CN113706253A - Real-time product recommendation method and device, electronic equipment and readable storage medium - Google Patents
Real-time product recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113706253A CN113706253A CN202111009741.2A CN202111009741A CN113706253A CN 113706253 A CN113706253 A CN 113706253A CN 202111009741 A CN202111009741 A CN 202111009741A CN 113706253 A CN113706253 A CN 113706253A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- target
- text
- label
- 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 48
- 238000012163 sequencing technique Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008094 contradictory effect 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
- 230000018109 developmental process Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning 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
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a real-time product recommendation method, which comprises the following steps: determining a text label set corresponding to the issued text data, and updating a corresponding product label set based on the text label set; constructing a user portrait based on the registration information; acquiring a target text tag set corresponding to the specified text data, updating an interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set; and inputting the target product label set corresponding to each product in the product set to be recommended and the target user portrait corresponding to the appointed user into the product sorting model to obtain a sorting result of the products in the product set to be recommended, and determining the target recommended product based on the sorting result. The invention also provides a real-time product recommendation device, electronic equipment and a readable storage medium. The invention realizes accurate and real-time product recommendation for the user.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a real-time product recommendation method and device, electronic equipment and a readable storage medium.
Background
With the development of science and technology, the product development is more diversified, and how to recommend interesting products for users from a plurality of products is a current focus of attention.
Currently, the following two ways are generally adopted to recommend products to users, one way is to recommend products to users based on preset indexes, such as sales volume and heat; and secondly, recommending products for the user based on the user behavior data. However, the recommendation accuracy of the first method is not high, the data size of the second method is large, the calculation is time-consuming, the method is suitable for offline recommendation, and the instantaneity is not high.
Therefore, a real-time product recommendation method is needed to accurately recommend products to users in real time.
Disclosure of Invention
In view of the above, there is a need to provide a real-time product recommendation method, which aims to accurately recommend products to users in real time.
The invention provides a real-time product recommendation method, which comprises the following steps:
when it is monitored that a target application program releases text data carrying product identification, determining a text label set corresponding to the released text data, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
when it is monitored that a target application program generates registration information carrying a user identifier, constructing a user portrait corresponding to the user identifier based on the registration information, and storing the user portrait to a second database;
when it is monitored that a certain specified user clicks on certain specified text data of the target application program, acquiring a target text tag set corresponding to the specified text data from the first database, updating an interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
Optionally, the determining a text label set corresponding to the published text data includes:
performing word segmentation processing on the issued text data to obtain a word set;
calculating the word frequency of each word in the word set in the published text data;
acquiring a text data set corresponding to the target application program, and calculating a relevance value of each word in the word set and the text data set;
calculating an importance value of each word in the set of words based on the word frequency and the relevance value;
and according to the sequence of the importance values from high to low, screening a first number of words from the word set as first keywords corresponding to the published text data, and taking the set of the first keywords as a text label set corresponding to the published text data.
Optionally, the updating the product tag set corresponding to the product identifier based on the text tag set includes:
acquiring a set of text label sets of each text data corresponding to the product identification to obtain an initial label set corresponding to the product identification;
and sorting the labels in the initial label set according to the order of the importance values from high to low, extracting a second number of labels which are sorted at the top as second keywords corresponding to the product identification, and taking the set of the second keywords as a product label set corresponding to the product identification.
Optionally, the constructing a user portrait corresponding to the user identifier based on the registration information includes:
acquiring a mapping relation between index values and labels of all index items in the registration information;
determining a target label corresponding to the index value of each index item in the registration information corresponding to the user identifier based on the mapping relation;
and taking the set of target labels as a user portrait corresponding to the user identification.
Optionally, the updating the interest tag set of the specified user based on the target text tag set includes:
obtaining an interest tag set corresponding to the specified user from a third database, and merging the interest tag set and the target text tag set to obtain a merged interest tag set;
and sorting the labels in the combined interest label set according to the order of the importance values from high to low, extracting a third number of labels which are sorted in the front as third key words corresponding to the specified user, and taking the set of the third key words as an updated interest label set corresponding to the specified user.
Optionally, the determining, based on the updated interest tag set, a to-be-recommended product set corresponding to the specified user includes:
matching the updated interest tag set with product tag sets corresponding to products of the target application program, and taking a set of successfully matched tags as a matched tag set corresponding to each product;
calculating the total importance value corresponding to each label in the matched label set corresponding to each product, and calculating the matching value of the designated user and each product based on the total importance value;
and sorting according to the sequence of the matching degree values from high to low, and taking the set of the fourth quantity of products which are sorted at the top as the set of the products to be recommended corresponding to the specified user.
Optionally, after determining the set of products to be recommended corresponding to the specified user based on the updated interest tag set, the method further includes:
and performing filtering processing on the products in the product set to be recommended to obtain an updated product set to be recommended.
In order to solve the above problems, the present invention also provides a real-time product recommendation apparatus, including:
the updating module is used for determining a text label set corresponding to the issued text data when it is monitored that a target application program issues the text data carrying the product identification, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
the construction module is used for constructing a user portrait corresponding to the user identification based on the registration information when the fact that the registration information carrying the user identification is generated by the target application program is monitored, and storing the user portrait to a second database;
the determining module is used for acquiring a target text tag set corresponding to the specified text data from the first database when it is monitored that a specified user clicks on the specified text data of the target application program, updating the interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and the recommending module is used for acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a real-time product recommendation program executable by the at least one processor, the real-time product recommendation program being executable by the at least one processor to enable the at least one processor to perform the real-time product recommendation method described above.
In order to solve the above problems, the present invention also provides a computer-readable storage medium having a real-time product recommendation program stored thereon, the real-time product recommendation program being executable by one or more processors to implement the above real-time product recommendation method.
Compared with the prior art, the method comprises the steps of firstly determining a text label set corresponding to published text data, and updating a corresponding product label set based on the text label set; then, constructing a user portrait based on the registration information; then, acquiring a target text tag set corresponding to the specified text data, updating the interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set; and finally, inputting the target product label set corresponding to each product in the product set to be recommended and the target user portrait corresponding to the appointed user into the product sorting model to obtain a sorting result of the products in the product set to be recommended and determine the target recommended product. The method and the system determine the text label set when the text data is published, and construct the user portrait when the user registers, so that the interest label set can be updated in real time when the user generates a clicking action, the product set to be recommended is determined based on the interest label set, and the products in the product set to be recommended are accurately sorted based on the user portrait, so that the target recommended product is determined, and the real-time performance and the accuracy of product recommendation are ensured. Therefore, the invention realizes accurate and real-time product recommendation for the user.
Drawings
FIG. 1 is a flowchart illustrating a real-time product recommendation method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a real-time product recommendation device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device implementing a real-time product recommendation method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
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.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides a real-time product recommendation method. Referring to fig. 1, a flowchart of a real-time product recommendation method according to an embodiment of the present invention is shown. The method may be performed by an electronic device, which may be implemented by software and/or hardware.
In this embodiment, the real-time product recommendation method includes:
s1, when it is monitored that the target application program releases the text data carrying the product identification, determining a text label set corresponding to the released text data, updating the product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database.
In this embodiment, a target application is taken as an example of an application for purchasing insurance products, and the text data may be articles or news about the insurance products in the target application.
In this embodiment, a keyword of each text data in the target application program is extracted, a text tag set corresponding to each text data is determined based on the keyword, and a product tag set corresponding to each product of the target application program is determined according to the text tag set.
The determining a text label set corresponding to the published text data includes:
a11, performing word segmentation processing on the issued text data to obtain a word set;
in this embodiment, a forward maximum matching method, a reverse maximum matching method, or a least segmentation method may be used to perform word segmentation processing on the published text data.
A12, calculating the word frequency of each word in the word set in the published text data;
the calculation formula of the word frequency is as follows:
wherein p isiThe word frequency of the ith word in the word set, ciThe number of times of the ith word in the word set appearing in the published text data is shown, n is the total number of words in the word set, cjThe number of times the jth word in the set of words appears in the published text data.
A13, acquiring a text data set corresponding to the target application program, and calculating a relevance value of each word in the word set and the text data set;
selecting a word from the set of words, the selected word having a relevance value to the text data set of: a ratio of a number of text data in the text data set including the selected word to a total number of text.
For example, if there are 100 text data in the text data set corresponding to the target application program, the selected word is word 1, and 20 text data in the 100 text data include word 1, then the relevance value between word 1 and the text data set is: 20/100 is 0.2.
A14, calculating the importance value of each word in the word set based on the word frequency and the relevance value;
the calculation formula of the importance value is as follows: v. ofi＝a*pi+b*qiWherein v isiIs the importance value, p, of the ith word in the set of wordsiWord frequency, q, of the ith word in the set of words in the published text dataiAnd a and b are the relevance values of the ith word in the word set and the text data set respectively, and are weights corresponding to the predetermined word frequency and the relevance values.
A15, according to the sequence of the importance values from high to low, screening a first number of words from the word set as first keywords corresponding to the published text data, and using the set of the first keywords as a text label set corresponding to the published text data.
In this embodiment, the first number may be 8, 8 words with the highest importance value are extracted from the word set as first keywords of the published text data, the importance value of each first keyword is used as its label information, and a set of the 8 first keywords carrying label information is used as a text label set corresponding to the published text data.
Updating the product label set corresponding to the product identifier based on the text label set includes:
b11, acquiring a set of text label sets of each text data corresponding to the product identification to obtain an initial label set corresponding to the product identification;
for example, if there are 10 text data about product 1 in the target application, the set of text label sets of the 10 text data is used as the initial label set of product 1.
B12, sorting the labels in the initial label set according to the order of the importance values from high to low, extracting a second number of labels which are sorted in the front as second keywords corresponding to the product identification, and taking the set of the second keywords as a product label set corresponding to the product identification.
In this embodiment, the second number may be 15, the 15 tags with the highest importance value in the initial tag set are used as the second keywords of the product 1, the importance values of the second keywords are used as the labeling information of the second keywords, and the set of the 15 second keywords carrying the labeling information is used as the product tag set of the product 1.
After the obtaining of the initial set of tags corresponding to the product identifier, the method further includes:
and adding the importance values of the same label in the initial label set to obtain the updated importance value of the same label.
For example, if the importance value of tag 1 in the text tag set of text data 1 corresponding to product 1 is 2 and the importance value of tag 1 in the text tag set of text data 3 corresponding to product 1 is 5, two tags 1 are included in the initial tag set corresponding to product 1, and the importance values are summed up to obtain the updated importance value of tag 1 of 5+2 — 7.
And S2, when it is monitored that the target application program generates registration information carrying a user identification, constructing a user portrait corresponding to the user identification based on the registration information, and storing the user portrait in a second database.
When a user logs in a target application program for the first time, an account needs to be registered, at the moment, a user portrait of each user of the target application program can be constructed according to registration information generated when the user registers the account, and each user portrait is stored in a second database.
The registration information includes the age, sex, occupation, place of residence, income, registration time, etc. of the user.
The building of the user portrait corresponding to the user identifier based on the registration information comprises:
c11, acquiring the mapping relation between the index value and the label of each index item in the registration information;
in this embodiment, the mapping relationship between the index value and the tag is described by taking the age of the index item and the registration time as examples.
The mapping relation between the index value of the age and the label is as follows:
under 18 years old: teenagers;
18-30 years old: young;
31-50 years old: middle-aged;
more than 50 years old: and (4) the elderly.
The mapping relation between the index value of the registration time and the label is as follows:
the registration time is less than half a year today: a new user;
the registration time is more than or equal to half a year: the old user.
C12, determining a target label corresponding to the index value of each index item in the registration information corresponding to the user identifier based on the mapping relation;
if the registered information of the user 1 includes an age of 25 years, a sex of a woman, a place of residence of shanghai, and a occupation of a foreign enterprise and employee, … …, the target tags corresponding to the index items of the user 1 are youth, a woman, a first-line city, white collar, and … …, respectively.
C13, using the set of target labels as the user representation corresponding to the user identification.
And summarizing the labels corresponding to the index items to obtain the user portrait corresponding to the user identification. For example, the user representation of USER-1 is obtained as a tag array { youth, woman, first-line city, white-collar, … … } according to step C12.
S3, when it is monitored that a certain specified user clicks on certain specified text data of the target application program, acquiring a target text label set corresponding to the specified text data from the first database, updating the interest label set of the specified user based on the target text label set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest label set.
The click behaviors can include searching, browsing, commenting and praise behaviors, and the click behaviors of the user in the text data of the target application program reflect the preference of the user to a certain degree.
In this embodiment, a corresponding text tag set is already stored in the first database for each text data in the target application program, so that the target text tag set corresponding to the clicked text data can be quickly obtained from the first database, the interest tag set of the user is updated in real time, and the product set to be recommended corresponding to the user is determined.
The updating of the interest tag set of the specified user based on the target text tag set comprises:
d11, obtaining an interest tag set corresponding to the specified user from a third database, and merging the interest tag set and the target text tag set to obtain a merged interest tag set;
in this embodiment, the third database stores an interest tag set of each user who logs in the target application program, where the interest tag set is determined according to a click behavior of the user and is updated when the user generates a new click behavior.
For example, when the user 1 clicks the text data 1 in the target application program for the first time, a preset number of tags in a text tag set corresponding to the text data 1 are used as an interest tag set of the user 1; and when the user 1 clicks the text data 2 for the second time, merging the text label set corresponding to the text data 2 with the interest label set of the user 1, and taking the labels with the preset number with the top importance value in the merged interest label set as the updated interest label set of the user 1, … ….
D12, sorting the labels in the merged interest label set according to the order of the importance values from high to low, extracting a third number of labels with the top sorting as third key words corresponding to the specified user, and taking the set of the third key words as an updated interest label set corresponding to the specified user.
In this embodiment, the third number may be 6, the 6 tags with the highest importance value in the merged interest tag set are used as third keywords of the specified user, the importance values of the third keywords are used as labeling information of the third keywords, and a set of the 6 third keywords carrying the labeling information is used as an updated interest tag set corresponding to the specified user.
The determining the to-be-recommended product set corresponding to the specified user based on the updated interest tag set comprises:
e11, matching the updated interest tag set with product tag sets corresponding to the products of the target application program, and taking a set of successfully matched tags as a matching tag set corresponding to each product;
for example, if 6 tags in the updated interest tag set of the user are specified, and the updated interest tag set has 3 tags that are the same as the product tag set of product 1 and 4 tags that are the same as the product tag set of product 2, then there are 3 tags in the matching tag set corresponding to product 1 and 4 tags in the matching tag set corresponding to product 2.
E12, calculating the total importance value corresponding to each label in the matching label set corresponding to each product, and calculating the matching value of the designated user and each product based on the total importance value;
for example, if 3 tags in the matching tag set corresponding to product 1 are tag 1, tag 2, and tag 3, the importance value of tag 1 in the interest tag set after update is 3, and the importance value of tag 1 in the product tag set of product 1 is 1, the total importance value of tag 1 in the matching tag set corresponding to product 1 is 3+1 — 4.
And summing the total importance value corresponding to each tag in the matching tag set corresponding to each product to obtain the matching value corresponding to each product, for example, if the total importance value of tag 1 in the matching tag set corresponding to product 1 is 4, the total importance value of tag 2 is 6, and the total importance value of tag 3 is 2, the matching value corresponding to product 1 is 4+6+2 — 12.
E13, sorting according to the sequence of the matching degree values from high to low, and taking the set of the fourth quantity of products sorted at the top as the set of products to be recommended corresponding to the specified user.
In this embodiment, the fourth number may be 10, and a set of 10 products with the highest matching degree value is used as a set of products to be recommended corresponding to the specified user.
S4, obtaining a target product label set corresponding to each product in the product set to be recommended from the first database, obtaining a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product ranking model to obtain a ranking result of the products in the product set to be recommended, and determining a target recommended product based on the ranking result.
In this embodiment, the product ranking model may be a trained logistic regression model or a trained neural network model, products in the set of products to be recommended may be accurately ranked by the product ranking model, and a target recommended product corresponding to the designated user may be determined according to a ranking result.
In this embodiment, a neural network model is taken as an example to illustrate a training process of the model: obtaining historical data of the target application program in a preset time period, wherein the historical data comprises order data of the user, for example, the historical data indicates that the user 1 purchases the product 1, the portrait of the user 1 and the product label set of the product 1 are taken as a positive sample (the labeling information of the positive sample is 1, that is, the real interest value of the user 1 to the product 1 is 1), the portrait of the user 1 and the product label set of other products are taken as a negative sample (the labeling information of the negative sample is 0, that is, the real interest value of the user 1 to other products is 0), thereby obtaining a positive sample set and a negative sample set, inputting the positive sample set and the negative sample set into the neural network model to obtain the predicted interest value of each sample, and determining the structural parameters of the model by minimizing the loss value between the predicted interest value and the real interest value to obtain a trained product sequencing model, wherein the loss value can be obtained by calculating through a cross entropy loss function.
The input of the product sorting model is a target user portrait corresponding to a specified user and a target product label set corresponding to each product in the product set to be recommended, the predicted interest value of the specified user for each product in the product set to be recommended is output, the products can be sorted according to the sequence from high to low of the predicted interest values, and the fifth quantity (for example, 3) of products with the highest sorting is used as the target recommended product corresponding to the specified user.
After determining the set of products to be recommended corresponding to the specified user based on the updated interest tag set, the method further includes:
and performing filtering processing on the products in the product set to be recommended to obtain an updated product set to be recommended.
In this embodiment, the filtering rules may be customized, for example, the products purchased by the specified user may be filtered, the products temporarily offline may be filtered, the products in the product blacklist may be filtered, the products not within the preset price range may be filtered, and the like.
According to the embodiment, the real-time product recommendation method provided by the invention comprises the steps of firstly, determining a text label set corresponding to published text data, and updating the corresponding product label set based on the text label set; then, constructing a user portrait based on the registration information; then, acquiring a target text tag set corresponding to the specified text data, updating the interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set; and finally, inputting the target product label set corresponding to each product in the product set to be recommended and the target user portrait corresponding to the appointed user into the product sorting model to obtain a sorting result of the products in the product set to be recommended and determine the target recommended product. The method and the system determine the text label set when the text data is published, and construct the user portrait when the user registers, so that the interest label set can be updated in real time when the user generates a clicking action, the product set to be recommended is determined based on the interest label set, and the products in the product set to be recommended are accurately sorted based on the user portrait, so that the target recommended product is determined, and the real-time performance and the accuracy of product recommendation are ensured. Therefore, the invention realizes accurate and real-time product recommendation for the user.
Fig. 2 is a schematic block diagram of a real-time product recommendation apparatus according to an embodiment of the present invention.
The real-time product recommendation device 100 of the present invention may be installed in an electronic device. Depending on the implemented functionality, the real-time product recommendation device 100 may include an update module 110, a build module 120, a determination module 130, and a recommendation module 140. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the updating module 110 is configured to, when it is monitored that a target application program issues text data carrying a product identifier, determine a text tag set corresponding to the issued text data, update a product tag set corresponding to the product identifier based on the text tag set, and store the text tag set and the product tag set in a first database.
The determining a text label set corresponding to the published text data includes:
a21, performing word segmentation processing on the issued text data to obtain a word set;
a22, calculating the word frequency of each word in the word set in the published text data;
a23, acquiring a text data set corresponding to the target application program, and calculating a relevance value of each word in the word set and the text data set;
a24, calculating the importance value of each word in the word set based on the word frequency and the relevance value;
a25, according to the sequence of the importance values from high to low, screening a first number of words from the word set as first keywords corresponding to the published text data, and using the set of the first keywords as a text label set corresponding to the published text data.
Updating the product label set corresponding to the product identifier based on the text label set includes:
b21, acquiring a set of text label sets of each text data corresponding to the product identification to obtain an initial label set corresponding to the product identification;
b22, sorting the labels in the initial label set according to the order of the importance values from high to low, extracting a second number of labels which are sorted in the front as second keywords corresponding to the product identification, and taking the set of the second keywords as a product label set corresponding to the product identification.
And the constructing module 120 is configured to, when it is monitored that the target application program generates registration information carrying a user identifier, construct a user portrait corresponding to the user identifier based on the registration information, and store the user portrait in a second database.
The building of the user portrait corresponding to the user identifier based on the registration information comprises:
c21, acquiring the mapping relation between the index value and the label of each index item in the registration information;
c22, determining a target label corresponding to the index value of each index item in the registration information corresponding to the user identifier based on the mapping relation;
c23, using the set of target labels as the user representation corresponding to the user identification.
The determining module 130 is configured to, when it is monitored that a certain specified user generates a click behavior on certain specified text data of the target application program, obtain a target text tag set corresponding to the specified text data from the first database, update an interest tag set of the specified user based on the target text tag set, and determine a to-be-recommended product set corresponding to the specified user based on the updated interest tag set.
The updating of the interest tag set of the specified user based on the target text tag set comprises:
d21, obtaining an interest tag set corresponding to the specified user from a third database, and merging the interest tag set and the target text tag set to obtain a merged interest tag set;
d22, sorting the labels in the merged interest label set according to the order of the importance values from high to low, extracting a third number of labels with the top sorting as third key words corresponding to the specified user, and taking the set of the third key words as an updated interest label set corresponding to the specified user.
The determining the to-be-recommended product set corresponding to the specified user based on the updated interest tag set comprises:
e21, matching the updated interest tag set with product tag sets corresponding to the products of the target application program, and taking a set of successfully matched tags as a matching tag set corresponding to each product;
e22, calculating the total importance value corresponding to each label in the matching label set corresponding to each product, and calculating the matching value of the designated user and each product based on the total importance value;
e23, sorting according to the sequence of the matching degree values from high to low, and taking the set of the fourth quantity of products sorted at the top as the set of products to be recommended corresponding to the specified user.
The recommending module 140 is configured to obtain a target product tag set corresponding to each product in the to-be-recommended product set from the first database, obtain a target user portrait corresponding to the designated user from the second database, input the target product tag set and the target user portrait into a product ranking model, obtain a ranking result of the products in the to-be-recommended product set, and determine a target recommended product based on the ranking result.
After determining the set of products to be recommended corresponding to the specified user based on the updated interest tag set, the recommending module 140 is further configured to:
and performing filtering processing on the products in the product set to be recommended to obtain an updated product set to be recommended.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a real-time product recommendation method according to an embodiment of the present invention.
The electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a command set or stored in advance. The electronic device 1 may be a computer, or may be a single network server, a server group composed of a plurality of network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing, where cloud computing is one of distributed computing and is a super virtual computer composed of a group of loosely coupled computers.
In the present embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which are communicatively connected to each other through a system bus, wherein the memory 11 stores a real-time product recommendation program 10, and the real-time product recommendation program 10 is executable by the processor 12. While FIG. 3 shows only the electronic device 1 with the components 11-13 and the real-time product recommendation program 10, those skilled in the art will appreciate that the configuration shown in FIG. 3 is not limiting of the electronic device 1 and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
The storage 11 includes a memory and at least one type of readable storage medium. The memory provides cache for the operation of the electronic equipment 1; the readable storage medium may be a non-volatile storage medium such as 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 readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the non-volatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk provided on the electronic device 1, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. In this embodiment, the readable storage medium of the memory 11 is generally used for storing an operating system and various application software installed in the electronic device 1, for example, codes of the real-time product recommendation program 10 in an embodiment of the present invention. Further, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 12 is generally configured to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 12 is configured to execute the program code stored in the memory 11 or process data, for example, execute the real-time product recommendation program 10.
The network interface 13 may comprise a wireless network interface or a wired network interface, and the network interface 13 is used for establishing a communication connection between the electronic device 1 and a client (not shown).
Optionally, the electronic device 1 may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface and 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 for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
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 real-time product recommendation program 10 stored by the memory 11 in the electronic device 1 is a combination of instructions that, when executed in the processor 12, may implement the steps of:
when it is monitored that a target application program releases text data carrying product identification, determining a text label set corresponding to the released text data, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
when it is monitored that a target application program generates registration information carrying a user identifier, constructing a user portrait corresponding to the user identifier based on the registration information, and storing the user portrait to a second database;
when it is monitored that a certain specified user clicks on certain specified text data of the target application program, acquiring a target text tag set corresponding to the specified text data from the first database, updating an interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
Specifically, the processor 12 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the real-time product recommendation program 10, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be non-volatile or non-volatile. The computer-readable storage medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The computer readable storage medium having stored thereon a real-time product recommendation program 10, the real-time product recommendation program 10 executable by one or more processors to perform the steps of:
when it is monitored that a target application program releases text data carrying product identification, determining a text label set corresponding to the released text data, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
when it is monitored that a target application program generates registration information carrying a user identifier, constructing a user portrait corresponding to the user identifier based on the registration information, and storing the user portrait to a second database;
when it is monitored that a certain specified user clicks on certain specified text data of the target application program, acquiring a target text tag set corresponding to the specified text data from the first database, updating an interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
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 method for real-time product recommendation, the method comprising:
when it is monitored that a target application program releases text data carrying product identification, determining a text label set corresponding to the released text data, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
when it is monitored that a target application program generates registration information carrying a user identifier, constructing a user portrait corresponding to the user identifier based on the registration information, and storing the user portrait to a second database;
when it is monitored that a certain specified user clicks on certain specified text data of the target application program, acquiring a target text tag set corresponding to the specified text data from the first database, updating an interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
2. The real-time product recommendation method of claim 1, wherein said determining a set of text labels corresponding to published text data comprises:
performing word segmentation processing on the issued text data to obtain a word set;
calculating the word frequency of each word in the word set in the published text data;
acquiring a text data set corresponding to the target application program, and calculating a relevance value of each word in the word set and the text data set;
calculating an importance value of each word in the set of words based on the word frequency and the relevance value;
and according to the sequence of the importance values from high to low, screening a first number of words from the word set as first keywords corresponding to the published text data, and taking the set of the first keywords as a text label set corresponding to the published text data.
3. The real-time product recommendation method of claim 1, wherein said updating the product tag set corresponding to the product identification based on the text tag set comprises:
acquiring a set of text label sets of each text data corresponding to the product identification to obtain an initial label set corresponding to the product identification;
and sorting the labels in the initial label set according to the order of the importance values from high to low, extracting a second number of labels which are sorted at the top as second keywords corresponding to the product identification, and taking the set of the second keywords as a product label set corresponding to the product identification.
4. The real-time product recommendation method of claim 1, wherein said building a user representation corresponding to said user identification based on said registration information comprises:
acquiring a mapping relation between index values and labels of all index items in the registration information;
determining a target label corresponding to the index value of each index item in the registration information corresponding to the user identifier based on the mapping relation;
and taking the set of target labels as a user portrait corresponding to the user identification.
5. The real-time product recommendation method of claim 2, wherein said updating the interest tag set of the specified user based on the target text tag set comprises:
obtaining an interest tag set corresponding to the specified user from a third database, and merging the interest tag set and the target text tag set to obtain a merged interest tag set;
and sorting the labels in the combined interest label set according to the order of the importance values from high to low, extracting a third number of labels which are sorted in the front as third key words corresponding to the specified user, and taking the set of the third key words as an updated interest label set corresponding to the specified user.
6. The real-time product recommendation method of claim 1, wherein the determining the set of products to be recommended corresponding to the specified user based on the updated interest tag set comprises:
matching the updated interest tag set with product tag sets corresponding to products of the target application program, and taking a set of successfully matched tags as a matched tag set corresponding to each product;
calculating the total importance value corresponding to each label in the matched label set corresponding to each product, and calculating the matching value of the designated user and each product based on the total importance value;
and sorting according to the sequence of the matching degree values from high to low, and taking the set of the fourth quantity of products which are sorted at the top as the set of the products to be recommended corresponding to the specified user.
7. The real-time product recommendation method of claim 1, wherein after determining the set of products to be recommended corresponding to the specified user based on the updated set of interest tags, the method further comprises:
and performing filtering processing on the products in the product set to be recommended to obtain an updated product set to be recommended.
8. A real-time product recommendation device, the device comprising:
the updating module is used for determining a text label set corresponding to the issued text data when it is monitored that a target application program issues the text data carrying the product identification, updating a product label set corresponding to the product identification based on the text label set, and storing the text label set and the product label set to a first database;
the construction module is used for constructing a user portrait corresponding to the user identification based on the registration information when the fact that the registration information carrying the user identification is generated by the target application program is monitored, and storing the user portrait to a second database;
the determining module is used for acquiring a target text tag set corresponding to the specified text data from the first database when it is monitored that a specified user clicks on the specified text data of the target application program, updating the interest tag set of the specified user based on the target text tag set, and determining a to-be-recommended product set corresponding to the specified user based on the updated interest tag set;
and the recommending module is used for acquiring a target product label set corresponding to each product in the product set to be recommended from the first database, acquiring a target user portrait corresponding to the specified user from the second database, inputting the target product label set and the target user portrait into a product sequencing model to obtain a sequencing result of the products in the product set to be recommended, and determining a target recommended product based on the sequencing result.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a real-time product recommendation program executable by the at least one processor to enable the at least one processor to perform the real-time product recommendation method of any one of claims 1-7.
10. A computer-readable storage medium having stored thereon a real-time product recommendation program executable by one or more processors to implement the real-time product recommendation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111009741.2A CN113706253A (en) | 2021-08-30 | 2021-08-30 | Real-time product recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111009741.2A CN113706253A (en) | 2021-08-30 | 2021-08-30 | Real-time product recommendation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113706253A true CN113706253A (en) | 2021-11-26 |
Family
ID=78657675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111009741.2A Pending CN113706253A (en) | 2021-08-30 | 2021-08-30 | Real-time product recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113706253A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549125A (en) * | 2022-02-18 | 2022-05-27 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device, electronic equipment and computer-readable storage medium |
| CN114723523A (en) * | 2022-04-06 | 2022-07-08 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability portrait |
| CN117372093A (en) * | 2023-09-20 | 2024-01-09 | 北京约来健康科技有限公司 | Content recommendation method, system, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046952A (en) * | 2019-01-30 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| CN111797210A (en) * | 2020-03-03 | 2020-10-20 | 中国平安人寿保险股份有限公司 | Information recommendation method, device and equipment based on user portrait and storage medium |
| CN112231555A (en) * | 2020-10-12 | 2021-01-15 | 中国平安人寿保险股份有限公司 | Recall method, apparatus, device and storage medium based on user portrait label |
| CN112818230A (en) * | 2021-01-29 | 2021-05-18 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN112818218A (en) * | 2021-01-21 | 2021-05-18 | 中国平安人寿保险股份有限公司 | Information recommendation method and device, terminal equipment and computer readable storage medium |
| CN112825089A (en) * | 2019-11-21 | 2021-05-21 | 腾讯科技（北京）有限公司 | Article recommendation method, article recommendation device, article recommendation equipment and storage medium |
-
2021
- 2021-08-30 CN CN202111009741.2A patent/CN113706253A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046952A (en) * | 2019-01-30 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| CN112825089A (en) * | 2019-11-21 | 2021-05-21 | 腾讯科技（北京）有限公司 | Article recommendation method, article recommendation device, article recommendation equipment and storage medium |
| CN111797210A (en) * | 2020-03-03 | 2020-10-20 | 中国平安人寿保险股份有限公司 | Information recommendation method, device and equipment based on user portrait and storage medium |
| CN112231555A (en) * | 2020-10-12 | 2021-01-15 | 中国平安人寿保险股份有限公司 | Recall method, apparatus, device and storage medium based on user portrait label |
| CN112818218A (en) * | 2021-01-21 | 2021-05-18 | 中国平安人寿保险股份有限公司 | Information recommendation method and device, terminal equipment and computer readable storage medium |
| CN112818230A (en) * | 2021-01-29 | 2021-05-18 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549125A (en) * | 2022-02-18 | 2022-05-27 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device, electronic equipment and computer-readable storage medium |
| CN114723523A (en) * | 2022-04-06 | 2022-07-08 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability portrait |
| CN114723523B (en) * | 2022-04-06 | 2023-05-30 | 平安科技（深圳）有限公司 | Product recommendation method, device, equipment and medium based on user capability image |
| CN117372093A (en) * | 2023-09-20 | 2024-01-09 | 北京约来健康科技有限公司 | Content recommendation method, system, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN112732915A (en) | Emotion classification method and device, electronic equipment and storage medium | |
| CN113706253A (en) | Real-time product recommendation method and device, electronic equipment and readable storage medium | |
| CN113706252B (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN112818218B (en) | Information recommendation method, device, terminal equipment and computer readable storage medium | |
| CN113435202A (en) | Product recommendation method and device based on user portrait, electronic equipment and medium | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN113435970B (en) | Product recommendation method and device based on biological information, electronic equipment and medium | |
| CN112597135A (en) | User classification method and device, electronic equipment and readable storage medium | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN113656690A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN112507230A (en) | Webpage recommendation method and device based on browser, electronic equipment and storage medium | |
| CN116362684A (en) | Library cluster-based book management method, library cluster-based book management device, library cluster-based book management equipment and storage medium | |
| CN115204971A (en) | Product recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN114706985A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN114281991A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113064984A (en) | Intention recognition method and device, electronic equipment and readable storage medium | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN113610580B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN115238179A (en) | Project pushing method and device, electronic equipment and computer readable storage medium | |
| CN113656586B (en) | Emotion classification method, emotion classification device, electronic equipment and readable storage medium | |
| CN112328752B (en) | Course recommendation method and device based on search content, computer equipment and medium | |
| CN114818685A (en) | Keyword extraction method and device, electronic equipment and storage medium | |
| CN114139530A (en) | Synonym extraction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |