CN113643103A - Product recommendation method, device, equipment and storage medium based on user similarity - Google Patents
Product recommendation method, device, equipment and storage medium based on user similarity Download PDFInfo
- Publication number
- CN113643103A CN113643103A CN202111015418.6A CN202111015418A CN113643103A CN 113643103 A CN113643103 A CN 113643103A CN 202111015418 A CN202111015418 A CN 202111015418A CN 113643103 A CN113643103 A CN 113643103A
- Authority
- CN
- China
- Prior art keywords
- user
- product
- similarity
- users
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000011159 matrix material Substances 0.000 claims abstract description 63
- 239000013598 vector Substances 0.000 claims description 57
- 230000006399 behavior Effects 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 13
- 238000001914 filtration Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 201000004569 Blindness Diseases 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The embodiment of the application belongs to the field of artificial intelligence, and relates to a product recommendation method based on user similarity. The application also provides a product recommendation device, computer equipment and a storage medium based on the user similarity. In addition, the present application also relates to blockchain techniques, where a user-product score matrix may be stored. The method and the device can improve the accuracy of the recommendation result.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a product recommendation method, apparatus, device, and storage medium based on user similarity.
Background
Many commercial platforms are used as predecessors of early intelligent recommendation, the coverage of recommendation is very wide, and the recommendation relates to aspects of daily living goods, and the main technology used by the recommendation algorithm based on content filtering and the association rule algorithm are. In the field of insurance products, internet marketing starts later, and meanwhile, the insurance products have certain characteristics such as long insurance period, high insurance amount and multiple obligation terms, so that the insurance industry is different from the traditional insurance sales of the common retail industry and one-to-one customization and recommendation are carried out by depending on sales consultants according to the requirements of clients.
With the continuous development of internet big data technology and medical guarantee system, the 1+ N insurance sales platform based on the general insurance form, such as bamboo shoots in spring after rain, blooms in many places. The general insurance is different from the traditional personal insurance, the price is low, and the marketing and the sales are carried out by relying on an internet multi-layer insurance platform. The current sales recommendation strategy of the current multi-layer insurance platform is recommended based on a rule algorithm. However, the recommendation algorithm based on the rules has great randomness, and the difference between customer groups causes that the product of the platform of the customer group cannot be accurately matched with the customer, so that the matching accuracy is low.
Disclosure of Invention
The embodiment of the application aims to provide a product recommendation method, a product recommendation device, computer equipment and a storage medium based on user similarity so as to solve the technical problems that products of a platform cannot be accurately matched with customers and the matching accuracy is low in the related technology.
In order to solve the above technical problem, an embodiment of the present application provides a product recommendation method based on user similarity, which adopts the following technical solutions:
acquiring a first user attribute of a target user, and constructing a first attribute vector according to the first user attribute;
constructing a user-product scoring matrix, acquiring a second user attribute of each user in the user-product scoring matrix, and constructing a second attribute vector according to the second user attribute;
calculating a similarity between the target user and each of the users based on the first attribute vector and the second attribute vector;
creating a similar neighbor set of the target user according to the similarity;
selecting products with historical behaviors of adjacent users in the similar neighbor set as a product set, and calculating the prediction scores of the adjacent users on the products in the product set;
recommending products for the target user according to the prediction scores.
Further, the step of constructing a first attribute vector according to the first user attribute comprises:
calculating a weight of the first user attribute through a vector space model;
and mapping the first user attribute into a first attribute vector according to the weight.
Further, the step of calculating the similarity between the target user and each of the users based on the first attribute vector and the second attribute vector comprises:
and calculating the similarity between the target user and each user by adopting a Pearson correlation coefficient method.
Further, the step of creating a similar neighbor set of the target user according to the similarity includes:
sequencing the users according to the sequence of the similarity from high to low to obtain a sequencing result;
and selecting a preset number of users from the sequencing result to form a similar neighbor set.
Further, the step of selecting a product with historical behavior of an adjacent user in the similar neighbor set as a product set, and calculating a prediction score of the adjacent user on the product in the product set includes:
constructing a similarity matrix of the adjacent users in the similar neighbor set according to the similarity;
acquiring all products of which the adjacent users have historical behaviors as a product set, and constructing a scoring result matrix according to the product set;
and calculating the prediction scores of the adjacent users on all products in the product set according to the similarity matrix and the scoring result matrix.
Further, the step of calculating the prediction scores of all the products in the product set by the neighboring users according to the similarity matrix and the scoring result matrix comprises:
and performing weighted calculation on the similarity matrix and the scoring result matrix according to the following formula to obtain the predicted score of each product in the product set by the adjacent user:
wherein, RatetRepresenting the predicted scores, s, of all neighboring users for the product tjtRepresents the score of the t product in the product set by the adjacent user j, mjRepresenting the similarity of the target user to the adjacent user j, and K representing the number of adjacent users.
Further, after the step of calculating the similarity between the target user and each user, the method further includes:
obtaining the number of products which are scored by a target user and each user together, and taking the minimum value between the number of the products and a preset common scoring product number threshold value as the target number;
and adjusting the similarity according to the target quantity and the common scoring product quantity threshold value.
In order to solve the above technical problem, an embodiment of the present application further provides a product recommendation device based on user similarity, which adopts the following technical solutions:
the acquisition module is used for acquiring a first user attribute of a target user and constructing a first attribute vector according to the first user attribute;
the building module is used for building a user-product scoring matrix, obtaining a second user attribute of each user in the user-product scoring matrix, and building a second attribute vector according to the second user attribute;
a calculating module, configured to calculate a similarity between the target user and each of the users based on the first attribute vector and the second attribute vector;
the creating module is used for creating a similar neighbor set of the target user according to the similarity;
the scoring module is used for selecting products with historical behaviors of adjacent users in the similar neighbor set as a product set and calculating the prediction scores of the adjacent users on the products in the product set;
and the recommending module is used for recommending products for the target user according to the prediction scores.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
the computer device comprises a memory and a processor, wherein the memory stores computer readable instructions, and the processor realizes the steps of the product recommendation method based on the user similarity when executing the computer readable instructions.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
the computer readable storage medium has stored thereon computer readable instructions which, when executed by a processor, implement the steps of the product recommendation method based on user similarity as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the method comprises the steps of obtaining a first user attribute of a target user, constructing a first attribute vector according to the first user attribute, constructing a user-product scoring matrix, obtaining a second user attribute of each user in the user-product scoring matrix, constructing a second attribute vector according to the second user attribute, calculating the similarity between the target user and each user based on the first attribute vector and the second attribute vector, creating a similar neighbor set of the target user according to the similarity, selecting a product with historical behaviors of adjacent users in the similar neighbor set as a product set, calculating the prediction score of the adjacent users on the product set, and recommending the product for the target user according to the prediction score; according to the method and the system, the product is recommended according to the similarity neighbor set created according to the similarity, the product is recommended through the prediction score of the adjacent user in the similarity neighbor set to the product set, the product of the platform and the user can be matched in an individualized mode, the recommendation result can reflect the hot spot of a small group similar to the user more accurately, meanwhile, the product recommended by the user is more and more individualized and accurate along with the fact that the data of the platform is more and more abundant, and the randomness and the blindness of the recommendation based on the rule are avoided.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for user similarity based product recommendation according to the present application;
FIG. 3 is a flow diagram of another embodiment of a method for user similarity-based product recommendation in accordance with the present application;
FIG. 4 is a schematic diagram illustrating an embodiment of a product recommendation device based on user similarity according to the present application;
FIG. 5 is a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
The application provides a product recommendation method based on user similarity, which can be applied to a system architecture 100 shown in fig. 1, where the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the product recommendation method based on user similarity provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, a product recommendation apparatus based on user similarity is generally disposed in the server/terminal device.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flowchart of one embodiment of a method for user similarity based product recommendation according to the present application is shown, comprising the steps of:
step S201, a first user attribute of the target user is obtained, and a first attribute vector is constructed according to the first user attribute.
The target users can be obtained through a plurality of channels, and the target users comprise users who consult at an insurance website, an insurance application or a related offline website or purchase insurance products. The first user attribute comprises a user self attribute, a user behavior attribute and a related attribute of an insured life associated with the user, wherein the user self attribute comprises age, gender, occupation, province and city, the age can be specifically divided into 4-17 years old, 18-40 years old, 40-65 years old and over 65 years old, and the occupation can be further distinguished according to categories, such as high-risk occupation, dangerous occupation, common occupation and the like; the user behavior attributes are mainly operation attributes of a user on a platform, such as whether product details, insurance application requisition and claim settlement requisition are clicked, whether a purchase button is clicked, whether a payment button is clicked, and the like are clicked; the related attributes of the insured life related to the user comprise the insured life, the insured life gender and the insured life relationship, wherein the age division can be consistent with the age in the attributes of the user, and the insured life relationship mainly comprises parents, children, spouses and the like.
In this embodiment, the constructing the first attribute vector according to the first user attribute specifically includes:
calculating the weight of the first user attribute through a vector space model;
the first user attribute is mapped to a first attribute vector according to the weights.
Among them, a Vector Space Model (VSM) simplifies the processing of text contents into Vector operations in a Vector Space, and it expresses semantic similarity in a spatial similarity degree.
Specifically, the weight W of the first user attribute may be calculated using TF-IDF (term frequency-inverse text frequency)i(d) The calculation formula is as follows:
wherein, tfi(d) Is tiFrequency of occurrence, idf, in product di(d) Is tiThe frequency of the inverse document appearing in product d, n representing the number of all first user attributes, niAs containing a first user attribute tiThe number of the cells.
The vector space model maps the first user attribute to a multi-dimensional feature vector:
V(d)＝(t1,ω1(d)；…；tn,ωn(d))，
wherein t isi(i 1, 2.. n.) is a list of mutually different first user attribute items, ω being different from each otheri(d) Is tiA weight in product d, the weight indicating how important the corresponding first user attribute is in product d.
In the embodiment, the first user attribute is mapped into the first attribute vector by adopting the vector space model, so that the vector construction is simpler and more convenient.
Step S202, a user-product scoring matrix is constructed, a second user attribute of each user in the user-product scoring matrix is obtained, and a second attribute vector is constructed according to the second user attributes.
Collaborative filtering, as the name implies, users can collaborate with each other, and through interaction with the system, content really interested by themselves is filtered out from a large amount of information. According to the definition of collaborative filtering, the core idea of the collaborative filtering algorithm is that users are interested in articles which are similar to interests of the users, so that the collaborative filtering algorithm needs to calculate the interest similarity between the users and generate neighbors with similar interests for each user, and the articles which are similar to the neighbors are recommended to target users. The input to the collaborative filtering algorithm is a user-product scoring matrix. The embodiment adopts collaborative filtering based on user similarity, and the principle is as follows: calculating the similarity of the users based on the behavior data of the users, namely a user-product scoring matrix, finding out a similar user set of the users, and recommending the similar products which are interested by the users to the users.
Specifically, the product is an insurance product, which can provide one or more guarantee responsibilities for customers, and further, the product is a '1 + N' multi-layer insurance product, wherein 1 is a general insurance, and N is an income-type medical supplementary insurance put forward on the basis of the general insurance.
Constructing a user-product scoring matrix assuming that the insurance platform has m users and n insurance productsIf the user set is U ═ U1,u2,…,umThe set of insurance products is S ═ S1,s2,…,snThe user-product scoring matrix can be represented by an m × n matrix, which is as follows:
wherein m represents the total number of users, n represents the total number of products, Ri,j(1 ≦ i ≦ m,1 ≦ j ≦ n) represents user uiFor insurance products sjThe score of (1).
It should be noted that the score is calculated based on the behavior attributes of the user, such as search behavior, browse behavior, click behavior, purchase behavior, and the like. The score is calculated in two ways, one is active score, the score is calculated by using the user's score or the given evaluation, the other is passive score, the evaluation is completed by the system instead of the user according to the behavior pattern of the user, for example, in an insurance platform, if only the details of an insurance product are browsed, the system considers that the user has a score of 3 for the insurance product, and if an insurance product is purchased and paid, the user has a score of 5 for the insurance product.
Obtaining the second user attribute of the user in the user-product scoring matrix, and similarly, converting the second user attribute into a second attribute vector by using VSM, where the specific conversion process is described above and is not described again.
It is emphasized that, to further ensure the privacy and security of the user-product scoring matrix, the user-product scoring matrix may also be stored in a node of a blockchain.
The block chain referred by the application 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.
Step S203, calculating a similarity between the target user and each user based on the first attribute vector and the second attribute vector.
The similarity calculation methods include a Pearson correlation coefficient method, a vector cosine method, an adjusted vector cosine method, a constrained Pearson correlation coefficient method, a spearman correlation coefficient method and the like, and different similarity calculation methods are selected in different application fields.
In the present embodiment, the similarity between the target user and each user is calculated by using the pearson correlation coefficient method.
Specifically, the Pearson correlation coefficient (Pearson correlation coefficient) algorithm is calculated as follows:
where sim (x, y) represents the similarity of target user x to user y in the user-product scoring matrix, xiAn ith first user attribute representing target user x,
is the average value of the first user attribute corresponding to the target user x, yiAn ith second user attribute representing user y,
and the average value of the second user attribute corresponding to the user y.
It should be noted that the range of the Pearson correlation coefficient is-1 to 1, and the stronger the correlation between the two vectors, the larger the absolute value of the Pearson coefficient is.
In some optional implementation manners of the embodiment, as the number of users and products is increasing, users generally only score some products due to limited time and energy, so that a user-product scoring matrix is very sparse, the number of common scoring products among some users is very small, and if the score values of the common scoring products by the users are slightly different, the calculated similarity is higher than the actual situation. In fact, if two users score a small number of products together, then their products of interest are likely to be dissimilar. In order to enable the similarity calculation to be more accurate, the user similarity can be adjusted by utilizing the number of products scored by the users together, the number of the products scored by the target user and each user together is obtained, the minimum value between the number of the products and a preset common scoring product number threshold value is taken as the target number, and the similarity is adjusted according to the target number and the common scoring product number threshold value.
The specific calculation formula is as follows:
wherein sim' (x, y) represents the similarity of the target user x and the user y after adjustment, k represents the number of products scored jointly by the target user x and the user y, α is a threshold value of the number of products scored jointly for adjusting the user similarity, Min (k, α) is the minimum value between k and α, and if k is greater than or equal to α, the similarity of the user does not need to be adjusted; otherwise, the similarity of the users is adjusted by the ratio of k to alpha.
And step S204, creating a similar neighbor set of the target user according to the similarity.
Specifically, the users are sorted according to the sequence of similarity from high to low to obtain a sorting result, and a preset number of users are selected from the sorting result to form a similar neighbor set, wherein the preset number is K, and K is a natural number greater than zero.
And after calculating the similarity between the target user and the user in the user-product scoring matrix, sorting the similarity according to a sequence from high to low, selecting the users corresponding to the K similarity sorted at the front, and forming a similar neighbor set by the K users.
In some optional implementation manners of this embodiment, in order to improve the accuracy of the recommendation result, a similarity threshold is introduced to limit the selection of the similar neighbors of the target user, and a calculation formula is as follows:
sim(x)＝{y|sim′(x,y)>θ,x≠y}
where sim (x) represents a similar neighbor set of the target user x, θ represents a similarity threshold, sim '(x, y) is the adjusted similarity between the target user x and the user y, and if sim' (x, y) is greater than the similarity threshold θ, the user y is a neighboring user of the target user x.
Step S205, selecting products with historical behaviors of adjacent users in the similar neighbor set as a product set, and calculating the prediction scores of the adjacent users on the products in the product set.
In this embodiment, a recommendation model is generated for the target user based on the historical behavior of K neighboring users in the similar neighbor set. The calculation of the predictive score is based on neighboring user behavior such as scoring behavior, browsing behavior, and purchasing behavior. The score is calculated in two modes, one mode is active score, and the score is calculated by using the score of the user or given evaluation; the other is passive scoring, and the system performs the rating in place of the user according to the user's behavior pattern, e.g., if only the details of a product are viewed, the system considers the user to score 3 for that product, and if a product is purchased, the system considers the user to score 5 for that product.
And step S206, recommending products for the target user according to the prediction scores.
The degree that the corresponding product meets the interest preference of the target user is represented by the size of the prediction score, and the recommending process is to preferentially recommend the product with the large prediction score to the target user. In the embodiment, the prediction scores are ranked from high to low, and products corresponding to h prediction scores ranked in the front are selected and recommended to the target user, wherein h is a natural number greater than zero.
According to the method and the device, the product is recommended according to the prediction scores of the adjacent users in the similar neighbor set created according to the similarity to the product set, the product of the platform can be matched with the users in a personalized mode, the recommendation result can reflect hot spots of small groups similar to the users more accurately, meanwhile, the product recommended by the users is more personalized and accurate along with the fact that the data of the platform is more abundant, and the randomness and the blindness of the recommendation based on the rule are avoided.
In some optional implementation manners of this embodiment, the selecting a product with a historical behavior of an adjacent user in the similar neighbor set as a product set, and the calculating a prediction score of the adjacent user on the product in the product set includes:
step S301, a similarity matrix of adjacent users in the similar neighbor set is constructed according to the similarity.
Specifically, the similarity between the target user and the adjacent user is obtained, and a similarity matrix is constructed according to the similarity.
In this embodiment, the similarity between the target user and the adjacent user is obtained, and a similarity matrix M is constructed according to the similarity, which is specifically as follows:
M＝[m1m2…mj-1mj…mk]
wherein m isjRepresenting the similarity of the target user to the neighboring user j.
Step S302, all products of which the adjacent users have historical behaviors are obtained as a product set, and a scoring result matrix is constructed according to the product set.
The user behaviors include browsing behaviors, clicking behaviors, purchasing behaviors and the like, and specifically include whether product details, insurance application notices and claim notices are clicked on a certain insurance product, whether a purchase button is clicked, whether a payment button is clicked, and the like.
The scoring result matrix is assumed to be S, whose elements are SjtAnd represents the score of the t-th product in the product set by the adjacent user j.
And step S303, calculating the prediction scores of the adjacent users on all products in the product set according to the similarity matrix and the scoring result matrix.
Specifically, the similarity matrix and the scoring result matrix are weighted and calculated according to the following formula, and the prediction score of each product in the product set by the adjacent user is obtained.
The calculation formula of the prediction score is specifically as follows:
wherein, RatetRepresenting the predicted scores for product t for all neighboring users.
The accuracy of the calculation of the prediction score can be further improved by the weighted calculation.
According to the method and the device, the similarity matrix of the adjacent users and the scoring matrix of the products with historical behaviors are constructed to calculate the prediction scores, so that the interested products can be recommended to the target user more accurately.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a product recommendation device based on user similarity, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.
As shown in fig. 4, the product recommendation device 400 based on user similarity according to this embodiment includes: an acquisition module 401, a construction module 402, a calculation module 403, a creation module 404, a scoring module 405, and a recommendation module 406. Wherein:
the obtaining module 401 is configured to obtain a first user attribute of a target user, and construct a first attribute vector according to the first user attribute;
the construction module 402 is configured to construct a user-product scoring matrix, obtain a second user attribute of each user in the user-product scoring matrix, and construct a second attribute vector according to the second user attribute;
the calculating module 403 is configured to calculate a similarity between the target user and each of the users based on the first attribute vector and the second attribute vector;
the creating module 404 is configured to create a similar neighbor set of the target user according to the similarity;
the scoring module 405 is configured to select a product with a historical behavior of an adjacent user in the similar neighbor set as a product set, and calculate a prediction score of the adjacent user on the product in the product set;
the recommendation module 406 is configured to recommend a product to the target user according to the prediction score.
It is emphasized that, to further ensure the privacy and security of the user-product scoring matrix, the user-product scoring matrix may also be stored in a node of a blockchain.
According to the product recommending device based on the user similarity, the product of the platform and the user can be matched in a personalized manner by predicting and scoring the product set by the adjacent user in the similar neighbor set created according to the similarity, so that the recommending result can reflect hot spots of small groups similar to the user more accurately, meanwhile, as the data of the platform is richer and richer, the product recommended by the user is more personalized and accurate, and the randomness and the blindness of the recommendation based on the rule are avoided.
In this embodiment, the obtaining module 401 is further configured to: calculating a weight of the first user attribute through a vector space model; and mapping the first user attribute into a first attribute vector according to the weight. By the method, the efficiency of vector construction can be improved, and vector conversion is simpler and more convenient.
In this embodiment, the calculating module 403 is further configured to: and calculating the similarity between the target user and each user by adopting a Pearson correlation coefficient method.
In this embodiment, the creating module 404 is further configured to:
sequencing the users according to the sequence of the similarity from high to low to obtain a sequencing result;
and selecting a preset number of users from the sequencing result to form a similar neighbor set.
According to the embodiment, the users are selected through the similarity to form the similar neighbor set, so that the accuracy of the recommendation result can be improved.
In some optional implementations of this embodiment, the scoring module 405 includes a constructing sub-module, an obtaining sub-module, and a scoring sub-module, where the constructing sub-module is configured to construct a similarity matrix of the neighboring users in the similar neighbor set according to the similarity; the acquisition submodule is used for acquiring all products of which the adjacent users have historical behaviors as a product set and constructing a scoring result matrix according to the product set; and the scoring submodule is used for calculating the prediction scores of the adjacent users on all products in the product set according to the similarity matrix and the scoring result matrix.
According to the method and the device, the similarity matrix of the adjacent users and the scoring matrix of the products with historical behaviors are constructed to calculate the prediction scores, so that the interested products can be recommended to the target user more accurately.
In this embodiment, the scoring submodule is further configured to: and performing weighted calculation on the similarity matrix and the scoring result matrix according to the following formula to obtain the predicted score of each product in the product set by the adjacent user:
wherein, RatetRepresenting the predicted scores, s, of all neighboring users for the product tjtRepresents the score of the t product in the product set by the adjacent user j, mjRepresenting the similarity of the target user to the adjacent user j, and K representing the number of adjacent users.
The accuracy of the calculation of the prediction score can be further improved by the weighted calculation.
In this embodiment, the product recommendation device 400 based on user similarity further includes an adjustment module, and the adjustment module is configured to:
obtaining the number of products which are scored by a target user and each user together, and taking the minimum value between the number of the products and a preset common scoring product number threshold value as the target number;
and adjusting the similarity according to the target quantity and the common scoring product quantity threshold value.
The embodiment adjusts the similarity, so that the similarity can be calculated more accurately.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 5, fig. 5 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 5 comprises a memory 51, a processor 52, a network interface 53 communicatively connected to each other via a system bus. It is noted that only a computer device 5 having components 51-53 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 51 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 51 may be an internal storage unit of the computer device 5, such as a hard disk or a memory of the computer device 5. In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the computer device 6. Of course, the memory 51 may also comprise both an internal storage unit of the computer device 5 and an external storage device thereof. In this embodiment, the memory 51 is generally used for storing an operating system installed in the computer device 5 and various application software, such as computer readable instructions of a product recommendation method based on user similarity. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is configured to execute the computer readable instructions stored in the memory 51 or process data, for example, execute the computer readable instructions of the product recommendation method based on user similarity.
The network interface 53 may comprise a wireless network interface or a wired network interface, and the network interface 53 is generally used for establishing communication connections between the computer device 5 and other electronic devices.
In the embodiment, when the processor executes the computer readable instructions stored in the memory, the steps of the product recommendation method based on the user similarity in the embodiment are realized, products are recommended according to the prediction scores of the adjacent users in the similar neighbor set created according to the similarity to the product set, the products of the platform can be matched with the users in a personalized manner, so that the recommendation result can reflect hot spots of small groups similar to the users more accurately, meanwhile, as the data of the platform is richer and richer, the products recommended by the users are more and more personalized and accurate, and the randomness and the blindness of recommendation based on rules are avoided.
The present application further provides another embodiment, which is to provide a computer-readable storage medium, where computer-readable instructions are stored, and the computer-readable instructions are executable by at least one processor, so that the at least one processor performs the steps of the product recommendation method based on user similarity as described above, and recommends a product by using the predicted scores of neighboring users in a similar neighbor set created according to the similarity to a product set, so that the product of a platform can be personalized and matched with the user, and the recommendation result can more accurately reflect the hot spots of a small group similar to the user.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A product recommendation method based on user similarity is characterized by comprising the following steps:
acquiring a first user attribute of a target user, and constructing a first attribute vector according to the first user attribute;
constructing a user-product scoring matrix, acquiring a second user attribute of each user in the user-product scoring matrix, and constructing a second attribute vector according to the second user attribute;
calculating a similarity between the target user and each of the users based on the first attribute vector and the second attribute vector;
creating a similar neighbor set of the target user according to the similarity;
selecting products with historical behaviors of adjacent users in the similar neighbor set as a product set, and calculating the prediction scores of the adjacent users on the products in the product set;
recommending products for the target user according to the prediction scores.
2. The method of claim 1, wherein the step of constructing a first attribute vector according to the first user attribute comprises:
calculating a weight of the first user attribute through a vector space model;
and mapping the first user attribute into a first attribute vector according to the weight.
3. The method of claim 1, wherein the step of calculating the similarity between the target user and each of the users based on the first attribute vector and the second attribute vector comprises:
and calculating the similarity between the target user and each user by adopting a Pearson correlation coefficient method.
4. The product recommendation method based on user similarity according to claim 1, wherein the step of creating the similar neighbor set of the target user according to the similarity comprises:
sequencing the users according to the sequence of the similarity from high to low to obtain a sequencing result;
and selecting a preset number of users from the sequencing result to form a similar neighbor set.
5. The product recommendation method based on user similarity according to claim 1, wherein the step of selecting products with historical behaviors of neighboring users in the similar neighbor set as a product set, and the step of calculating the prediction scores of the neighboring users on the products in the product set comprises:
constructing a similarity matrix of the adjacent users in the similar neighbor set according to the similarity;
acquiring all products of which the adjacent users have historical behaviors as a product set, and constructing a scoring result matrix according to the product set;
and calculating the prediction scores of the adjacent users on all products in the product set according to the similarity matrix and the scoring result matrix.
6. The user similarity based product recommendation method according to claim 5, wherein the step of calculating the predicted scores of all the products in the product set by the neighboring users according to the similarity matrix and the scoring result matrix comprises:
and performing weighted calculation on the similarity matrix and the scoring result matrix according to the following formula to obtain the predicted score of each product in the product set by the adjacent user:
wherein, RatetRepresenting the predicted scores, s, of all neighboring users for the product tjtRepresents the score of the t product in the product set by the adjacent user j, mjRepresenting the similarity of the target user to the adjacent user j, and K representing the number of adjacent users.
7. The method of claim 1, further comprising, after the step of calculating the similarity between the target user and each of the users:
obtaining the number of products which are scored by a target user and each user together, and taking the minimum value between the number of the products and a preset common scoring product number threshold value as the target number;
and adjusting the similarity according to the target quantity and the common scoring product quantity threshold value.
8. A product recommendation device based on user similarity, comprising:
the acquisition module is used for acquiring a first user attribute of a target user and constructing a first attribute vector according to the first user attribute;
the building module is used for building a user-product scoring matrix, obtaining a second user attribute of each user in the user-product scoring matrix, and building a second attribute vector according to the second user attribute;
a calculating module, configured to calculate a similarity between the target user and each of the users based on the first attribute vector and the second attribute vector;
the creating module is used for creating a similar neighbor set of the target user according to the similarity;
the scoring module is used for selecting products with historical behaviors of adjacent users in the similar neighbor set as a product set and calculating the prediction scores of the adjacent users on the products in the product set;
and the recommending module is used for recommending products for the target user according to the prediction scores.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the user similarity based product recommendation method of any one of claims 1-7.
10. A computer-readable storage medium, having computer-readable instructions stored thereon, which, when executed by a processor, implement the steps of the product recommendation method based on user similarity according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015418.6A CN113643103A (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on user similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015418.6A CN113643103A (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on user similarity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113643103A true CN113643103A (en) | 2021-11-12 |
Family
ID=78424655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111015418.6A Pending CN113643103A (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on user similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643103A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429384A (en) * | 2021-12-30 | 2022-05-03 | 杭州盟码科技有限公司 | Intelligent product recommendation method and system based on e-commerce platform |
| CN114741605A (en) * | 2022-04-26 | 2022-07-12 | 泰康保险集团股份有限公司 | Method and device for recommending annuity products, electronic equipment and readable medium |
| WO2023134496A1 (en) * | 2022-01-14 | 2023-07-20 | 京东方科技集团股份有限公司 | Object recommendation method and apparatus, electronic device, and storage medium |
| CN116701772A (en) * | 2023-08-03 | 2023-09-05 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| WO2023206960A1 (en) * | 2022-04-24 | 2023-11-02 | 康键信息技术（深圳）有限公司 | Product recommendation method and apparatus based on content and collaborative filtering, and computer device |
| CN117151819A (en) * | 2023-09-04 | 2023-12-01 | 杭州易靓好车互联网科技有限公司 | Transaction user risk recommendation method based on data analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523055A (en) * | 2020-04-28 | 2020-08-11 | 安徽农业大学 | Collaborative recommendation method and system based on agricultural product characteristic attribute comment tendency |
| CN112801803A (en) * | 2021-02-07 | 2021-05-14 | 中国工商银行股份有限公司 | Financial product recommendation method and device |
| CN113032682A (en) * | 2021-04-22 | 2021-06-25 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and storage medium based on collaborative filtering |
| CN113191911A (en) * | 2021-07-01 | 2021-07-30 | 明品云(北京)数据科技有限公司 | Insurance recommendation method, system, equipment and medium based on user information |
-
2021
- 2021-08-31 CN CN202111015418.6A patent/CN113643103A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523055A (en) * | 2020-04-28 | 2020-08-11 | 安徽农业大学 | Collaborative recommendation method and system based on agricultural product characteristic attribute comment tendency |
| CN112801803A (en) * | 2021-02-07 | 2021-05-14 | 中国工商银行股份有限公司 | Financial product recommendation method and device |
| CN113032682A (en) * | 2021-04-22 | 2021-06-25 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and storage medium based on collaborative filtering |
| CN113191911A (en) * | 2021-07-01 | 2021-07-30 | 明品云(北京)数据科技有限公司 | Insurance recommendation method, system, equipment and medium based on user information |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429384A (en) * | 2021-12-30 | 2022-05-03 | 杭州盟码科技有限公司 | Intelligent product recommendation method and system based on e-commerce platform |
| CN114429384B (en) * | 2021-12-30 | 2022-12-09 | 杭州盟码科技有限公司 | Intelligent product recommendation method and system based on e-commerce platform |
| WO2023134496A1 (en) * | 2022-01-14 | 2023-07-20 | 京东方科技集团股份有限公司 | Object recommendation method and apparatus, electronic device, and storage medium |
| WO2023206960A1 (en) * | 2022-04-24 | 2023-11-02 | 康键信息技术（深圳）有限公司 | Product recommendation method and apparatus based on content and collaborative filtering, and computer device |
| CN114741605A (en) * | 2022-04-26 | 2022-07-12 | 泰康保险集团股份有限公司 | Method and device for recommending annuity products, electronic equipment and readable medium |
| CN116701772A (en) * | 2023-08-03 | 2023-09-05 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| CN116701772B (en) * | 2023-08-03 | 2024-03-19 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| CN117151819A (en) * | 2023-09-04 | 2023-12-01 | 杭州易靓好车互联网科技有限公司 | Transaction user risk recommendation method based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113643103A (en) | Product recommendation method, device, equipment and storage medium based on user similarity | |
| Agarwal et al. | An interdisciplinary review of research in conjoint analysis: Recent developments and directions for future research | |
| Grupac et al. | Image processing computational algorithms, sensory data mining techniques, and predictive customer analytics in the metaverse economy | |
| US11243992B2 (en) | System and method for information recommendation | |
| CN112287244A (en) | Product recommendation method and device based on federal learning, computer equipment and medium | |
| CN112766649B (en) | Target object evaluation method based on multi-scoring card fusion and related equipment thereof | |
| CN112633973A (en) | Commodity recommendation method and related equipment thereof | |
| CN112215658A (en) | Big data-based addressing method and device, computer equipment and storage medium | |
| Tsai et al. | Comparing the Apple iPad and non-Apple camp tablet PCs: a multicriteria decision analysis | |
| CN113569129A (en) | Click rate prediction model processing method, content recommendation method, device and equipment | |
| CN110399479A (en) | Search for data processing method, device, electronic equipment and computer-readable medium | |
| CN113420212A (en) | Deep feature learning-based recommendation method, device, equipment and storage medium | |
| CN106600360B (en) | Method and device for sorting recommended objects | |
| Fareed et al. | A collaborative filtering recommendation framework utilizing social networks | |
| US20230245210A1 (en) | Knowledge graph-based information recommendation | |
| CN110020918B (en) | Recommendation information generation method and system | |
| CN115618859A (en) | Research efficiency management method, device, equipment and storage medium based on big data | |
| CN113792952A (en) | Method and apparatus for generating a model | |
| Jiang et al. | Personalized collaborative filtering based on improved slope one alogarithm | |
| Prajna et al. | Implementation of a hybrid recommendation system for Movies | |
| US11972358B1 (en) | Contextually relevant content sharing in high-dimensional conceptual content mapping | |
| CN116911913B (en) | Method and device for predicting interaction result | |
| EP4354382A1 (en) | Contextually relevant content sharing in high-dimensional conceptual content mapping | |
| CN112529718B (en) | Product demonstration method and device based on multiple scenes, computer equipment and medium | |
| CN112529718A (en) | Multi-scene-based product demonstration method and device, computer equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220523 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |