal weight coefficient corresponds to predicting the most accurate purchase condition of the to-be-recommended goods.
Specifically, an equation is constructed by using linear regression, and nonlinear processing is performed on a linear regression result by using a Sigmoid function, so that the probability under the condition of two categories is obtained, and the predicted value of y is finally obtained.
Respectively by x 1 、x 2 、x 3 The method comprises the following steps of expressing a purchase similarity score, a name similarity score and a commodity normalized heat score of a commodity, wherein the score calculation formula of the commodity to be recommended is as follows:
h(x)＝α 1 x 1 +α 2 x 2 +α 3 x 3 ，
wherein alpha is 1 、α 2 、α 3 The weight parameters respectively representing the purchase similarity score, the name similarity score and the commodity normalized heat score are written into a matrix form as follows:
h(x)＝Xα T ，
the logistic regression model is based on a linear regression model of Sigmoid function and independent variables, and thus, the logistic regression model can be expressed as:
and fitting the parameter alpha by using the prediction result of the logistic regression model to finally obtain the optimal parameter alpha.
Specifically, the detailed method for fitting the parameter α is as follows: initially, at the time of satisfying alpha 1 +α 2 +α 3 In the condition of =1, a is randomly designated first 1 、α 2 、α 3 And (4) calculating a predicted value y ^ of the commodity y by using a logistic regression model, comparing the predicted value y ^ with an actual y value, and counting the prediction accuracy of the y value corresponding to the current group of a values. Then, the value a is changed, and the prediction accuracy of the value y is recalculated. The above process is repeated until a set of values of a is fitted that maximizes the prediction accuracy of the y values.
It will be appreciated that an optimal set of a valuesIs to include an optimum alpha 1 、α 2 、α 3 A combination of (a) and (b). The predicted value y ^ refers to the prediction condition of whether the commodity is purchased or not, and the actual value y refers to the actual condition of whether the commodity is actually purchased or not, for example: if not purchased, it is 0, and if purchased, it is 1. The predicted value y ^ is between 0 and 1, and if the actual value y is 1, the more the predicted value is close to 1, the more accurate the predicted value is, and similarly, if the actual value y is 0, the more the predicted value is close to 0, the more accurate the prediction is.
S103: and obtaining a recommendation score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score.
In this example, obtaining a recommendation score of the to-be-recommended item based on the multidimensional score and the optimal weight coefficient, and recommending the item based on the recommendation score includes: and based on the optimal weight coefficient, carrying out weighted summation on the multidimensional scores to obtain the recommendation scores of the commodities to be recommended, and recommending the commodities based on the recommendation scores.
According to the commodity recommendation method provided by the embodiment of the invention, when commodity recommendation is carried out, three factors of commodity text similarity, commodity popularity and commodity purchase history are comprehensively considered, namely: the method gives consideration to several dimensional factors such as recommendation accuracy, sales service requirements, model efficiency and the like, so that the commodity recommendation is more accurate and the purchase intention of the consumer is better met. In addition, the weight parameters obtained by fitting are used for replacing the weight parameters appointed according to manual experience in the prior art, so that the values of the weight parameters are determined in a more scientific and reasonable mode, commodity recommendation is more reasonable and accurate, and the use experience of a user is improved.
Fig. 3 is a schematic structural diagram illustrating a product recommendation apparatus according to an embodiment of the present invention, and as shown in fig. 3, the product recommendation apparatus according to the embodiment of the present invention includes: a multidimensional score obtaining module 310, an optimal weight coefficient obtaining module 320, and a recommending module 330, wherein:
the multi-dimensional score obtaining module 310 is configured to obtain a multi-dimensional score of a to-be-recommended commodity, where the multi-dimensional score at least includes at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score;
an optimal weight coefficient obtaining module 320, configured to obtain an optimal weight coefficient corresponding to the multidimensional score, where the optimal weight coefficient is obtained by fitting;
and the recommending module 330 is configured to obtain a recommendation score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient, and recommend the commodity based on the recommendation score.
According to the commodity recommending device provided by the embodiment of the invention, when commodity recommendation is carried out, three factors of commodity text similarity, commodity popularity and commodity purchase history are comprehensively considered, namely: the method gives consideration to several dimensional factors such as recommendation accuracy, sales service requirements, model efficiency and the like, so that the commodity recommendation is more accurate and the purchase intention of the consumer is better met. In addition, the weight parameters obtained by fitting are used for replacing the weight parameters appointed according to manual experience in the prior art, so that the values of the weight parameters are determined in a more scientific and reasonable mode, commodity recommendation is more reasonable and accurate, and the use experience of a user is improved.
It should be noted that a specific implementation manner of the commodity recommendation device in the embodiment of the present invention is similar to a specific implementation manner of the commodity recommendation method in the embodiment of the present invention, and please refer to the description of the method part specifically, and details are not described here specifically in order to reduce redundancy.
Based on the same inventive concept, another embodiment of the present invention provides an electronic device, referring to fig. 4, which specifically includes the following contents: a processor 401, a memory 402, a communication interface 403, and a communication bus 404;
the processor 401, the memory 402 and the communication interface 403 complete mutual communication through the communication bus 404; the communication interface 403 is used for implementing information transmission between the devices;
the processor 401 is configured to call the computer program in the memory 402, and the processor implements all steps of the method for recommending a product when executing the computer program, for example, the processor implements the following steps when executing the computer program: acquiring multi-dimensional scores of commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score; obtaining an optimal weight coefficient corresponding to the multidimensional score, wherein the optimal weight coefficient is obtained by fitting; and obtaining a recommendation score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score.
Based on the same inventive concept, yet another embodiment of the present invention provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements all the steps of the recommendation method for an article of manufacture described above, for example, the processor implements the following steps when executing the computer program: acquiring multi-dimensional scores of commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score; obtaining an optimal weight coefficient corresponding to the multidimensional grading, wherein the optimal weight coefficient is obtained through fitting; and obtaining the recommendation score of the to-be-recommended commodity based on the multi-dimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units 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 embodiment of the present invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be essentially or partially implemented in the form of software products, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the index monitoring method according to the embodiments or some parts of the embodiments.
In addition, in the present invention, terms such as "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The term "comprising", without further limitation, means that the element so defined is not excluded from the group consisting of additional identical elements in the process, method, article, or apparatus that comprises the element.
Furthermore, in the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for recommending a commodity, comprising:
acquiring multi-dimensional scores of commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score;
obtaining an optimal weight coefficient corresponding to the multidimensional grading, wherein the optimal weight coefficient is obtained through fitting;
and obtaining the recommendation score of the to-be-recommended commodity based on the multi-dimensional score and the optimal weight coefficient, and recommending the commodity based on the recommendation score.
2. The method for recommending commodities according to claim 1, wherein said obtaining a multidimensional score of a commodity to be recommended includes:
obtaining a commodity to be recommended based on a target commodity and a pre-obtained purchase similarity matrix, wherein the purchase similarity matrix is obtained by pre-training through an ALS matrix decomposition model based on historical purchase records of all commodities;
and obtaining cosine similarity between the to-be-recommended commodity and the target commodity, and taking the cosine similarity as a purchase similarity score of the to-be-recommended commodity.
3. The method for recommending commodities according to claim 1, wherein said obtaining a multidimensional score of a commodity to be recommended comprises:
obtaining a TF-IDF value of the to-be-recommended commodity;
and taking the TF-IDF value as the name similarity score of the to-be-recommended commodity.
4. The method for recommending commodities according to claim 1, wherein said obtaining a multidimensional score of a commodity to be recommended comprises:
determining the heat degree of the commodity to be recommended according to the commodity requirement;
and normalizing the heat to obtain a commodity normalized heat score of the commodity to be recommended.
5. The method for recommending a commodity according to any one of claims 1 to 4, wherein said obtaining an optimal weight coefficient corresponding to said multidimensional score comprises:
and fitting each group of weight coefficients corresponding to the multidimensional scores by using the logistic regression model and the prediction result of the purchase condition of the commodity to be recommended to determine a group of optimal weight coefficients.
6. The method of claim 5, wherein the optimal weighting factor corresponds to predicting the most accurate purchase of the item to be recommended.
7. The method for recommending commodities according to claim 1, wherein said obtaining a recommendation score of the commodity to be recommended based on the multidimensional score and the optimal weight coefficient and recommending the commodity based on the recommendation score comprises:
and based on the optimal weight coefficient, carrying out weighted summation on the multidimensional scores to obtain the recommendation scores of the commodities to be recommended, and recommending the commodities based on the recommendation scores.
8. An apparatus for recommending an article of merchandise, comprising:
the multi-dimensional score acquisition module is used for acquiring multi-dimensional scores of the commodities to be recommended, wherein the multi-dimensional scores at least comprise at least two of a purchase similarity score, a name similarity score and a commodity normalization heat score;
the optimal weight coefficient acquisition module is used for acquiring an optimal weight coefficient corresponding to the multidimensional score, wherein the optimal weight coefficient is obtained by fitting;
and the recommending module is used for obtaining the recommending score of the to-be-recommended commodity based on the multidimensional score and the optimal weight coefficient, and recommending the commodity based on the recommending score.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for recommending merchandise according to any of claims 1 to 7 when executing the computer program.
10. A non-transitory computer-readable storage medium on which a computer program is stored, the computer program being configured to implement, when executed by a processor, a recommendation method for an item according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460447.7A CN115249164A (en) | 2021-04-27 | 2021-04-27 | Commodity recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460447.7A CN115249164A (en) | 2021-04-27 | 2021-04-27 | Commodity recommendation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115249164A true CN115249164A (en) | 2022-10-28 |
Family
ID=83696382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110460447.7A Pending CN115249164A (en) | 2021-04-27 | 2021-04-27 | Commodity recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115249164A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113689266A (en) * | 2021-08-27 | 2021-11-23 | 重庆锐云科技有限公司 | Mobile phone purchasing recommendation method and device, server and computer readable storage medium |
| CN116862561A (en) * | 2023-07-10 | 2023-10-10 | 深圳爱巧网络有限公司 | Product heat analysis method and system based on convolutional neural network |
-
2021
- 2021-04-27 CN CN202110460447.7A patent/CN115249164A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113689266A (en) * | 2021-08-27 | 2021-11-23 | 重庆锐云科技有限公司 | Mobile phone purchasing recommendation method and device, server and computer readable storage medium |
| CN116862561A (en) * | 2023-07-10 | 2023-10-10 | 深圳爱巧网络有限公司 | Product heat analysis method and system based on convolutional neural network |
| CN116862561B (en) * | 2023-07-10 | 2024-01-26 | 深圳爱巧网络有限公司 | Product heat analysis method and system based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Supplier selection using consistent fuzzy preference relations | |
| Wang et al. | A strategy-oriented operation module for recommender systems in E-commerce | |
| CN111523976A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN110717098A (en) | Meta-path-based context-aware user modeling method and sequence recommendation method | |
| CN111695719A (en) | User value prediction method and system | |
| Pitchipoo et al. | A distinct decision model for the evaluation and selection of a supplier for a chemical processing industry | |
| CN115249164A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| Zhao et al. | Sales prediction and product recommendation model through user behavior analytics. | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| Malik et al. | EPR-ML: E-Commerce Product Recommendation Using NLP and Machine Learning Algorithm | |
| CN113763095B (en) | Information recommendation method and device and model training method and device | |
| Ocampo | Decision modeling for manufacturing sustainability with fuzzy analytic hierarchy process | |
| Chang | Enhanced assessment of a supplier selection problem by integration of soft sets and hesitant fuzzy linguistic term set | |
| CN110852785A (en) | User grading method, device and computer readable storage medium | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN113850654A (en) | Training method of item recommendation model, item screening method, device and equipment | |
| CN111310029B (en) | Mixed recommendation method based on user commodity portrait and potential factor feature extraction | |
| CN115511582B (en) | Commodity recommendation system and method based on artificial intelligence | |
| Thomas et al. | A novel framework for an intelligent deep learning based product recommendation system using sentiment analysis (SA) | |
| CN116402569A (en) | Commodity recommendation method, device and system based on knowledge graph and storage medium | |
| Chu et al. | Deep graph embedding for ranking optimization in e-commerce | |
| Hooda et al. | A study of recommender systems on social networks and content-based web systems | |
| Madić et al. | Application of the ORESTE method for solving decision making problems in transportation and logistics | |
| CN115456656A (en) | Method and device for predicting purchase intention of consumer, electronic equipment and storage medium | |
| JP6686208B1 (en) | Information processing device, information processing method, and program |
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 |