CN115222478A - Product message pushing method, electronic equipment and readable storage medium - Google Patents
Product message pushing method, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN115222478A CN115222478A CN202210672410.5A CN202210672410A CN115222478A CN 115222478 A CN115222478 A CN 115222478A CN 202210672410 A CN202210672410 A CN 202210672410A CN 115222478 A CN115222478 A CN 115222478A
- Authority
- CN
- China
- Prior art keywords
- product
- information
- target
- preset
- bag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a product message pushing method, electronic equipment and a readable storage medium, which are applied to the technical field of big data, wherein the product message pushing method comprises the following steps: acquiring user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user; selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait characteristic information and the historical concern product characteristic information; pushing the target preferred product message to the target user. The product message pushing method and device solve the technical problem that product message pushing is low in product message selection accuracy.
Description
Technical Field
The present application relates to the field of big data technologies, and in particular, to a product message pushing method, an electronic device, and a readable storage medium.
Background
With the rapid development of science and technology, the pushing of product messages is more and more intelligent, at present, favorite products obtained by analyzing video types of videos watched by a target user are pushed to the target user, the video types watched by the target user are diverse, the favorite products of the target user cannot be accurately analyzed, the target user is only analyzed according to the video types, the obtained result is single and inaccurate, and therefore the product message selection accuracy of product message pushing is low.
Disclosure of Invention
The application mainly aims to provide a product message pushing method, an electronic device and a readable storage medium, and aims to solve the technical problem that product message selection accuracy of product message pushing in the prior art is low.
In order to achieve the above object, the present application provides a product message pushing method, which is applied to a product message pushing device, where the product message pushing method includes:
acquiring user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user;
selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information;
and pushing the target preference product message to the target user.
To achieve the above object, the present application further provides a product message pushing device, where the product message pushing device is applied to a product message pushing device, and the product message pushing device includes:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring user characteristic information corresponding to a target user, and the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user;
the selection module is used for selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait characteristic information and the historical concerned product characteristic information;
a push module for pushing the target preferred product message to the target user.
The present application further provides an electronic device, the electronic device including: a memory, a processor and a program of the product message push method stored on the memory and executable on the processor, which when executed by the processor, may implement the steps of the product message push method as described above.
The present application also provides a computer-readable storage medium, on which a program for implementing the product message push method is stored, and when executed by a processor, the program implements the steps of the product message push method as described above.
The present application also provides a computer program product comprising a computer program, which when executed by a processor implements the steps of the product message pushing method as described above.
Compared with a favorite product obtained by pushing a video type of a watched video to a target user, the product message pushing method, the electronic equipment and the readable storage medium have the advantages that user characteristic information corresponding to the target user is obtained, wherein the user characteristic information at least comprises user portrait characteristic information and historical attention product characteristic information corresponding to the target user; selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information; the target preference product information is pushed to the target user, the user portrait characteristic information and the historical attention product characteristic information of the target user are integrated, the target preference product information of the target user is matched, the influence of various factors on the preference of the target user is considered, therefore, the selection accuracy of the target preference product information is improved, the technical defects that when a preference product is obtained by analyzing the video type of the pushed and watched video of the target user, the preference product of the target user cannot be accurately analyzed due to the fact that the video type watched by the target user is diverse, the target user is analyzed only according to the video type, the obtained result is single and inaccurate are overcome, and the product information selection accuracy of product information pushing of the product information is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a first embodiment of a product message pushing method according to the present application;
fig. 2 is a schematic flowchart of a second embodiment of a product message pushing method according to the present application;
fig. 3 is a schematic device structure diagram of a hardware operating environment related to a product message pushing method in an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments of the present application are described in detail below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
Example one
In a first embodiment of the product message pushing method of the present application, referring to fig. 1, the product message pushing method includes:
step S10, obtaining user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user;
step S20, selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information;
and step S30, pushing the target preference product message to the target user.
In this embodiment, it should be noted that the present invention is applied to a display device, and the display device may be any device having a display function, such as a mobile phone, a computer, or a television. The preset product message library is the sum of preset product information provided by the message recommendation platform. The number of the target preference product can be one or more. The product pushing message can be product pushing information, product pushing advertisements and product pushing videos.
Optionally, before step S20, the method further includes: acquiring identification information of the target user, wherein the identification information at least comprises one of an equipment identifier of mobile communication terminal equipment of the target user, an equipment identity code of the mobile communication terminal equipment and a local area network address of the mobile communication terminal equipment, and selecting a target product message library corresponding to the identification information from each product message library as the preset product message library according to the identification information; and if the target product message library corresponding to the identification information does not exist in each product message library, constructing the product message library corresponding to the target user as the preset product message library according to the user portrait feature information of the target user and each product information of the message recommendation platform.
Exemplarily, steps S10 to S30 include: acquiring user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user; inquiring target preference product information corresponding to the user characteristic information in a preset product information library; pushing the target preferred product message to the target user in a display screen of the display device.
In step S10, the step of obtaining user characteristic information corresponding to a target user, where the user characteristic information at least includes user portrait characteristic information and historical concern product characteristic information corresponding to the target user includes:
step S11, generating user portrait feature information of the target user according to the age and/or the gender of the target user;
in this embodiment, it should be noted that the age of the target user may be the age of the target user, or may be the age value of the target user.
Exemplarily, step S11 includes: acquiring the age bracket of the target user or the age value of the target user to obtain age information; acquiring the gender of a target user to obtain gender information; and aggregating the gender information and the age information to obtain the user portrait feature information of the target user, and considering the influence of the age and the gender of the target user on the preference of the target user, thereby improving the product message selection accuracy of product message pushing.
As an example, step S11 includes: acquiring a target user age group or a target user age value set by the target user to obtain age information; acquiring gender set by the target user to obtain gender information; acquiring the occupation type set by the target user to obtain the occupation information of the target user; acquiring the character type set by the target user to obtain the character characteristics of the target user; and aggregating the occupation information, the character characteristics, the sex information and the age information to obtain user portrait characteristic information of the target user, comprehensively considering the influence of the age, the sex, the occupation and the character of the target user on the preference of the target user, and providing more decision bases for selecting target preference product information, thereby improving the product information selection accuracy of product information push.
As an example, step S11 includes: when a camera is arranged in the display device, acquiring a target user image carrying the target user information through the camera, or when the camera is not arranged in the display device, performing communication connection with the display device through an external camera, wherein the communication connection can be wired connection such as an interface or wireless connection such as Bluetooth, and acquiring the target user image carrying the target user information through the external camera; according to the target user image, the age information and the gender information of the target user and the environment information of the target user are determined, the favorite object of the target user is determined through the environment information, the age information, the gender information and the favorite object are integrated to obtain the user portrait characteristic information, the influence of the age, the gender and the favorite object of the target user on the preference of the target user is comprehensively considered, more decision-making bases are provided for the selection of the target favorite product information, and the product information selection accuracy of product information pushing is improved.
Step S12, determining the playing frequency of each product characteristic information in the historical watching video data of the target user, and selecting a target playing frequency which is greater than or equal to a preset playing frequency threshold value from each playing frequency;
and S13, taking the product characteristic information corresponding to the target playing frequency as the historical concerned product characteristic information.
In this embodiment, it should be noted that the preset playing frequency threshold is a preset critical value for determining the playing frequency of the product feature information with a higher probability of being paid attention by the target user, the preset playing frequency threshold may be 5 times a day, or may also be any frequency such as 10 times a day, and the preset playing frequency threshold may be automatically generated by the product message pushing system, or may be set by the target user. The historical attention product characteristic information can be one or more.
Exemplarily, steps S12 to S13 include: extracting a product information frame carrying product characteristic information from the watching video data, determining the number of the product characteristic information contained in the product information frame to obtain the playing frequency of each product characteristic information, judging whether a target playing frequency is greater than or equal to a preset playing frequency threshold value or not in the playing frequency, and if the target playing frequency is greater than or equal to the preset playing frequency threshold value in the playing frequency, taking the product characteristic information corresponding to the target playing frequency as the historical attention product characteristic information; and if the target playing frequency does not exist in the playing frequencies and is greater than or equal to the preset playing frequency threshold value, canceling the pushing of the target preference product message to the target user.
In step S20, the step of selecting a target preferred product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical attention product feature information includes:
step S21, matching the characteristic information of the historical concerned product with each product message in the preset product message library to obtain a matching result;
and S22, selecting a target preference product message corresponding to the target user from the matching result according to the user portrait feature information.
Exemplarily, the steps S21 to S22 include: matching the historical concerned product characteristic information with each product message in the preset product message library to obtain a matching result; according to the user portrait feature information, selecting a target product price corresponding to the target user from the product prices in each product message, and taking the product message corresponding to the target product price as the target preference product message, wherein the target product price may be one or more.
In step S21, the matching result includes a fuzzy matching result and an accurate matching result, and the step of matching the historical attention product feature information with each product message in the preset product message library to obtain the matching result includes:
step A10, fuzzy matching is carried out on the historical concerned product characteristic information and each product message in the preset product message library to obtain a fuzzy matching result;
step A20, when the matching state of the fuzzy matching result is matching success, taking the fuzzy matching result as the matching result;
and step A30, when the matching state of the fuzzy matching result is matching failure, accurately matching the historical concerned product characteristic information with each product message in the preset product message library to obtain an accurate matching result, and taking the accurate matching result as the matching result.
Exemplarily, the steps a10 to a30 include: performing Gaussian blur on product message characteristic information corresponding to each product message in the preset product message library to obtain fuzzy characteristic information, and matching the fuzzy characteristic information with the historical concerned product characteristic information to obtain a fuzzy matching result, wherein the fuzzy matching result comprises fuzzy matching product messages and matching probabilities corresponding to each fuzzy matching product message; when the matching probability is larger than or equal to a preset probability threshold, judging that the matching state of the fuzzy matching result is successful in matching, and taking the fuzzy matching result as the matching result; and when the matching probability is smaller than a preset probability threshold, judging that the matching state of the fuzzy matching result is matching failure, accurately matching the historical concerned product characteristic information with each product message in the preset product message library to obtain an accurate matching result, and taking the accurate matching result as the matching result, wherein the preset probability threshold is a preset critical value of the matching probability corresponding to the fuzzy matching product message for judging that the fuzzy matching is successful, and the preset probability threshold can be 0.5, 0.6 or 0.7.
The product message characteristic information is subjected to secondary matching with each product message in a preset product message library, the product message selection efficiency of product message pushing is improved through primary fuzzy matching, the product message selection accuracy of product message pushing is improved through secondary accurate matching, secondary selection of a product message pushing message determination flow is realized, and the product message selection efficiency and the product message selection accuracy of product message pushing are considered.
In step a30, the historical product characteristic information of interest includes bag product information, and the step of accurately matching the historical product characteristic information of interest with each product message in the preset product message library to obtain the accurate matching result includes:
step A31, performing feature extraction on the bag product information according to a preset feature extraction model to obtain target bag information features;
step A32, classifying a target bag corresponding to the bag product information according to a preset bag product classification model and the target bag information characteristics to obtain a bag classification label;
step A33, inquiring the bag classification label in the preset product message library to obtain the accurate matching result.
In this embodiment, it should be noted that the preset feature extraction model is configured to extract features that can represent bag classification information in the bag product information, and the preset bag product classification model is configured to classify bags according to the bag information features.
Exemplarily, the steps a31 to a33 include: according to a preset feature extraction model, performing feature extraction on the bag product information to obtain target bag information features, wherein the bag product information at least comprises one of color information, pattern information, accessory information and shape information; mapping the target bag information characteristics into bag classification labels through a preset bag product classification model; and querying the bag classification labels in the preset product message library to obtain the accurate matching result, wherein the number of the bag classification labels can be one or at least two.
In step a31, the preset feature extraction model includes a shape feature extraction model, a color feature extraction model, a pattern feature extraction model, and an accessory feature extraction model, and the step of extracting the features of the bag product information according to the preset feature extraction model to obtain the target bag information features includes:
step C10, extracting the shape characteristics of the bag product information through the shape characteristic extraction model to obtain bag shape characteristics;
step C20, extracting color features of the bag product information through the color feature extraction model to obtain bag color features;
step C30, extracting the pattern characteristics of the bag product information through the pattern characteristic extraction model to obtain bag pattern characteristics;
step C40, carrying out accessory feature extraction on the bag product information through the accessory feature extraction model to obtain bag accessory features;
and step C50, constructing the information characteristic of the target bag according to the shape characteristic of the bag, the color characteristic of the bag, the pattern characteristic of the bag and the accessory characteristic of the bag.
Exemplarily, the steps C10 to C50 include: mapping the bag product information to a preset characteristic dimension through the shape characteristic extraction model to obtain bag shape characteristics; mapping the bag product information to the preset characteristic dimension through the color characteristic extraction model to obtain bag color characteristics; mapping the bag product information to the preset characteristic dimension through the pattern characteristic extraction model to obtain bag pattern characteristics; mapping the bag product information to the preset characteristic dimension through the accessory characteristic extraction model to obtain bag accessory characteristics; and splicing the bag shape characteristic, the bag color characteristic, the bag pattern characteristic and the bag accessory characteristic to obtain the target bag information characteristic.
The bags are classified by integrating the information such as colors, shapes, patterns, accessories and the like of the bags to obtain classification results, so that bag information corresponding to the classification results is accurately pushed, and the bag information selection accuracy of bag information pushing is improved.
Optionally, the historical product feature information of interest includes clothing product information, and the step of accurately matching the historical product feature information of interest with each product message in the preset product message library to obtain an accurate matching result further includes:
according to a preset feature extraction model, feature extraction is carried out on the clothing product information to obtain target clothing information features; classifying the target clothes corresponding to the clothes product information according to a preset clothes product classification model and the target clothes information characteristics to obtain a clothes classification label; and inquiring the clothing classification label in the preset product message library to obtain the accurate matching result.
Optionally, the preset feature extraction model includes a style feature extraction model, a color feature extraction model, a pattern feature extraction model, a material feature extraction model, and an accessory feature extraction model, and the step of extracting the features of the clothing product information according to the preset feature extraction model to obtain the target clothing information features includes:
style feature extraction is carried out on the clothing product information through the style feature extraction model, and clothing style features are obtained; extracting color features of the clothing product information through the color feature extraction model to obtain clothing color features; extracting the pattern characteristics of the clothing product information through the pattern characteristic extraction model to obtain clothing pattern characteristics; carrying out accessory feature extraction on the clothing product information through the accessory feature extraction model to obtain clothing accessory features; performing material characteristic extraction on the clothing product information through the material characteristic extraction model to obtain clothing material characteristics; and constructing the target clothing information characteristic according to the clothing style characteristic, the clothing color characteristic, the clothing pattern characteristic, the clothing material characteristic and the clothing accessory characteristic.
The clothes are classified by integrating the information of the color, style, pattern, material, accessories and the like of the clothes to obtain a classification result, so that the clothes information corresponding to the classification result is accurately pushed, and the clothes information selection accuracy of the pushed clothes information is improved.
Compared with a favorite product obtained by pushing a video type of a watched video to a target user, the product message pushing method provided by the embodiment of the application obtains user characteristic information corresponding to the target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user; selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information; the target preference product information is pushed to the target user, the user portrait characteristic information and the historical attention product characteristic information of the target user are integrated, the target preference product information of the target user is matched, the influence of various factors on the preference of the target user is considered, therefore, the selection accuracy of the target preference product information is improved, the technical defects that when a preference product is obtained by analyzing the video type of the pushed and watched video of the target user, the preference product of the target user cannot be accurately analyzed due to the fact that the video type watched by the target user is diverse, the target user is analyzed only according to the video type, the obtained result is single and inaccurate are overcome, and the product information selection accuracy of product information pushing of the product information is improved.
Example two
Further, referring to fig. 2, based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents to those of the first embodiment of the present application may be referred to the above description, and are not repeated herein. On this basis, in step S20, the step of selecting the target preferred product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical attention product feature information further includes:
step B10, extracting the viewing characteristics of the target user in the viewing characteristic information of the target user;
step B20, predicting preference probability of the target user to the feature information of each historical concern product according to the viewing features of the target user and a preset preference product prediction model to obtain a preference product prediction result;
and B30, selecting the target preference product message corresponding to the preference product prediction result from the preset product message library.
In this embodiment, it should be noted that the preset preferred product prediction model is a preset model for predicting preference probabilities of the target user on the feature information of each historical attention product, and the preset preferred product prediction model may be a convolutional neural network or a cyclic neural network.
Exemplarily, the steps B10 to B30 include: constructing a target user viewing characteristic according to the user portrait characteristic information and the historical concerned product characteristic information; inputting the viewing characteristics of the target user into the preset preference product prediction model, and mapping the viewing characteristics of the target user into preference probabilities of the target user on the characteristic information of each historical concerned product through the preset preference product prediction model to obtain preference product prediction results; acquiring the push quantity of preset messages, and selecting target preference product messages corresponding to the preference product prediction results of the push quantity of the preset messages from the preset product message library; or selecting a target preference probability which is greater than or equal to a preset preference probability threshold from the preference probabilities according to the preference product prediction result, and determining a product message corresponding to the target preference probability as the target preference product message.
Wherein, in step S30, the step of pushing the target preferred product message to the target user comprises:
step S31, acquiring the video playing state of the target user;
step S32, when the video playing state is a full-screen playing state, pushing the target preference product message to the target user in a preset first area of a display screen, wherein the area of the first area of the preset first area is smaller than the area of the screen of the display screen;
step S33, when the playing video state is a pause playing state or a stop playing state, pushing the target preference product message to the target user in a preset second region of the display screen, wherein the area of the second region of the preset second region is larger than the area of the first region and smaller than or equal to the area of the screen.
In this embodiment, it should be noted that the preset first area is an area that is preset and pushes the target preferred product message when the video playing state of the display device is the full-screen playing state. The preset second area is an area which is preset and used for pushing the target preference product message when the video playing state of the display equipment is a playing pause state or a playing stop state.
By switching the area of the display area of the target preference product message in real time, the video watching effect and the advertisement pushing effect of a target user can be considered under each playing state.
Optionally, when the video playing state is a full-screen playing state, determining a second playing volume pushed by the target preference product message according to a first playing volume corresponding to the playing video of the target user, where the first playing volume is greater than the second playing volume; when the playing video state is a pause playing state or a stop playing state, according to the first playing volume, the third playing volume of the target preference product message pushing is determined, the third playing volume is larger than the second playing volume, the third playing volume is larger than the first playing volume, the pushing volume of the target preference product message is determined in real time through the playing video state and the playing video volume, and therefore the video watching effect and the advertisement pushing effect of a target user can be considered under each playing state.
Compared with a favorite product obtained by analyzing the video type of a video pushed to a target user, the product message pushing method provided by the embodiment of the application obtains user characteristic information corresponding to the target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical attention product characteristic information corresponding to the target user; selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information; the target preference product information is pushed to the target user, the user portrait characteristic information and the historical attention product characteristic information of the target user are integrated, the target preference product information of the target user is matched, the influence of various factors on the preference of the target user is considered, therefore, the selection accuracy of the target preference product information is improved, the technical defects that when a preference product is obtained by analyzing the video type of the pushed and watched video of the target user, the preference product of the target user cannot be accurately analyzed due to the fact that the video type watched by the target user is diverse, the target user is analyzed only according to the video type, the obtained result is single and inaccurate are overcome, and the product information selection accuracy of product information pushing of the product information is improved.
EXAMPLE III
The embodiment of the present application further provides a product message pushing device, where the product message pushing device is applied to a product message pushing device, and the product message pushing device includes:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring user characteristic information corresponding to a target user, and the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user;
the selection module is used for selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait characteristic information and the historical concerned product characteristic information;
and the pushing module is used for pushing the target preference product message to the target user.
Optionally, the obtaining module is further configured to:
generating user portrait feature information of the target user according to the age information and/or the gender information of the target user;
determining the playing frequency of each product characteristic information in the historical watching video data of the target user, and selecting a target playing frequency which is greater than or equal to a preset playing frequency threshold value from the playing frequencies;
and taking the product characteristic information corresponding to the target playing frequency as the historical concerned product characteristic information.
Optionally, the selecting module is further configured to:
matching the historical concerned product characteristic information with each product message in the preset product message library to obtain a matching result;
and selecting a target preference product message corresponding to the target user from the matching result according to the user portrait characteristic information.
Optionally, the selecting module is further configured to:
carrying out fuzzy matching on the historical concerned product characteristic information and each product message in the preset product message library to obtain a fuzzy matching result;
when the matching state of the fuzzy matching result is successful matching, taking the fuzzy matching result as the matching result;
and when the matching state of the fuzzy matching result is matching failure, accurately matching the historical concerned product characteristic information with each product message in the preset product message library to obtain an accurate matching result, and taking the accurate matching result as the matching result.
Optionally, the historical product-related characteristic information includes bag product information, and the selection module is further configured to:
according to a preset feature extraction model, feature extraction is carried out on the bag product information to obtain target bag information features;
classifying the target bags corresponding to the bag product information according to a preset bag product classification model and the target bag information characteristics to obtain bag classification labels;
and inquiring the bag classification label in the preset product message library to obtain the accurate matching result.
Optionally, the preset feature extraction model includes a shape feature extraction model, a color feature extraction model, a pattern feature extraction model, and an accessory feature extraction model, and the selection module is further configured to:
carrying out shape feature extraction on the bag product information through the shape feature extraction model to obtain bag shape features;
carrying out color feature extraction on the bag product information through the color feature extraction model to obtain bag color features;
extracting the pattern characteristics of the bag product information through the pattern characteristic extraction model to obtain bag pattern characteristics;
carrying out accessory feature extraction on the bag product information through the accessory feature extraction model to obtain bag accessory features;
and constructing the target bag information characteristic according to the bag shape characteristic, the bag color characteristic, the bag pattern characteristic and the bag accessory characteristic.
Optionally, the selecting module is further configured to:
extracting target user viewing characteristics in the target user viewing characteristic information;
predicting preference probability of the target user to the feature information of each historical concerned product according to the viewing feature of the target user and a preset preference product prediction model to obtain a preference product prediction result;
and selecting the target preference product message corresponding to the preference product prediction result from the preset product message library.
Optionally, the pushing module is further configured to:
acquiring the video playing state of the target user;
when the video playing state is a full-screen playing state, pushing the target preference product message to the target user in a preset first area of a display screen, wherein the area of the first area of the preset first area is smaller than the area of the screen of the display screen;
and when the video playing state is a pause playing state or a stop playing state, pushing the target preference product message to the target user in a preset second region of the display screen, wherein the area of the second region of the preset second region is larger than the area of the first region and smaller than or equal to the area of the screen.
By adopting the product message pushing device in the embodiment, the technical problem of low product message selection accuracy in product message pushing is solved. Compared with the prior art, the beneficial effects of the product message pushing device provided by the embodiment of the present application are the same as the beneficial effects of the product message pushing method provided by the above embodiment, and other technical features of the product message pushing device are the same as those disclosed by the above embodiment method, which are not described herein again.
Example four
An embodiment of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the product message pushing method in the above embodiments.
Referring now to FIG. 3, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing apparatus (e.g., a central processing unit, a graphic processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage apparatus into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
By adopting the product message pushing method in the embodiment, the electronic device provided by the application solves the technical problem of low product message selection accuracy in product message pushing. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the present application are the same as the beneficial effects of the product message pushing method provided by the above embodiment, and other technical features in the electronic device are the same as the features disclosed in the above embodiment method, which are not repeated herein.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having stored thereon computer-readable program instructions for executing the method of the product message push method in the above-described embodiments.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be separate and not incorporated into the electronic device.
The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user; selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait feature information and the historical concern product feature information; and pushing the target preference product message to the target user.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the target user's computer, partly on the target user's computer, as a stand-alone software package, partly on the target user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the target user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium stores computer-readable program instructions for executing the product message pushing method, and solves the technical problem that the product message pushing accuracy is low. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the present application are the same as those of the product message pushing method provided by the foregoing implementation, and are not described herein again.
Example six
The present application also provides a computer program product comprising a computer program, which when executed by a processor implements the steps of the product message pushing method as described above.
The computer program product solves the technical problem that the product message pushed by the product message is low in selection accuracy. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the product message pushing method provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. A product message pushing method is characterized by comprising the following steps:
acquiring user characteristic information corresponding to a target user, wherein the user characteristic information at least comprises user portrait characteristic information and historical concern product characteristic information corresponding to the target user;
selecting a target preference product message corresponding to the target user from a preset product message library according to the user portrait characteristic information and the historical concern product characteristic information;
pushing the target preferred product message to the target user.
2. The product message pushing method according to claim 1, wherein the step of obtaining user characteristic information corresponding to a target user, wherein the user characteristic information at least includes user portrait characteristic information and historical product attention characteristic information corresponding to the target user includes:
generating user portrait characteristic information of the target user according to the age information and/or the sex information of the target user;
determining the playing frequency of each product characteristic information in the historical watching video data of the target user, and selecting a target playing frequency which is greater than or equal to a preset playing frequency threshold value from the playing frequencies;
and taking the product characteristic information corresponding to the target playing frequency as the historical concerned product characteristic information.
3. The product message pushing method according to claim 1, wherein the step of selecting the target preferred product message corresponding to the target user from a preset product message library according to the user image feature information and the historical product-of-interest feature information comprises:
matching the historical concerned product characteristic information with each product message in the preset product message library to obtain a matching result;
and selecting a target preference product message corresponding to the target user from the matching result according to the user portrait feature information.
4. The product message pushing method according to claim 3, wherein the step of matching the historical attention product feature information with each product message in the preset product message library to obtain a matching result comprises:
carrying out fuzzy matching on the historical concerned product characteristic information and each product message in the preset product message library to obtain a fuzzy matching result;
when the matching state of the fuzzy matching result is matching success, taking the fuzzy matching result as the matching result;
and when the matching state of the fuzzy matching result is matching failure, accurately matching the historical concerned product characteristic information with each product message in the preset product message library to obtain an accurate matching result, and taking the accurate matching result as the matching result.
5. The product message pushing method according to claim 4, wherein the historical product feature information of interest includes bag product information, and the step of accurately matching the historical product feature information of interest with each product message in the preset product message library to obtain an accurate matching result includes:
according to a preset feature extraction model, feature extraction is carried out on the bag product information to obtain target bag information features;
classifying the target bags corresponding to the bag product information according to a preset bag product classification model and the target bag information characteristics to obtain bag classification labels;
and inquiring the bag classification label in the preset product message library to obtain the accurate matching result.
6. The product message pushing method according to claim 5, wherein the preset feature extraction model comprises a shape feature extraction model, a color feature extraction model, a pattern feature extraction model and an accessory feature extraction model, and the step of extracting the features of the bag product information according to the preset feature extraction model to obtain the target bag information features comprises:
carrying out shape feature extraction on the bag product information through the shape feature extraction model to obtain bag shape features;
carrying out color feature extraction on the bag product information through the color feature extraction model to obtain bag color features;
carrying out pattern feature extraction on the bag product information through the pattern feature extraction model to obtain bag pattern features;
carrying out accessory feature extraction on the bag product information through the accessory feature extraction model to obtain bag accessory features;
and constructing the target bag information characteristic according to the bag shape characteristic, the bag color characteristic, the bag pattern characteristic and the bag accessory characteristic.
7. The method for pushing product messages according to claim 1, wherein the step of selecting the target preferred product message corresponding to the target user from a preset product message library according to the user image feature information and the historical product-of-interest feature information further comprises:
extracting the viewing characteristics of the target user in the viewing characteristic information of the target user;
predicting preference probability of the target user to the feature information of each historical concerned product according to the viewing feature of the target user and a preset preference product prediction model to obtain a preference product prediction result;
and selecting the target preference product message corresponding to the preference product prediction result from the preset product message library.
8. The product message pushing method of claim 1, wherein the step of pushing the targeted preferred product message to the targeted user comprises:
acquiring the video playing state of the target user;
when the video playing state is a full-screen playing state, pushing the target preference product message to the target user in a preset first area of a display screen, wherein the area of the first area of the preset first area is smaller than the area of the screen of the display screen;
and when the video playing state is a pause playing state or a stop playing state, pushing the target preference product message to the target user in a preset second region of the display screen, wherein the area of the second region of the preset second region is larger than that of the first region and smaller than or equal to that of the screen.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the product message push method of any of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for implementing the product message push method, and the program is executed by a processor to implement the steps of the product message push method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210672410.5A CN115222478A (en) | 2022-06-15 | 2022-06-15 | Product message pushing method, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210672410.5A CN115222478A (en) | 2022-06-15 | 2022-06-15 | Product message pushing method, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115222478A true CN115222478A (en) | 2022-10-21 |
Family
ID=83607609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210672410.5A Pending CN115222478A (en) | 2022-06-15 | 2022-06-15 | Product message pushing method, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115222478A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743681A (en) * | 2023-12-05 | 2024-03-22 | 工信人本(北京)管理咨询有限公司 | Method and system for pushing data based on feature matching |
-
2022
- 2022-06-15 CN CN202210672410.5A patent/CN115222478A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743681A (en) * | 2023-12-05 | 2024-03-22 | 工信人本(北京)管理咨询有限公司 | Method and system for pushing data based on feature matching |
| CN117743681B (en) * | 2023-12-05 | 2024-05-14 | 工信人本(北京)管理咨询有限公司 | Method and system for pushing data based on feature matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109976620B (en) | Method, device, equipment and storage medium for determining list item display attribute information | |
| CN111444356B (en) | Recommendation method and device based on search | |
| CN109684589B (en) | Client comment data processing method and device and computer storage medium | |
| CN111190520A (en) | Menu item selection method and device, readable medium and electronic equipment | |
| CN111309240B (en) | Content display method and device and electronic equipment | |
| CN111738316B (en) | Zero sample learning image classification method and device and electronic equipment | |
| CN112395022B (en) | Information display method, information display device, electronic equipment and computer readable storage medium | |
| CN111726675A (en) | Object information display method and device, electronic equipment and computer storage medium | |
| CN109902726B (en) | Resume information processing method and device | |
| CN115222478A (en) | Product message pushing method, electronic equipment and readable storage medium | |
| CN114021016A (en) | Data recommendation method, device, equipment and storage medium | |
| CN109542743B (en) | Log checking method and device, electronic equipment and computer readable storage medium | |
| CN111832354A (en) | Target object age identification method and device and electronic equipment | |
| CN116092092A (en) | Matching method, device, medium and electronic equipment | |
| CN115086700A (en) | Push processing method, device, equipment and medium | |
| CN113836415A (en) | Information recommendation method, device, medium and equipment | |
| CN114416945A (en) | Word cloud picture display method, device, equipment and medium | |
| CN113592607A (en) | Product recommendation method and device, storage medium and electronic equipment | |
| CN113177176A (en) | Feature construction method, content display method and related device | |
| CN111738311A (en) | Multitask-oriented feature extraction method and device and electronic equipment | |
| CN112214665A (en) | Content display method and device, electronic equipment and computer readable storage medium | |
| CN115412389B (en) | Message recommendation method and device, electronic equipment and readable storage medium | |
| CN111310031B (en) | House source information display method, device, terminal and storage medium | |
| CN114816609B (en) | Method and device for displaying window, electronic equipment and computer readable storage medium | |
| CN112199187B (en) | Content display method, device, electronic equipment and computer readable 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 |