CN113468421A - Product recommendation method, device, equipment and medium based on vector matching technology - Google Patents
Product recommendation method, device, equipment and medium based on vector matching technology Download PDFInfo
- Publication number
- CN113468421A CN113468421A CN202110728147.2A CN202110728147A CN113468421A CN 113468421 A CN113468421 A CN 113468421A CN 202110728147 A CN202110728147 A CN 202110728147A CN 113468421 A CN113468421 A CN 113468421A
- Authority
- CN
- China
- Prior art keywords
- product
- vector
- score
- user
- recommendation
- 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
- 239000013598 vector Substances 0.000 title claims abstract description 156
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005516 engineering process Methods 0.000 title claims description 26
- 238000012216 screening Methods 0.000 claims abstract description 56
- 238000000605 extraction Methods 0.000 claims description 37
- 230000011218 segmentation Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000006835 compression Effects 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims 1
- 238000004891 communication Methods 0.000 description 8
- 238000012015 optical character recognition Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000010276 construction Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of intelligent decision making, and discloses a product recommendation method, which comprises the following steps: constructing a product requirement sequence by utilizing the product requirement information to screen products in a preset product library to obtain a first product set; respectively extracting the characteristics of the user information and the products in the first product set to obtain a user vector and a product vector; calculating the relevance of the user vector and the product vector, and screening the first product set by using the calculated relevance score to obtain a second product set; obtaining a product feedback score of products in the second product set, and calculating a product satisfaction score according to the product feedback score; screening the second product set by using the product satisfaction score and the relevancy score to obtain a target product; and pushing the target product to a preset terminal. The invention also relates to a block chaining technique, the user information can be stored in block chain link points. The invention also provides a product recommendation device, equipment and a medium. The invention can improve the accuracy of product recommendation.
Description
Technical Field
The invention relates to the field of intelligent decision making, in particular to a product recommendation method and device based on a vector matching technology, electronic equipment and a readable storage medium.
Background
With the rapid development of national economy, product recommendation for users by means of operators alone cannot keep pace with the development speed of the current economy, and cannot meet the requirements of a plurality of users, so that a more intelligent product recommendation method is needed for product recommendation for users.
At present, most product recommendation methods can only perform matching screening of products according to the demand data of users and the data of products in a product library, so as to recommend products meeting conditions, such as: if the customer needs to purchase financial products at a certain investment institution and the demand of the customer for the products is low-risk and long-period, the low-risk and long-period products are screened from all financial products sold at the institution and recommended to the user. However, the product data matching dimension of the product recommendation method is single, and the accuracy of the data matching is not high, so that the accuracy of the product recommendation is low.
Disclosure of Invention
The invention provides a product recommendation method and device based on a vector matching technology, electronic equipment and a computer readable storage medium, and mainly aims to improve the accuracy of product recommendation.
In order to achieve the above object, the present invention provides a product recommendation method based on a vector matching technology, comprising:
obtaining a product recommendation request, wherein the product recommendation request comprises user information and product requirement information;
combining the product requirement information to construct a product requirement sequence;
screening products in a preset product library according to the product requirement sequence to obtain a first product set;
extracting user characteristics of the user information to obtain a user vector;
performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
calculating the relevance of the user vector and the product vector to obtain a relevance score;
performing relevance screening on the first product set by using the relevance scores to obtain a second product set;
obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores;
performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and pushing the target product to the terminal equipment corresponding to the product recommendation request.
Optionally, the extracting the user features of the user information to obtain a user vector includes:
performing text conversion on the user information to obtain text data;
performing word segmentation processing on the text data to obtain a plurality of text words;
performing word vector conversion on the text word segmentation to obtain a text word vector;
performing feature extraction on the text word vector by using a pre-trained feature extraction algorithm to obtain a feature word vector;
and performing arithmetic mean calculation on all the feature word vectors to obtain the user vector.
Optionally, the performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product includes:
acquiring all product attribute data of each product in the first product set;
converting each product attribute data of the product into a vector to obtain the product attribute vector;
transversely combining all product attribute vectors according to a preset sequence to obtain a product matrix;
and performing feature compression on the product matrix to obtain the product vector.
Optionally, the performing feature compression on the product matrix to obtain the product vector includes:
screening the maximum value of each column in the product matrix as the column characteristic value of each column;
and combining the column characteristic values of each column in sequence according to the sequence of the columns in the product matrix to obtain the product vector.
Optionally, the performing satisfaction screening on the second product set by using the product satisfaction score and the relevancy score includes:
calculating a recommendation coefficient for each product in the second set of products based on the product satisfaction score and the relevancy score;
and screening the products of which the recommendation coefficient is greater than a preset recommendation threshold value in the second product set to obtain the target products.
Optionally, before the obtaining of the product feedback score of each product in the second product set within the preset feedback time interval, the method further includes:
acquiring request time of the product recommendation request;
taking the request time as a right end point of an interval and taking the time period as the length of the interval;
and constructing an interval according to the interval right endpoint and the interval length to obtain the feedback time interval.
Optionally, the calculating a product satisfaction score from the product feedback score comprises:
evaluating the scoring characteristics of all the product feedback scores corresponding to each product in the second product set to obtain standard feedback scores;
performing score fluctuation evaluation calculation according to all the product feedback scores to obtain a fluctuation coefficient;
and performing multiplication calculation according to the standard feedback score and the fluctuation coefficient to obtain the product satisfaction score.
In order to solve the above problem, the present invention further provides a product recommendation device based on a vector matching technology, the device comprising:
the system comprises a feature extraction module, a product recommendation module and a product recommendation module, wherein the feature extraction module is used for acquiring a product recommendation request, and the product recommendation request comprises user information and product requirement information; combining the product requirement information to construct a product requirement sequence; screening products in a preset product library according to the product requirement sequence to obtain a first product set; extracting user characteristics of the user information to obtain a user vector; performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
the product screening module is used for calculating the relevancy of the user vector and the product vector to obtain a relevancy score; performing relevance screening on the first product set by using the relevance scores to obtain a second product set; obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores; performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and the product recommendation module is used for pushing the target product to the terminal equipment corresponding to the product recommendation request.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one computer program; and
and a processor executing the computer program stored in the memory to implement the product recommendation method based on the vector matching technology.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above product recommendation method based on the vector matching technology.
According to the embodiment of the invention, the products in the preset product library are screened according to the product requirement sequence obtained by combining the product requirement information to obtain the first product set, so that the products are primarily screened according to the user requirements; further, feature extraction is respectively carried out on the user information and each product in the first product set to obtain a user vector and a product vector, and relevance screening is carried out on the first product set according to relevance scores between the user vector and the product vector to obtain a second product set, so that secondary screening is carried out on the products by utilizing the relevance degree of the user features and the products; and further calculating a product satisfaction score according to the product feedback score of each product in the second product set within a preset feedback time interval, performing satisfaction screening on the second product set by using the product satisfaction score and the relevance score to obtain a target product, and further performing third screening on the product by using the product satisfaction score. The product is screened and recommended by using three dimensions of user requirements, the association degree of user characteristics and products and the product satisfaction degree score, so that the accuracy of product recommendation is improved. Therefore, the product recommendation method, the product recommendation device, the electronic equipment and the readable storage medium based on the vector matching technology improve the accuracy of product recommendation.
Drawings
Fig. 1 is a schematic flowchart of a product recommendation method based on a vector matching technique according to an embodiment of the present invention;
FIG. 2 is a block diagram of a product recommendation device based on vector matching technology according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device implementing a product recommendation method based on a vector matching technology according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a product recommendation method based on a vector matching technology. The execution subject of the product recommendation method based on the vector matching technology includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application. In other words, the product recommendation method based on the vector matching technology may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, which is a schematic flow chart of a product recommendation method based on a vector matching technology according to an embodiment of the present invention, in an embodiment of the present invention, the product recommendation method based on the vector matching technology includes:
s1, obtaining a product recommendation request, wherein the product recommendation request comprises user information and product requirement information;
in the embodiment of the present invention, the product recommendation request is a request for recommending a related product, which is initiated by a user, for example: the product recommendation request is a product recommendation request initiated by the user A for recommending a trusted product of a financial company. In the embodiment of the present invention, the user information is personal related information of the user, such as: basic information of the user, historical transaction information of the user, personal preference of the user, and the like; the product requirement information is the requirement of the user on the product, for example, the product is a financial product, the risk type is low risk, the investment cycle is long cycle, and the like.
S2, combining the product requirement information to construct a product requirement sequence;
in detail, in order to better recommend a product meeting the product requirement information, the embodiment of the present invention needs a more intuitive presentation of the requirement information, and performs field construction on the product requirement information to obtain a product requirement field, optionally, in the embodiment of the present invention, if the field is constructed to construct the product requirement information as a key value pair to obtain the product requirement field, if the product requirement information is a low risk type, the field construction is performed to obtain a corresponding product requirement field as a "risk type: low risk"; further, all the product requirement fields are randomly combined to obtain the product requirement sequence, wherein the combination mode comprises sequential combination and random combination, such as common 'risk type: low risk', 'investment period: long period', and then the product requirement sequence can be [ risk type: low risk, investment period: long period ]. Optionally, in another implementation of the present invention, all the product requirement fields may be combined according to a preset order to obtain the product requirement sequence.
S3, screening products in a preset product library according to the product requirement sequence to obtain a first product set;
in the embodiment of the invention, product attribute data of fields corresponding to each product in the product library are screened according to data fields and corresponding field sequences in the product requirement sequence, and are combined to obtain a product sequence; such as: the product requirement sequence may be [ risk type: low risk, investment cycle: long cycle ], the corresponding data fields are "risk type" and "investment cycle", then the product attribute data corresponding to the "risk type" field and the product attribute data corresponding to the "investment cycle" field corresponding to each product are screened and combined to obtain the corresponding product sequence, further, the product sequence and the product requirement sequence are compared for data consistency to obtain a comparison result, optionally, the comparison result is data consistency or data inconsistency, further, the comparison result is screened and the product with the data consistency is obtained, and the first product set is obtained. If the product requirement sequence is [ risk type: low risk, investment period: long period ], and the product sequence is [ risk type: low risk, investment period: short period ], the comparison result is inconsistent data.
S4, extracting user characteristics of the user information to obtain a user vector;
in detail, in the embodiment of the present invention, the user information includes, but is not limited to, the age, sex, occupation, and hobbies of the user, and the obtained user information may be in various forms, such as video, image, text, and the like, so that the extracted user features are more accurate.
The embodiment of the invention can analyze the user information through the pre-trained intelligent model and extract the user characteristics of the user. The intelligent model includes, but is not limited to, an OCR (Optical Character Recognition) model, an NLP (Natural Language Processing) model, an ASR (Automatic Speech Recognition) model, and the like.
In one embodiment of the present invention, the extracting user characteristics of the user information to obtain a user vector includes:
step A, performing text conversion on the user information to obtain text data;
b, performing word segmentation processing on the text data to obtain a plurality of text word segments;
step C, performing word vector conversion on the text participles to obtain text word vectors;
d, performing feature extraction on the text word vector by using a pre-trained feature extraction algorithm to obtain a feature word vector;
and E, performing arithmetic mean calculation on all the feature word vectors to obtain the user vector.
For example, the user information includes image data and video data, and the image data in the user information can be processed by using an OCR model to convert the image data into text data; and processing the video data in the user information by utilizing the combination of the ASR model and the OCR model so as to convert the video data into text data.
The present embodiment may perform word segmentation processing on the text data by using a pre-constructed standard dictionary, where the standard dictionary includes a plurality of standard words. For example, the text data is divided into different lengths, the division result is retrieved from the standard dictionary, and if the standard participle identical to the division result can be retrieved, the standard participle is determined to be the text participle of the text data.
In one embodiment of the present invention, the performing word segmentation processing on the text data to obtain text words includes:
acquiring a pre-constructed standard dictionary, wherein the standard dictionary comprises a plurality of standard participles;
dividing the text data into texts according to a preset first length to obtain search terms;
and searching the search word in the standard dictionary, determining the search word as a text word of the text data when a standard word which is the same as the search word is searched from the standard dictionary, returning to the step of text division, and dividing the text according to a preset second length until the number of times of the text division reaches a preset number of times to obtain the text word corresponding to the text data.
For example, the text data is divided according to different preset lengths, and the search words obtained by dividing the text each time are searched in the dictionary to obtain text word segmentation until the number of times of text division reaches the preset number of times, so as to implement word segmentation of the text data.
In the embodiment, the word segmentation of the text data is realized in a mode of dividing and searching the text data according to different lengths, the content of the text data does not need to be analyzed, and the efficiency of word segmentation of the text data is improved.
In this embodiment, the text segmentation may be converted into a text word vector by using a preset word2vec model.
Further, the feature extraction algorithm includes, but is not limited to, a bayesian classification algorithm, a logistic regression algorithm, a KNN algorithm, and the like, and the feature extraction algorithm is used to perform feature extraction on the text word vectors to obtain feature word vectors, and vector compression is performed on all the feature word vectors to obtain the user vectors.
In another embodiment of the invention, the user information can be stored in the block chain nodes, and the privacy of the user information is protected.
S5, extracting product features of each product in the first product set to obtain a product vector corresponding to each product;
in the embodiment of the present invention, each product corresponds to a plurality of product attributes, and each product attribute corresponds to corresponding product attribute data, such as: the corresponding product attribute of the financial product has risk level, expected income and investment period.
Further, in the embodiment of the present invention, performing product feature extraction on each product in the first product set includes:
acquiring all product attribute data of each product in the first product set;
converting each product attribute data of the product into a vector to obtain the product attribute vector;
transversely combining all product attribute vectors according to a preset sequence to obtain a product matrix;
screening the maximum value of each column in the product matrix as the column characteristic value of each column;
and combining the column characteristic values of each column in sequence according to the sequence of the columns in the product matrix to obtain the product vector.
For example: the product matrix is
Then the column eigenvalue of the first column of the product matrix is 3, the class eigenvalue of the second column is 9, the column eigenvalue of the third column is 6, and the column eigenvalues of each column are combined in turn to obtain the product vector [ 396 ]]。
S6, calculating the relevance of the user vector and the product vector to obtain a relevance score;
in the embodiment of the invention, in order to further screen products more suitable for users in the first product set, correlation calculation is performed according to the user vector and the product vector to obtain a correlation score.
Optionally, in the embodiment of the present invention, the following formula is used to calculate the correlation degree:
wherein, XiThe i-th element, Y, representing the user vector XiAnd the ith element of the product vector Y is Sim, the similarity of the user vector X and the product vector Y is represented by Sim, and the vector dimensionality of the user vector and the product vector is represented by n.
S7, performing relevance screening on the first product set by using the relevance scores to obtain a second product set;
in the embodiment of the invention, the size of the relevancy score represents the matching degree of the corresponding product and the user, so that in order to select the product with the best matching degree, relevancy screening is performed on the first product set by using the relevancy score to obtain a second product set.
In detail, in the embodiment of the present invention, the products in the first product set whose relevancy scores are greater than a preset relevancy score threshold are screened to obtain the second product set.
S8, obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback score;
in the embodiment of the present invention, in order to ensure that the product feedback scores of the products have a reference value, it is necessary to evaluate the product feedback scores with a relatively new evaluation time, so the embodiment of the present invention obtains the product feedback scores of each product in the second product set within a preset feedback time interval, and calculates the product satisfaction scores according to the product feedback scores, where the product feedback scores of each product in the embodiment of the present invention may be one or more, for example: the product feedback score of the product A is that the score of the user A is 3, the score of the user B is 5 and the score of the user C is 4.
In detail, in the embodiment of the present invention, before obtaining the product feedback score of each product in the second product set within the preset feedback time interval, the method further includes: acquiring request time of the product recommendation request; and taking the request time as an interval right endpoint, taking a preset time period as an interval length, and constructing an interval according to the interval right endpoint and the interval length to obtain the feedback time interval. For example: the request time is 3/11 and the time period is two days, then the feedback time interval is 3/9, 3/11.
In detail, in the embodiment of the present invention, the calculating a product satisfaction score according to the product feedback score includes: scoring feature evaluation is performed on all the product feedback scores corresponding to each product in the second product set, optionally, an arithmetic mean of all the product feedback scores is used as the standard feedback score or a median of all the product feedback scores is used as the standard feedback score, and features of all the product feedback scores are evaluated through the standard feedback score; further, in order to reduce the condition that the reference value of the score is too low due to the fact that the product feedback score fluctuates too much, the embodiment of the present invention performs score fluctuation evaluation calculation according to all the product feedback scores to obtain a fluctuation coefficient, and optionally, the embodiment of the present invention may calculate the variance or standard deviation of all the product feedback scores to measure the score fluctuation of the product feedback scores to obtain the fluctuation coefficient; further, in the embodiment of the present invention, a product satisfaction score is obtained by performing multiplication according to the standard feedback score and the fluctuation coefficient, for example: the standard feedback score is 5 and the ripple factor is 0.2, then the product satisfaction score is 5 x 0.2 ═ 1.
S9, performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
in detail, in the embodiment of the present invention, a recommendation coefficient of each product in the second product set is calculated according to the product satisfaction score and the relevancy score, and products in the second product set whose recommendation coefficient is greater than a preset recommendation threshold are screened to obtain the target product.
Optionally, in the embodiment of the present invention, the recommendation coefficient may be calculated by using the following formula:
T＝a*mj+b*nj
wherein a and b are preset product weights, and m isjIs the relevancy score, n, of product j in the second product setjAnd T is the product satisfaction score of the product j in the second product set, and T is the recommendation coefficient of the product j in the second product set.
And S10, pushing the target product to the terminal equipment corresponding to the product recommendation request.
In the embodiment of the invention, the target product is pushed to the terminal equipment corresponding to the product recommendation request. The terminal device includes: intelligent terminals such as mobile phones, computers and tablets.
According to the embodiment of the invention, the products in the preset product library are screened according to the product requirement sequence obtained by combining the product requirement information to obtain the first product set, so that the products are primarily screened according to the user requirements; further, feature extraction is respectively carried out on the user information and each product in the first product set to obtain a user vector and a product vector, and relevance screening is carried out on the first product set according to relevance scores between the user vector and the product vector to obtain a second product set, so that secondary screening is carried out on the products by utilizing the relevance degree of the user features and the products; and further calculating a product satisfaction score according to the product feedback score of each product in the second product set within a preset feedback time interval, performing satisfaction screening on the second product set by using the product satisfaction score and the relevance score to obtain a target product, and further performing third screening on the product by using the product satisfaction score. The product is screened and recommended by using three dimensions of user requirements, the association degree of user characteristics and products and the product satisfaction degree score, so that the accuracy of product recommendation is improved. Therefore, the product recommendation method based on the vector matching technology provided by the embodiment of the invention improves the accuracy of product recommendation.
Fig. 2 is a functional block diagram of the product recommendation device based on the vector matching technology according to the present invention.
The product recommendation device 100 based on the vector matching technology can be installed in an electronic device. According to the implemented functions, the product recommendation device based on the vector matching technology may include a feature extraction module 101, a product screening module 102, and a product recommendation module 103, which may also be referred to as a unit, and refer to a series of computer program segments that can be executed by a processor of an electronic device and can perform fixed functions, and are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the feature extraction module 101 is configured to obtain a product recommendation request, where the product recommendation request includes user information and product requirement information; combining the product requirement information to construct a product requirement sequence; screening products in a preset product library according to the product requirement sequence to obtain a first product set; extracting user characteristics of the user information to obtain a user vector; performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
in the embodiment of the present invention, the product recommendation request is a request for recommending a related product, which is initiated by a user, for example: the product recommendation request is a product recommendation request initiated by the user A for recommending a trusted product of a financial company. In the embodiment of the present invention, the user information is personal related information of the user, such as: basic information of the user, historical transaction information of the user, personal preference of the user, and the like; the product requirement information is the requirement of the user on the product, for example, the product is a financial product, the risk type is low risk, the investment cycle is long cycle, and the like.
In detail, in order to better recommend a product meeting the product requirement information, the embodiment of the present invention needs more intuitive presentation of the requirement information, the feature extraction module 101 performs field construction on the product requirement information to obtain a product requirement field, optionally, in the embodiment of the present invention, if the field construction is performed, the product requirement information is constructed as a key value pair to obtain a product requirement field, and if the product requirement information is a low risk type, the field construction is performed to obtain a corresponding product requirement field as a "risk type: low risk"; further, all the product requirement fields are randomly combined to obtain the product requirement sequence, wherein the combination mode comprises sequential combination and random combination, such as common 'risk type: low risk', 'investment period: long period', and then the product requirement sequence can be [ risk type: low risk, investment period: long period ]. Optionally, in another implementation of the present invention, all the product requirement fields may be combined according to a preset order to obtain the product requirement sequence.
In the embodiment of the present invention, the feature extraction module 101 filters product attribute data of corresponding fields of each product in the product library according to data fields in the product requirement sequence and corresponding field sequences, and combines the product attribute data to obtain a product sequence; such as: the product requirement sequence may be [ risk type: low risk, investment cycle: long cycle ], the corresponding data fields are "risk type" and "investment cycle", then the product attribute data corresponding to the "risk type" field and the product attribute data corresponding to the "investment cycle" field corresponding to each product are screened and combined to obtain the corresponding product sequence, further, the product sequence and the product requirement sequence are compared for data consistency to obtain a comparison result, optionally, the comparison result is data consistency or data inconsistency, further, the comparison result is screened and the product with the data consistency is obtained, and the first product set is obtained. If the product requirement sequence is [ risk type: low risk, investment period: long period ], and the product sequence is [ risk type: low risk, investment period: short period ], the comparison result is inconsistent data.
In detail, in the embodiment of the present invention, the user information includes, but is not limited to, the age, sex, occupation, and hobbies of the user, and the obtained user information may be in various forms, such as video, image, text, and the like, so that the extracted user features are more accurate.
The feature extraction module 101 of the embodiment of the present invention may analyze the user information through a pre-trained intelligent model to extract the user features of the user. The intelligent model includes, but is not limited to, an OCR (Optical Character Recognition) model, an NLP (Natural Language Processing) model, an ASR (Automatic Speech Recognition) model, and the like.
In one embodiment of the present invention, the extracting user characteristics of the user information by the characteristic extracting module 101 to obtain a user vector includes:
step A, performing text conversion on the user information to obtain text data;
b, performing word segmentation processing on the text data to obtain a plurality of text word segments;
step C, performing word vector conversion on the text participles to obtain text word vectors;
d, performing feature extraction on the text word vector by using a pre-trained feature extraction algorithm to obtain a feature word vector;
and E, performing arithmetic mean calculation on all the feature word vectors to obtain the user vector.
For example, the user information includes image data and video data, and the image data in the user information can be processed by using an OCR model to convert the image data into text data; and processing the video data in the user information by utilizing the combination of the ASR model and the OCR model so as to convert the video data into text data.
The present embodiment may perform word segmentation processing on the text data by using a pre-constructed standard dictionary, where the standard dictionary includes a plurality of standard words. For example, the text data is divided into different lengths, the division result is retrieved from the standard dictionary, and if the standard participle identical to the division result can be retrieved, the standard participle is determined to be the text participle of the text data.
In one embodiment of the present invention, the performing word segmentation processing on the text data by the feature extraction module 101 to obtain text word segmentation includes:
acquiring a pre-constructed standard dictionary, wherein the standard dictionary comprises a plurality of standard participles;
dividing the text data into texts according to a preset first length to obtain search terms;
and searching the search word in the standard dictionary, determining the search word as a text word of the text data when a standard word which is the same as the search word is searched from the standard dictionary, returning to the step of text division, and dividing the text according to a preset second length until the number of times of the text division reaches a preset number of times to obtain the text word corresponding to the text data.
For example, the text data is divided according to different preset lengths, and the search words obtained by dividing the text each time are searched in the dictionary to obtain text word segmentation until the number of times of text division reaches the preset number of times, so as to implement word segmentation of the text data.
In the embodiment, the word segmentation of the text data is realized in a mode of dividing and searching the text data according to different lengths, the content of the text data does not need to be analyzed, and the efficiency of word segmentation of the text data is improved.
In this embodiment, the text segmentation may be converted into a text word vector by using a preset word2vec model.
Further, the feature extraction algorithm includes, but is not limited to, a bayesian classification algorithm, a logistic regression algorithm, a KNN algorithm, and the like, and the feature extraction algorithm is used to perform feature extraction on the text word vectors to obtain feature word vectors, and vector compression is performed on all the feature word vectors to obtain the user vectors.
In another embodiment of the invention, the user information can be stored in the block chain nodes, and the privacy of the user information is protected.
In the embodiment of the present invention, each product corresponds to a plurality of product attributes, and each product attribute corresponds to corresponding product attribute data, such as: the corresponding product attribute of the financial product has risk level, expected income and investment period.
Further, in the embodiment of the present invention, the performing, by the feature extraction module 101, product feature extraction on each product in the first product set includes:
acquiring all product attribute data of each product in the first product set;
converting each product attribute data of the product into a vector to obtain the product attribute vector;
transversely combining all product attribute vectors according to a preset sequence to obtain a product matrix;
screening the maximum value of each column in the product matrix as the column characteristic value of each column;
and combining the column characteristic values of each column in sequence according to the sequence of the columns in the product matrix to obtain the product vector.
For example: the product matrix is
Then the column eigenvalue of the first column of the product matrix is 3, the class eigenvalue of the second column is 9, the column eigenvalue of the third column is 6, and the column eigenvalues of each column are combined in turn to obtain the product vector [ 396 ]]。
The product screening module 102 is configured to perform relevancy calculation on the user vector and the product vector to obtain a relevancy score; performing relevance screening on the first product set by using the relevance scores to obtain a second product set; obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores; performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
in an embodiment of the present invention, in order to further screen products in the first product set that are more suitable for the user, the product screening module 102 performs relevancy calculation according to the user vector and the product vector to obtain a relevancy score.
Optionally, in the embodiment of the present invention, the following formula is used to calculate the correlation degree:
wherein, XiThe i-th element, Y, representing the user vector XiAnd the ith element of the product vector Y is Sim, the similarity of the user vector X and the product vector Y is represented by Sim, and the vector dimensionality of the user vector and the product vector is represented by n.
In the embodiment of the present invention, the size of the relevancy score represents the matching degree between the corresponding product and the user, and therefore, in order to select the product with the best matching degree, the product screening module 102 performs relevancy screening on the first product set by using the relevancy score to obtain a second product set.
In detail, in the embodiment of the present invention, the product screening module 102 screens the products in the first product set whose relevancy scores are greater than a preset relevancy score threshold to obtain the second product set.
In the embodiment of the present invention, in order to ensure that the product feedback scores of the products have a reference value, it is necessary to evaluate the product feedback scores with a relatively new evaluation time, so in the embodiment of the present invention, the product screening module 102 obtains the product feedback scores of each product in the second product set within a preset feedback time interval, and calculates the product satisfaction scores according to the product feedback scores, where the product feedback score number of each product in the embodiment of the present invention may be one or more, for example: the product feedback score of the product A is that the score of the user A is 3, the score of the user B is 5 and the score of the user C is 4.
In detail, before the product screening module 102 obtains the product feedback score of each product in the second product set within a preset feedback time interval, the method further includes: acquiring request time of the product recommendation request; and taking the request time as an interval right endpoint, taking a preset time period as an interval length, and constructing an interval according to the interval right endpoint and the interval length to obtain the feedback time interval. For example: the request time is 3/11 and the time period is two days, then the feedback time interval is 3/9, 3/11.
In detail, in the embodiment of the present invention, the product screening module 102 calculates a product satisfaction score according to the product feedback score, including: scoring feature evaluation is performed on all the product feedback scores corresponding to each product in the second product set, optionally, an arithmetic mean of all the product feedback scores is used as the standard feedback score or a median of all the product feedback scores is used as the standard feedback score, and features of all the product feedback scores are evaluated through the standard feedback score; further, in order to reduce the condition that the reference value of the score is too low due to the fact that the product feedback score fluctuates too much, the embodiment of the present invention performs score fluctuation evaluation calculation according to all the product feedback scores to obtain a fluctuation coefficient, and optionally, the embodiment of the present invention may calculate the variance or standard deviation of all the product feedback scores to measure the score fluctuation of the product feedback scores to obtain the fluctuation coefficient; further, in the embodiment of the present invention, a product satisfaction score is obtained by performing multiplication according to the standard feedback score and the fluctuation coefficient, for example: the standard feedback score is 5 and the ripple factor is 0.2, then the product satisfaction score is 5 x 0.2 ═ 1.
In detail, in the embodiment of the present invention, the product screening module 102 calculates a recommendation coefficient of each product in the second product set according to the product satisfaction score and the relevancy score, and screens products in the second product set whose recommendation coefficients are greater than a preset recommendation threshold value to obtain the target product.
Optionally, in the embodiment of the present invention, the recommendation coefficient may be calculated by using the following formula:
T＝a*mj+b*nj
wherein a and b are preset product weights, and m isjIs the relevancy score, n, of product j in the second product setjAnd T is the product satisfaction score of the product j in the second product set, and T is the recommendation coefficient of the product j in the second product set.
The product recommendation module 103 is configured to push the target product to a terminal device corresponding to the product recommendation request.
In the embodiment of the present invention, the product recommendation module 103 pushes the target product to the terminal device corresponding to the product recommendation request. The terminal device includes: intelligent terminals such as mobile phones, computers and tablets.
Fig. 3 is a schematic structural diagram of an electronic device implementing the product recommendation method based on the vector matching technology according to the present invention.
The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a product recommendation program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of product recommendation programs, etc., but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., product recommendation programs, etc.) stored in the memory 11 and calling data stored in the memory 11.
The communication bus 12 may be a PerIPheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Optionally, the communication interface 13 may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further include a user interface, which may be a Display (Display), an input unit (such as a Keyboard (Keyboard)), and optionally, a standard wired interface, or a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The product recommendation program stored in the memory 11 of the electronic device is a combination of computer programs, which when run in the processor 10, may implement:
obtaining a product recommendation request, wherein the product recommendation request comprises user information and product requirement information;
combining the product requirement information to construct a product requirement sequence;
screening products in a preset product library according to the product requirement sequence to obtain a first product set;
extracting user characteristics of the user information to obtain a user vector;
performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
calculating the relevance of the user vector and the product vector to obtain a relevance score;
performing relevance screening on the first product set by using the relevance scores to obtain a second product set;
obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores;
performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and pushing the target product to the terminal equipment corresponding to the product recommendation request.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
Embodiments of the present invention may also provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program may implement:
obtaining a product recommendation request, wherein the product recommendation request comprises user information and product requirement information;
combining the product requirement information to construct a product requirement sequence;
screening products in a preset product library according to the product requirement sequence to obtain a first product set;
extracting user characteristics of the user information to obtain a user vector;
performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
calculating the relevance of the user vector and the product vector to obtain a relevance score;
performing relevance screening on the first product set by using the relevance scores to obtain a second product set;
obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores;
performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and pushing the target product to the terminal equipment corresponding to the product recommendation request.
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A product recommendation method based on a vector matching technology is characterized by comprising the following steps:
obtaining a product recommendation request, wherein the product recommendation request comprises user information and product requirement information;
combining the product requirement information to construct a product requirement sequence;
screening products in a preset product library according to the product requirement sequence to obtain a first product set;
extracting user characteristics of the user information to obtain a user vector;
performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
calculating the relevance of the user vector and the product vector to obtain a relevance score;
performing relevance screening on the first product set by using the relevance scores to obtain a second product set;
obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores;
performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and pushing the target product to the terminal equipment corresponding to the product recommendation request.
2. The method for recommending products based on vector matching technology according to claim 1, wherein said extracting user features from said user information to obtain a user vector comprises:
performing text conversion on the user information to obtain text data;
performing word segmentation processing on the text data to obtain a plurality of text words;
performing word vector conversion on the text word segmentation to obtain a text word vector;
performing feature extraction on the text word vector by using a pre-trained feature extraction algorithm to obtain a feature word vector;
and performing arithmetic mean calculation on all the feature word vectors to obtain the user vector.
3. The method for recommending products based on vector matching technology according to claim 1, wherein said extracting product features of each product in said first product set to obtain a product vector corresponding to each product comprises:
acquiring all product attribute data of each product in the first product set;
converting each product attribute data of the product into a vector to obtain the product attribute vector;
transversely combining all product attribute vectors according to a preset sequence to obtain a product matrix;
and performing feature compression on the product matrix to obtain the product vector.
4. The method of claim 3, wherein the feature compressing the product matrix to obtain the product vector comprises:
screening the maximum value of each column in the product matrix as the column characteristic value of each column;
and combining the column characteristic values of each column in sequence according to the sequence of the columns in the product matrix to obtain the product vector.
5. The vector matching technique based product recommendation method of claim 1, wherein said performing satisfaction screening on said second set of products using said product satisfaction score and said relevancy score comprises:
calculating a recommendation coefficient for each product in the second set of products based on the product satisfaction score and the relevancy score;
and screening the products of which the recommendation coefficient is greater than a preset recommendation threshold value in the second product set to obtain the target products.
6. The method of claim 5, wherein before obtaining the product feedback score of each product in the second set within a preset feedback time interval, the method further comprises:
acquiring request time of the product recommendation request;
taking the request time as a right end point of an interval and taking the time period as the length of the interval;
and constructing an interval according to the interval right endpoint and the interval length to obtain the feedback time interval.
7. The vector matching technique-based product recommendation method of any one of claims 1-6, wherein said calculating a product satisfaction score from said product feedback score comprises:
evaluating the scoring characteristics of all the product feedback scores corresponding to each product in the second product set to obtain standard feedback scores;
performing score fluctuation evaluation calculation according to all the product feedback scores to obtain a fluctuation coefficient;
and performing multiplication calculation according to the standard feedback score and the fluctuation coefficient to obtain the product satisfaction score.
8. A product recommendation device based on a vector matching technology is characterized by comprising:
the system comprises a feature extraction module, a product recommendation module and a product recommendation module, wherein the feature extraction module is used for acquiring a product recommendation request, and the product recommendation request comprises user information and product requirement information; combining the product requirement information to construct a product requirement sequence; screening products in a preset product library according to the product requirement sequence to obtain a first product set; extracting user characteristics of the user information to obtain a user vector; performing product feature extraction on each product in the first product set to obtain a product vector corresponding to each product;
the product screening module is used for calculating the relevancy of the user vector and the product vector to obtain a relevancy score; performing relevance screening on the first product set by using the relevance scores to obtain a second product set; obtaining a product feedback score of each product in the second product set within a preset feedback time interval, and calculating a product satisfaction score according to the product feedback scores; performing satisfaction screening on the second product set by using the product satisfaction scores and the relevancy scores to obtain target products;
and the product recommendation module is used for pushing the target product to the terminal equipment corresponding to the product recommendation request.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of product recommendation based on vector matching techniques of any of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for product recommendation based on vector matching technique according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110728147.2A CN113468421A (en) | 2021-06-29 | 2021-06-29 | Product recommendation method, device, equipment and medium based on vector matching technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110728147.2A CN113468421A (en) | 2021-06-29 | 2021-06-29 | Product recommendation method, device, equipment and medium based on vector matching technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113468421A true CN113468421A (en) | 2021-10-01 |
Family
ID=77873870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110728147.2A Pending CN113468421A (en) | 2021-06-29 | 2021-06-29 | Product recommendation method, device, equipment and medium based on vector matching technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468421A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115018588A (en) * | 2022-06-24 | 2022-09-06 | 平安普惠企业管理有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
| CN115146704A (en) * | 2022-05-27 | 2022-10-04 | 中睿信数字技术有限公司 | Event automatic classification method and system based on distributed database and machine learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技（深圳）有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
| CN109584003A (en) * | 2018-11-26 | 2019-04-05 | 上海景域文化传播股份有限公司 | Intelligent recommendation system |
| CN112559901A (en) * | 2020-12-11 | 2021-03-26 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device, electronic equipment, storage medium and computer program product |
| CN112633988A (en) * | 2020-12-30 | 2021-04-09 | 平安证券股份有限公司 | User product recommendation method and device, electronic equipment and readable storage medium |
-
2021
- 2021-06-29 CN CN202110728147.2A patent/CN113468421A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技（深圳）有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
| CN109584003A (en) * | 2018-11-26 | 2019-04-05 | 上海景域文化传播股份有限公司 | Intelligent recommendation system |
| CN112559901A (en) * | 2020-12-11 | 2021-03-26 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device, electronic equipment, storage medium and computer program product |
| CN112633988A (en) * | 2020-12-30 | 2021-04-09 | 平安证券股份有限公司 | User product recommendation method and device, electronic equipment and readable storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115146704A (en) * | 2022-05-27 | 2022-10-04 | 中睿信数字技术有限公司 | Event automatic classification method and system based on distributed database and machine learning |
| CN115146704B (en) * | 2022-05-27 | 2023-11-07 | 中睿信数字技术有限公司 | Event automatic classification method and system based on distributed database and machine learning |
| CN115018588A (en) * | 2022-06-24 | 2022-09-06 | 平安普惠企业管理有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
| CN112541338A (en) | Similar text matching method and device, electronic equipment and computer storage medium | |
| CN111797214A (en) | FAQ database-based problem screening method and device, computer equipment and medium | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN112883190A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN112507230B (en) | Webpage recommendation method and device based on browser, electronic equipment and storage medium | |
| CN113468421A (en) | Product recommendation method, device, equipment and medium based on vector matching technology | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN112883730A (en) | Similar text matching method and device, electronic equipment and storage medium | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113591881B (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN115204971B (en) | Product recommendation method, device, electronic equipment and computer readable storage medium | |
| CN116450916A (en) | Information query method and device based on fixed-segment classification, electronic equipment and medium | |
| CN113705201B (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| CN113343102A (en) | Data recommendation method and device based on feature screening, electronic equipment and medium | |
| CN114741608A (en) | News recommendation method, device, equipment and storage medium based on user portrait | |
| CN113656586B (en) | Emotion classification method, emotion classification device, electronic equipment and readable storage medium | |
| CN114676307A (en) | Ranking model training method, device, equipment and medium based on user retrieval | |
| CN115186188A (en) | Product recommendation method, device and equipment based on behavior analysis and storage medium | |
| CN114240560A (en) | Product ranking method, device, equipment and storage medium based on multidimensional analysis | |
| CN114610854A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114518993A (en) | System performance monitoring method, device, equipment and medium based on business characteristics | |
| CN113434660A (en) | Product recommendation method, device, equipment and storage medium based on multi-domain classification |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211001 |
|
| WD01 | Invention patent application deemed withdrawn after publication |