CN113409123A - Information recommendation method, device, equipment and storage medium - Google Patents
Information recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113409123A CN113409123A CN202110743949.0A CN202110743949A CN113409123A CN 113409123 A CN113409123 A CN 113409123A CN 202110743949 A CN202110743949 A CN 202110743949A CN 113409123 A CN113409123 A CN 113409123A
- Authority
- CN
- China
- Prior art keywords
- recommended
- determining
- recommendation
- user
- weight
- 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 77
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 11
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 9
- 230000000875 corresponding effect Effects 0.000 description 65
- 230000008569 process Effects 0.000 description 18
- 238000012545 processing Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an information recommendation method, which comprises the following steps: determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended; determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic; and determining a recommended object from the at least one object to be recommended based on the recommendation value of each object to be recommended. In addition, the application also discloses an information recommendation device, equipment and a storage medium.
Description
Technical Field
The present application relates to the field of information recommendation, and relates to, but is not limited to, an information recommendation method, apparatus, device, and storage medium.
Background
In the related art, a terminal device (e.g., a mobile phone, a tablet computer, etc.) mainly depends on an interactive behavior (e.g., clicking, purchasing) of a user on an Application (APP) to provide personalized recommendations for the user.
However, in the process of providing personalized recommendation to the user by means of interaction behaviors such as clicking and purchasing on the APP, feedback of the user on the commodity in the process from when the user browses the commodity to before the user finally generates the interaction behavior with the commodity is lost, so that the accuracy of a personalized recommendation result is not high.
Disclosure of Invention
The embodiment of the application provides an information recommendation method, an information recommendation device, information recommendation equipment and a storage medium for solving at least one problem in the related art, and the accuracy of a personalized recommendation result can be improved.
The technical scheme of the application is realized as follows:
in a first aspect, an embodiment of the present application provides an information recommendation method, where the method includes:
determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended;
determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic;
and determining a recommended object from the at least one object to be recommended based on the recommendation value of each object to be recommended.
In a second aspect, an embodiment of the present application provides an information recommendation apparatus, where the apparatus includes:
the first determining unit is used for determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended;
the second determining unit is used for determining the recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic;
and the third determining unit is used for determining a recommended object from the at least one object to be recommended based on the recommended value of each object to be recommended.
In a third aspect, an embodiment of the present application provides an electronic device, a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the information recommendation method when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, where the computer program is executed by a processor to implement the information recommendation method.
The embodiment of the application provides an information recommendation method, device, equipment and storage medium, and the recommendation parameter of each object to be recommended in at least one object to be recommended is determined; the recommended parameters include: the user browses the biological characteristics of the object to be recommended; determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic; and then determining a recommended object from the at least one object to be recommended based on the recommended value of each object to be recommended. In this way, in the process of determining the recommended object, the recommended object is determined from at least one object to be recommended based on the recommendation value of each object to be recommended, and since the recommendation value is related to the first weight corresponding to the biological characteristic and the first weight represents the interest degree of the object browsed by the user under the condition of the biological characteristic, in the process of browsing the object to be recommended by the user, the recommended object can be provided to the user based on the biological characteristic of the user, so that the accuracy of the personalized recommendation result can be improved.
Drawings
Fig. 1 is an alternative schematic diagram of an information recommendation system provided in an embodiment of the present application;
fig. 2 is an optional schematic flow chart of an information recommendation method provided in an embodiment of the present application;
fig. 3 is an optional flowchart schematic diagram of an information recommendation method provided in an embodiment of the present application;
fig. 4 is an optional flowchart schematic diagram of an information recommendation method provided in an embodiment of the present application;
fig. 5 is an optional structural schematic diagram of an information recommendation device provided in an embodiment of the present application;
fig. 6 is an optional structural schematic diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will describe the specific technical solutions of the present application in further detail with reference to the accompanying drawings in the embodiments of the present application. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The information recommendation method according to the embodiment of the present application may be applied to the information recommendation system 100 shown in fig. 1, where as shown in fig. 1, the information recommendation system 100 includes: a server 10 and a client 20. Wherein the server 10 and the client 20 communicate with each other via a network 30.
The information recommendation method provided by the embodiment of the application is applied to recommendation equipment, and the recommendation equipment can be a server 10 or a client 20.
The recommendation equipment determines a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended; determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic; and determining a recommended object from the at least one object to be recommended based on the recommendation value of each object to be recommended.
In the case where the recommendation device is the server 10, the server 10 sends the recommendation object to the client 20 through the network 30, and the client 20 presents the recommendation object to the user.
In the case where the recommendation device is the client 20, the client 20 directly presents the recommendation object to the user.
In practical application, the recommendation system further comprises wearable equipment, and the wearable equipment can detect the biological characteristics of the user and send the detected biological characteristics to the recommendation equipment.
The invention is further described in detail below with reference to the figures and the specific embodiments.
Fig. 2 is a schematic flow chart of an implementation process of an information recommendation method provided in an embodiment of the present application, where the method is applied to a recommendation device, and as shown in fig. 2, the method may include the following steps:
s201, determining a recommendation parameter of each object to be recommended in at least one object to be recommended.
Wherein the recommendation parameters include: and the user browses the biological characteristics under the condition of the object to be recommended.
The biometric features may include: one or more of pulse, heartbeat, brain wave, facial expression, etc. are detected by the wearable device, wherein the wearable device may include: one or more of a mobile bracelet, brain wave tracking instrument, and the like.
The object to be recommended may include: goods, advertisements, news, etc.
In an example, when the object to be recommended is a commodity and the user browses the commodity, that is, the object to be recommended, the recommendation device may determine, through the wearable device, a biometric feature generated when the user browses each object to be recommended.
In the embodiment of the application, the wearable device detects the biological characteristics of the user and sends the detected biological characteristics to the recommendation device, so that the recommendation device obtains the biological characteristics of the user when the user browses an object to be recommended.
Use wearing equipment as the removal bracelet for example, when the user wears the removal bracelet and browses each in the APP and treat recommendation object, remove the bracelet and monitor biological characteristics such as pulse, heartbeat at user's browsing process, send the biological characteristics who monitors to recommendation equipment again, the biological characteristics that recommendation equipment received the removal bracelet and sent to can make recommendation equipment confirm that the user produces pulse, heartbeat biological characteristics when browsing each and treat recommendation object.
In the embodiment of the application, the number of the objects to be recommended can be multiple, and the recommendation device can acquire the biological characteristics of each object to be recommended.
In an example, 3 objects to be recommended are displayed in the APP, where the 3 objects to be recommended include: the method comprises the steps that an object A to be recommended, an object B to be recommended and an object C to be recommended are obtained, biological characteristics are pulse, when a user browses the object A to be recommended, the pulse generated when the user browses the object A to be recommended is determined to be 60 times/minute by a recommending device, when the user browses the object B to be recommended, the pulse generated when the user browses the object B to be recommended is determined to be 70 times/minute by the recommending device, and when the user browses the object C to be recommended, the pulse generated when the user browses the object C to be recommended is determined to be 80 times/minute by the recommending device.
In this embodiment of the application, recommending parameters may further include: click rate, purchase amount and other information. The content included in the recommended parameters is not limited in any way in the embodiment of the present application.
In practical application, the recommendation apparatus records an interactive behavior of a user to an object to be recommended to obtain interactive data, where the interactive behavior may include: click, buy, collect, share, buy, etc. After obtaining the interactive data of each object to be recommended, the recommendation equipment stores the interactive data in the database, so that in the process of browsing the objects to be recommended again by the user, the recommendation equipment can take the interactive data and the biological characteristics of the user when browsing the objects to be recommended as recommendation parameters.
S202, determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended.
The recommendation value is related to a first weight corresponding to the biological feature, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological feature. The larger the first weight is, the higher the degree of interest of the user in the object browsed under the condition of the biological characteristics is, and correspondingly, the smaller the first weight is, the lower the degree of interest of the user in the object browsed under the condition of the biological characteristics is.
When the recommendation parameter only includes the biological feature, the recommendation device may determine the recommendation value of one object to be recommended according to the first weight corresponding to the biological feature of the object to be recommended.
In one example, the biometric features include: pulse, the object to be recommended includes: when the pulse of the object a to be recommended is 60 times/minute, the first weight corresponding to the 60 times/minute is 0.3, and when the user browses the object a to be recommended, the pulse generated by the user when browsing the object a to be recommended is 60 times/minute, which is determined by the recommendation device, at this time, the recommendation device may determine the first weight corresponding to the 60 times/minute to be 0.3 according to the 60 times/minute, and determine the recommendation value of the object a to be recommended to be 0.3 according to the 0.3.
In the embodiment of the application, under the condition that the recommendation parameters include multiple types, the recommendation value of the object to be recommended can be determined based on the weight corresponding to each recommendation parameter.
Taking the example that the recommendation parameters include the biological characteristics, the click rate and the purchase amount, the recommendation value of the object to be recommended can be determined according to the first weight corresponding to the biological characteristics, the weight corresponding to the click rate and the weight corresponding to the purchase amount.
In one example, the recommended parameters include: the pulse rate is 70 times/minute, the click rate is 20, the purchase amount is 30, and the objects to be recommended comprise: the first weight corresponding to 70 times/minute of the object B to be recommended is 0.4, the weight corresponding to 20 click rate is 0.2, the weight corresponding to 30 purchase amount is 0.3, and the recommending device can determine the recommendation value of the user when browsing the object B to be recommended according to the first weight 0.4 corresponding to 70 times/minute of the pulse, the weight 0.2 corresponding to 20 click rate and the weight 0.3 corresponding to 30 purchase amount.
S203, determining a recommended object from the at least one object to be recommended based on the recommended value of each object to be recommended.
In the embodiment of the application, the recommending device can determine the object to be recommended with the recommending value meeting the recommending condition as the recommending object.
The recommendation condition may include: the recommended value is within a threshold range. The threshold value range is not limited in any way in the embodiment of the present application.
In one example, the object to be recommended includes: the recommendation method includes the steps that an object D to be recommended, an object E to be recommended and an object F to be recommended are obtained, wherein the recommendation value of the object D to be recommended is 50, the recommendation value of the object E to be recommended is 30, the recommendation value of the object F to be recommended is 70, the threshold range is 60-80, and the threshold range is 60-80, so that the recommendation device can determine the object F to be recommended as the object F to be recommended from the three objects to be recommended based on the recommendation value 50 of the object D to be recommended, the recommendation value 30 of the object E to be recommended and the recommendation value 70 of the object F to be recommended.
In this embodiment of the application, the recommendation condition may further include: a maximum recommendation value of the at least one recommendation value.
In one example, the object to be recommended includes: the recommendation method comprises the following steps that an object to be recommended H, an object to be recommended I and an object to be recommended G are recommended, wherein the recommendation value of the object to be recommended H is 60, the recommendation value of the object to be recommended I is 70, the recommendation value of the object to be recommended G is 80, and the recommendation value 80 of the object to be recommended G is the largest of the three objects to be recommended, so that the recommendation device can determine the object to be recommended G as the recommendation object from the three objects to be recommended.
The embodiment of the application provides an information recommendation method, which comprises the steps of determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended; determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic; and then determining a recommended object from the at least one object to be recommended based on the recommended value of each object to be recommended. In this way, in the process of determining the recommended object, the recommended object is determined from at least one object to be recommended based on the recommendation value of each object to be recommended, and since the recommendation value is related to the first weight corresponding to the biological characteristic and the first weight represents the interest degree of the object browsed by the user under the condition of the biological characteristic, in the process of browsing the object to be recommended by the user, the recommended object can be provided to the user based on the biological characteristic of the user, so that the accuracy of the personalized recommendation result can be improved.
In some embodiments, as shown in fig. 3, before the above S201, the method further includes the following steps:
s301, determining a second weight of each first reference object in at least one first reference object;
the second weight characterizes a degree of interest of the user in the first reference object. The larger the second weight is, the higher the degree of interest of the characterization user in the first reference object is, and correspondingly, the smaller the second weight is, the lower the degree of interest of the characterization user in the first reference object is.
Here, the first reference object is an object displayed for determining the first weight.
S302, determining a biological feature corresponding to each first reference object in the at least one first reference object;
s303, for each biological feature, determining at least one target object corresponding to the biological feature in the at least one first reference object, and determining a first weight corresponding to the biological feature according to a second weight of the at least one target object.
In an example, the at least one first reference object comprises: SKU1、SKU2、SKU3、SKU4And SKU5；SKU1Corresponding pulse rate of 60 beats/minute, SKU2Corresponding pulse rate of 60 beats/minute, SKU3Corresponding pulse rate of 60 beats/minute, SKU4Corresponding pulse rate of 90 beats/min, SKU5The corresponding pulse rate is 100 times/min; for a pulse of 60 times/minute, the recommendation device can determine that the target object corresponding to the 60 times/minute is SKU from the 5 first reference objects1、SKU2And SKU3And according to SKU1Second weight of 0.4, SKU2Second weight of 0.5, SKU3Is 0.6, the first weight corresponding to the 60 times/minute is determined.
In the embodiment of the application, for a biological feature, the recommendation device determines a first weight corresponding to the biological feature according to the second weight of each target object and the coefficient corresponding to each target object. The coefficient corresponding to each second weight can be set according to actual requirements.
When the coefficients of the second weights are equal and the sum of the coefficients is 1, the first weight obtained based on the second weight of each target object is the mean value of the second weights.
In one example, the at least one target object determined for a pulse of 60 beats/minute from the biometric characteristic includes: SKU4And SKU5；SKU4Second weight of 0.7, SKU5Second weight of 0.8, SKU4Is 1/2 SKU51/2; for a biometric pulse of 60 beats/minute, the recommendation device may be based on SKU40.7, the proportion 1/2 of the second weight 0.7, SKU5The ratio 1/2 of the second weight 0.8, the first weight corresponding to the 80/min is determined to be 0.75.
In the above example, the value ranges of the first weight and the second weight are 0 to 1, in practical applications, the value ranges of the first weight and the second weight are not limited at all, and the value ranges of the first weight and the second weight may be the same or different.
In some embodiments, the S301 includes:
determining at least one second reference object with which the user has interactive behavior; for each of the at least one first reference object, determining a second weight of the first reference object based on a correlation of each of the at least one second reference object with the first reference object.
Here, the at least one second reference object is an object displayed for determining the second weight.
In the embodiment of the application, when a user browses at least one first reference object, the recommendation device determines the biological characteristics of the user when the user browses at least one first reference object, and if the user clicks one of the at least one first reference object, the reference object clicked by the user is the second reference object.
Here, for each first reference object in the at least one first reference object, for each second reference object in the at least one second reference object, the correlation between the second reference object and the first reference object is used to represent whether the second reference object is correlated with the first reference object, and the correlation between the second reference object and the first reference object is represented by the same correlation degree, the same category or the same category between the second reference object and the first reference object.
In one example, if the second reference object is the same as the first reference object, the degree of correlation between the second reference object and the first reference object is high; if the second reference object and the first reference object belong to the same category, the correlation degree between the second reference object and the first reference object is medium; if the second reference object is similar to the first reference object in category, the correlation degree between the second reference object and the first reference object is low.
The value range of the degree of correlation is not limited in the embodiment of the present application, for example, the value range of high is 0.8 to 1, the value range of medium is 0.6 to 0.8, and the value range of low is 0.5 to 0.6.
In an example, if the second reference object and the first reference object are both one-piece dresses, it may be determined that the second reference object and the first reference object are the same, and the degree of correlation therebetween is high.
In some embodiments, determining the second weight of the first reference object according to the correlation of each of the at least one second reference object with the first reference object comprises:
and determining a second weight of the first reference object according to a value corresponding to the degree of correlation between the second reference object and the first reference object.
In an example, if a value corresponding to the degree of correlation between the second reference object and the first reference object is 1, it is determined that the second weight of the first reference object is 1.
In some embodiments, the determining the biometric characteristic corresponding to each of the at least one first reference object comprises:
determining a browsing time of each of the first reference objects; determining an acquisition time of each of the biological features; and for each first reference object in the at least one first reference object, determining the biological characteristics corresponding to the first reference object according to the browsing time and the acquisition time.
Here, when the user browses the first reference object, the client records the current time to obtain the browsing time of the first reference object; and the mobile bracelet records the current time to obtain the acquisition time of the biological characteristics.
Under the condition that the recommendation device is the server, if the client obtains the browsing time of the first reference object, the client can send the browsing time to the server; if the mobile bracelet obtains the acquisition time of the biological features, the mobile bracelet can send the acquisition time to the server.
Under the condition that the recommendation device is the client, if the client obtains the browsing time of the first reference object, the client can directly determine the browsing time; if the mobile bracelet obtains the acquisition time of the biological features, the mobile bracelet can send the acquisition time to the client.
In the embodiment of the application, in the case that at least one first reference object includes 5 first reference objects, the recommendation device determines, from the 5 first reference objects, the biological feature corresponding to each first reference object according to the browsing time and the acquisition time.
And under the condition that the browsing time and the acquisition time are the same, the recommendation device acquires the corresponding biological characteristics of the first reference object according to the same browsing time and the same acquisition time.
In one example, the first reference object is a SKU1，SKU1The browsing time of (2) is 10: 00, SKU1The acquisition time of (2) is 10: 00, SKU1Is 70 pulses/min due to SKU1The browsing time and the acquisition time are the same, and therefore the recommendation device can determine the biometric characteristic 70 times/minute.
In a case that a difference between the browsing time and the obtaining time is smaller than a time difference threshold, the recommendation device may determine the biometric characteristic corresponding to the first reference object according to the browsing time and the obtaining time.
In one example, the first reference object is a SKU2，SKU2The browsing time of (1) is 11:00, the acquisition time of pulse 1 is 11:01, the acquisition time of the pulse 2 is 11:05, time difference threshold of 2 minutes, pulse 1 is SKU since the time difference between 11:00 and 11:01 is less than 2 minutes for 1 minute2A corresponding biometric feature; the time difference between 11:00 and 11:05 5 minutes is greater than 2 minutes, therefore, pulse 2 is not a SKU2A corresponding biometric characteristic.
For the same first reference object, in the case where it is determined that there are a plurality of acquisition times, the recommendation device may take the biometric characteristic corresponding to the last acquisition time as the biometric characteristic corresponding to the first reference object.
In one example, the first reference object is a SKU3First time obtainTaking time as 11: 02, the biological characteristics are obtained at 70 times/min, and the second acquisition time is 11:06, the biometric feature is acquired 80 times/minute, and since the last acquisition time is 11:06, the recommending device can take the biometric feature 80 times/minute corresponding to the acquisition time 11:06 as the SKU3The biological characteristics of (1).
For the same reference object, in the case that multiple acquisition times are determined, the recommendation device may further take the biometric characteristic corresponding to each acquisition time as the biometric characteristic corresponding to the first reference object.
In one example, the first reference object is a SKU4The first acquisition time is 11: 03, the biological characteristics obtained are 70 times/min, the second acquisition time is 11: 07, the acquired biometric characteristic is 80 times/minute, the recommending device may respectively set the first acquisition time 11: 03 biometric feature 70 times/min as SKU4And the second acquisition time 11: 07 corresponding biometric feature 80 times/min as SKU4The biological characteristics of (1).
In some embodiments, the method further comprises:
determining a position on a screen where the user's gaze is projected; determining the first reference object based on the location.
Here, the recommendation apparatus may determine a position on the screen where the user's sight line is projected by being installed on a camera and an eye tracker. Here, the recommendation device collects an image when the user browses the first reference object, and determines a position where the current sight line is projected on the screen based on the collected image, and may also track the position where the sight line is projected on the screen based on the eye tracker.
In this embodiment, one position may correspond to one first reference object, and the recommendation device may determine the first reference object based on a position on the screen where the line of sight of the user is projected.
In some embodiments, the method further comprises: collecting an image; the user's eyes are included in the image; analyzing the image based on a gaze tracking model to determine a location on the screen where the user's gaze is projected.
In the embodiment of the application, the recommendation device can analyze the image including the eyes of the user based on the sight tracking model to determine the position of the sight line of the user projected on the screen.
In some embodiments, the process of establishing the gaze tracking model is: the method comprises the steps of obtaining a training set, wherein the training set comprises images and labels, the labels are used for representing the actual positions of eyes included in the images, analyzing the images included in the training set by a sight tracking model to obtain the predicted positions of the eyes, and continuously training the images included in the training set by the sight tracking model according to the actual positions and the predicted positions to determine the sight tracking model.
In some embodiments, after S203 above, the method further comprises:
receiving interaction information aiming at the recommended object; determining the interest degree of the user in the recommended object based on the interaction information; and updating the first weight corresponding to the biological characteristics according to the interest degree.
In an example, if the user clicks on a recommendation object, it may be determined that the user has a high level of interest in the recommendation object; accordingly, if the user does not click on the recommended object, it may be determined that the user has a low interest level in the recommended object.
In the embodiment of the application, if the user is interested in the recommended object, the first weight corresponding to the biological feature can be increased; accordingly, if the user is not interested in the recommended object, the first weight corresponding to the biometric feature may be decreased.
In an example, the first weight corresponding to the biometric is 0.4, and if the user is interested in the recommended object, 0.4 may be increased to 0.5; if the user is not interested in the recommended object, 0.4 may be reduced to 0.3.
The information recommendation method provided by the embodiment of the application can judge the user interest based on the visual tracking and the user biological feature fluctuation feedback such as the user heartbeat, obtain the implicit feedback of the user, expand the user interest feature and improve the accuracy of the personalized recommendation result.
As shown in fig. 4, the information recommendation method provided in the embodiment of the present application includes the following steps:
s401, the client determines the commodities browsed by the user currently by means of line-of-sight tracking.
In the process of using the mobile phone by a user, the deep learning technology is applied to the sight tracking task, so that the user can operate the picture of the mobile phone picture only by the user shot by the front camera of the mobile phone without the help of other hardware equipment such as an eye tracker, the focusing position of the sight of the user on the mobile phone screen is predicted by a pure software mode, and the commodity browsed by the user at present is known.
Here, the front camera in the terminal device may be used to record the gaze tracking of the user, and the current goods browsed by the user may be determined based on the deep learning network model by using the gaze tracking.
In an example, when a user browses a commodity a, the eyes of the user may rotate upwards, at this time, the front-facing camera records the upwards rotation of the eyes of the user, i.e. gaze tracking, and based on a deep learning network model, determines what the position corresponding to the upwards rotation of the eyes of the user corresponds to from the deep learning network model, and then determines what the commodity the user currently browses based on the correspondence between the position and the commodity.
S402, the client side obtains the user biological feedback information.
Here, the fluctuation data of the biofeedback information such as the pulse and the heartbeat of the user can be acquired by using hardware wearing equipment such as a mobile bracelet, and then the acquired fluctuation data of the biofeedback information is sent to the client.
And S403, the client associates the commodities browsed by the user with the biofeedback information.
Here, when the user browses the goods, the mobile bracelet synchronously records the biofeedback information generated when the user browses the goods and sends the recorded biofeedback information to the client, and after the client receives the biofeedback information, the goods browsed by the user are associated with the biofeedback, that is, the goods browsed by the user correspond to the biofeedback information when the user browses the goods one by one.
And correlating the time when the user keeps track of the sight line to the commodity with the fluctuation information of the biofeedback of the user, such as pulse, heartbeat and the like, and determining the biofeedback information of which wave band the user corresponds to when browsing which commodity. Record X series of items X ═ SKU1，KU2，…，SKUnWhen appearing, the biofeedback information S ═ S occurs1，S2，…，SnChanges in the mean time.
S404, the client identifies the interest signal.
Here, the client records the commodities of which the user in the X-series commodities finally has interactive behaviors such as clicking, collecting, buying, purchasing, sharing and the like, gives different user behavior interest scores to the commodities, fuses the user behavior interest scores of the commodities with the biofeedback information S of the user when the user browses the X-series commodities, and defines the corresponding biofeedback information value S as { S ═ according to the level of the user interest scores1，S2，…，SnAnd obtaining the user interest score of the user biofeedback information according to the matched user interest.
S405, the client side models the interest of the user according to the biological feedback information.
Here, the client uses the weight of biofeedback information such as pulse, heartbeat fluctuation and the like of different commodities browsed by the user as the user characteristic, introduces the final commodity personalized recommendation model according to the strength of the represented user interest, if similar related recommendation can be performed according to the characteristic, if the interest score of the biofeedback information is the highest when the user sees the one-piece dress, recommends more one-piece dress and one-piece dress matched commodities for the user, and introduces the final commodity personalized recommendation model.
S406, the client carries out personalized recommendation for the user.
Here, after the commodity personalized recommendation model is established, personalized recommendation may be performed for the user according to the commodity personalized recommendation model.
And carrying out personalized recommendation according to the weight of the user biofeedback information interest signal, observing whether a personalized recommendation experiment using the user commodity interest signal as a variable has a positive effect on an experiment result, and continuously optimizing the accuracy of a training model, wherein if the weight of the current user biofeedback information interest signal in the commodity personalized recommendation model is 0.5 and the experiment effect is slightly negative, the weight can be considered to be adjusted to 0.3.
In the embodiment of the application, changes of different commodities when being seen can be used as interest characteristics of the user by utilizing other collected biological characteristics such as brain waves, facial expressions and the like of the user, and the personalized recommendation model is introduced to supplement the lack of user feedback from the moment that the user browses the commodities to the moment that the user finally generates active interaction with the commodities, so that the accuracy of personalized recommendation is improved.
Fig. 5 is an information recommendation apparatus according to an embodiment of the present application, and as shown in fig. 5, the information recommendation apparatus 500 includes:
a first determining unit 501, configured to determine a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended;
a second determining unit 502, configured to determine a recommendation value of each object to be recommended according to a recommendation parameter corresponding to the object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic;
a third determining unit 503, configured to determine, based on the recommendation value of each object to be recommended, a recommended object from the at least one object to be recommended.
In some embodiments, the information recommendation apparatus further includes:
a processing unit for determining a second weight for each of at least one first reference object; the second weight characterizes a degree of interest of the user in the first reference object;
the processing unit is further configured to determine a biological feature corresponding to each of the at least one first reference object;
the processing unit is further configured to, for each biometric feature, determine at least one target object corresponding to the biometric feature in the at least one first reference object, and determine a first weight corresponding to the biometric feature according to a second weight of the at least one target object.
In some embodiments, the processing unit is further configured to determine at least one second reference object with which the user has interactive behavior;
the processing unit is further configured to determine, for each of the at least one first reference object, a second weight of the first reference object according to a correlation of each of the at least one second reference object with the first reference object.
In some embodiments, the processing unit is further configured to determine a browsing time of each of the first reference objects;
the processing unit is further used for determining the acquisition time of each biological characteristic;
the processing unit is further configured to determine, for each of the at least one first reference object, a biometric feature corresponding to the first reference object according to the browsing time and the acquisition time.
In some embodiments, the processing unit is further configured to determine a location on a screen where the user's gaze is projected; the processing unit is further configured to determine the first reference object based on the position.
In some embodiments, the information recommendation device 500 further includes: the acquisition unit is used for acquiring images; the user's eyes are included in the image; the processing unit is further used for analyzing the image based on a sight tracking model and determining the position of the sight line of the user projected on the screen.
In some embodiments, as shown in fig. 5, the information recommendation apparatus 500 further includes: a receiving unit and an updating unit;
the receiving unit is used for receiving the interaction information aiming at the recommended object;
the processing unit is further used for determining the interest degree of the user in the recommended object based on the interaction information;
the updating unit is used for updating the first weight corresponding to the biological characteristics according to the interest degree.
It should be noted that each unit included in the recommendation apparatus provided in the embodiment of the present application may be implemented by a processor in an electronic device; of course, the implementation can also be realized through a specific logic circuit; in the implementation process, the Processor may be a Central Processing Unit (CPU), a microprocessor Unit (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.
The above description of the apparatus embodiments, similar to the above description of the method embodiments, has similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
It should be noted that, in the embodiment of the present application, if the recommendation method is implemented in the form of a software functional module and sold or used as a standalone product, the recommendation method may also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the related art may be embodied in the form of a software product stored in a storage medium, and including several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
The embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the recommended method provided in the foregoing embodiment is implemented. The electronic device can be a client or a server.
The present application provides a storage medium, that is, a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the recommendation method provided in the above embodiments.
Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
It should be noted that fig. 6 is a schematic hardware entity diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 6, the electronic device 600 includes: a processor 601, at least one communication bus 602, at least one external communication interface 604, and memory 605. Wherein the communication bus 602 is configured to enable connective communication between these components. In an example, the electronic device 600 further comprises: a user interface 603, wherein the user interface 603 may comprise a display screen and the external communication interface 604 may comprise a standard wired interface and a wireless interface.
The Memory 605 is configured to store instructions and applications executable by the processor 601, and may also buffer data (e.g., image data, audio data, voice communication data, and video communication data) to be processed or already processed by the processor 601 and modules in the electronic device, and may be implemented by a FLASH Memory (FLASH) or a Random Access Memory (RAM).
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be 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 unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the related art may be embodied in the form of a software product stored in a storage medium, and including several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the 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 conceive of 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.
Claims (10)
1. An information recommendation method, characterized in that the method comprises:
determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended;
determining a recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic;
and determining a recommended object from the at least one object to be recommended based on the recommendation value of each object to be recommended.
2. The method according to claim 1, wherein before determining the recommendation parameter of each of the at least one object to be recommended, the method further comprises:
determining a second weight for each of at least one first reference object; the second weight characterizes a degree of interest of the user in the first reference object;
determining a corresponding biological feature of each first reference object in the at least one first reference object;
for each biological feature, at least one target object corresponding to the biological feature in the at least one first reference object is determined, and a first weight corresponding to the biological feature is determined according to a second weight of the at least one target object.
3. The method of claim 2, wherein determining the second weight of each of the at least one first reference object comprises:
determining at least one second reference object with which the user has interactive behavior;
for each of the at least one first reference object, determining a second weight of the first reference object based on a correlation of each of the at least one second reference object with the first reference object.
4. The method of claim 2, wherein the determining the corresponding biometric characteristic of each of the at least one first reference object comprises:
determining a browsing time of each of the first reference objects;
determining an acquisition time of each of the biological features;
and for each first reference object in the at least one first reference object, determining the biological characteristics corresponding to the first reference object according to the browsing time and the acquisition time.
5. The method of claim 2, further comprising:
determining a position on a screen where the user's gaze is projected;
determining the first reference object based on the location.
6. The method of claim 5, wherein determining the location on the screen where the user's eyes are projected comprises:
collecting an image; the user's eyes are included in the image;
analyzing the image based on a gaze tracking model to determine a location on the screen where the user's gaze is projected.
7. The method of claim 1, wherein after the determining the recommended object, the method further comprises:
receiving interaction information aiming at the recommended object;
determining the interest degree of the user in the recommended object based on the interaction information;
and updating the first weight corresponding to the biological characteristics according to the interest degree.
8. An information recommendation apparatus, characterized in that the apparatus comprises:
the first determining unit is used for determining a recommendation parameter of each object to be recommended in at least one object to be recommended; the recommended parameters include: the user browses the biological characteristics of the object to be recommended;
the second determining unit is used for determining the recommendation value of each object to be recommended according to the recommendation parameter corresponding to each object to be recommended; the recommendation value is related to a first weight corresponding to the biological characteristic, and the first weight represents the interest degree of the user in the object browsed under the condition of the biological characteristic;
and the third determining unit is used for determining a recommended object from the at least one object to be recommended based on the recommended value of each object to be recommended.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the information recommendation method of any one of claims 1 to 7 when executing the computer program.
10. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the information recommendation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110743949.0A CN113409123A (en) | 2021-07-01 | 2021-07-01 | Information recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110743949.0A CN113409123A (en) | 2021-07-01 | 2021-07-01 | Information recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113409123A true CN113409123A (en) | 2021-09-17 |
Family
ID=77680773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110743949.0A Pending CN113409123A (en) | 2021-07-01 | 2021-07-01 | Information recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409123A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708358A (en) * | 2012-04-18 | 2012-10-03 | 北京十分科技有限公司 | Reading-trajectory recognizing method |
| KR20160088770A (en) * | 2015-01-16 | 2016-07-26 | 김성일 | Method for providing location-based information |
| CN106503140A (en) * | 2016-10-20 | 2017-03-15 | 安徽大学 | One kind is based on Hadoop cloud platform web resource personalized recommendation system and method |
| CN107210830A (en) * | 2015-02-05 | 2017-09-26 | 华为技术有限公司 | A kind of object based on biological characteristic presents, recommends method and apparatus |
| CN107666518A (en) * | 2017-09-27 | 2018-02-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, terminal device and computer-readable recording medium |
| CN108073284A (en) * | 2017-12-15 | 2018-05-25 | 南京信息工程大学 | Purchase system based on brain wave identification mood |
| CN109145195A (en) * | 2017-06-28 | 2019-01-04 | 南宁富桂精密工业有限公司 | Information recommendation method, electronic device and computer readable storage medium |
| US20190019236A1 (en) * | 2017-07-13 | 2019-01-17 | Sk Planet Co., Ltd. | Method for providing service of personalized recommendation based on e-mail and apparatus therefor |
| CN109582821A (en) * | 2018-11-27 | 2019-04-05 | 努比亚技术有限公司 | A kind of music object recommendation method, terminal and computer readable storage medium |
| CN110311950A (en) * | 2019-05-21 | 2019-10-08 | 平安科技（深圳）有限公司 | Information-pushing method, device, equipment and computer readable storage medium |
| CN110750707A (en) * | 2018-07-23 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Keyword recommendation method and device and electronic equipment |
| CN111008869A (en) * | 2019-12-05 | 2020-04-14 | 秒针信息技术有限公司 | Advertisement recommendation method and device, electronic equipment and storage medium |
| WO2020165717A1 (en) * | 2019-02-12 | 2020-08-20 | Gaurav Dubey | Systems and methods for career/profession recommendation |
| CN112184374A (en) * | 2020-09-28 | 2021-01-05 | 广东智源机器人科技有限公司 | Commodity recommendation method and device, computer equipment and storage medium |
| CN112308650A (en) * | 2020-07-01 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Recommendation reason generation method, device, equipment and storage medium |
| CN112541093A (en) * | 2020-12-10 | 2021-03-23 | 新华网股份有限公司 | Music recommendation method, system, storage medium and electronic device |
-
2021
- 2021-07-01 CN CN202110743949.0A patent/CN113409123A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708358A (en) * | 2012-04-18 | 2012-10-03 | 北京十分科技有限公司 | Reading-trajectory recognizing method |
| KR20160088770A (en) * | 2015-01-16 | 2016-07-26 | 김성일 | Method for providing location-based information |
| CN107210830A (en) * | 2015-02-05 | 2017-09-26 | 华为技术有限公司 | A kind of object based on biological characteristic presents, recommends method and apparatus |
| CN106503140A (en) * | 2016-10-20 | 2017-03-15 | 安徽大学 | One kind is based on Hadoop cloud platform web resource personalized recommendation system and method |
| CN109145195A (en) * | 2017-06-28 | 2019-01-04 | 南宁富桂精密工业有限公司 | Information recommendation method, electronic device and computer readable storage medium |
| US20190019236A1 (en) * | 2017-07-13 | 2019-01-17 | Sk Planet Co., Ltd. | Method for providing service of personalized recommendation based on e-mail and apparatus therefor |
| CN107666518A (en) * | 2017-09-27 | 2018-02-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, terminal device and computer-readable recording medium |
| CN108073284A (en) * | 2017-12-15 | 2018-05-25 | 南京信息工程大学 | Purchase system based on brain wave identification mood |
| CN110750707A (en) * | 2018-07-23 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Keyword recommendation method and device and electronic equipment |
| CN109582821A (en) * | 2018-11-27 | 2019-04-05 | 努比亚技术有限公司 | A kind of music object recommendation method, terminal and computer readable storage medium |
| WO2020165717A1 (en) * | 2019-02-12 | 2020-08-20 | Gaurav Dubey | Systems and methods for career/profession recommendation |
| CN110311950A (en) * | 2019-05-21 | 2019-10-08 | 平安科技（深圳）有限公司 | Information-pushing method, device, equipment and computer readable storage medium |
| CN111008869A (en) * | 2019-12-05 | 2020-04-14 | 秒针信息技术有限公司 | Advertisement recommendation method and device, electronic equipment and storage medium |
| CN112308650A (en) * | 2020-07-01 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Recommendation reason generation method, device, equipment and storage medium |
| CN112184374A (en) * | 2020-09-28 | 2021-01-05 | 广东智源机器人科技有限公司 | Commodity recommendation method and device, computer equipment and storage medium |
| CN112541093A (en) * | 2020-12-10 | 2021-03-23 | 新华网股份有限公司 | Music recommendation method, system, storage medium and electronic device |
Non-Patent Citations (1)
| Title |
|---|
| 谢祈鸿: "一种基于混合用户兴趣模型的个性化推荐系统", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》, no. 01, 15 January 2007 (2007-01-15), pages 138 - 314 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
| CN116823408B (en) * | 2023-08-29 | 2023-12-01 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740466B (en) | Method for acquiring advertisement putting strategy and computer readable storage medium | |
| JP6482172B2 (en) | RECOMMENDATION DEVICE, RECOMMENDATION METHOD, AND PROGRAM | |
| US20130243332A1 (en) | Method and System for Estimating an Object of Interest | |
| US11270368B2 (en) | Method and apparatus for presenting object based on biometric feature | |
| US20200175303A1 (en) | Customized action based on video item events | |
| US20150215412A1 (en) | Social network service queuing using salience | |
| CN104994409A (en) | Media data editing method and device | |
| US20180330249A1 (en) | Method and apparatus for immediate prediction of performance of media content | |
| US20180121946A1 (en) | Information processing system, communication device, control method, and storage medium | |
| CN106897369B (en) | Content data recommendation method and system | |
| US20160267521A1 (en) | Systems and methods for electronically monitoring audience attentiveness and receptiveness | |
| US20160267532A1 (en) | Method and system for dynamically adjusting displayed content based on analysis of viewer attributes | |
| CN111465949A (en) | Information processing apparatus, information processing method, and program | |
| Wedel et al. | Eye tracking methodology for research in consumer psychology | |
| CN113409123A (en) | Information recommendation method, device, equipment and storage medium | |
| CN107833263A (en) | Feature tracking method and device | |
| WO2019206038A1 (en) | Attention information processing method and apparatus, storage medium, and electronic device | |
| JP7110738B2 (en) | Information processing device, program and information processing system | |
| CN113033413A (en) | Glasses recommendation method and device, storage medium and terminal | |
| CN110262663B (en) | Schedule generation method based on eyeball tracking technology and related product | |
| US10755088B2 (en) | Augmented reality predictions using machine learning | |
| EP4113413A1 (en) | Automatic purchase of digital wish lists content based on user set thresholds | |
| CN111787860A (en) | Measuring method for storing multimedia message | |
| JP2024520442A (en) | Effective identification and notification of hidden stressors | |
| CN112905904B (en) | Recommendation method, recommendation device, server 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 |