CN113435970B - Product recommendation method and device based on biological information, electronic equipment and medium - Google Patents
Product recommendation method and device based on biological information, electronic equipment and medium Download PDFInfo
- Publication number
- CN113435970B CN113435970B CN202110701968.7A CN202110701968A CN113435970B CN 113435970 B CN113435970 B CN 113435970B CN 202110701968 A CN202110701968 A CN 202110701968A CN 113435970 B CN113435970 B CN 113435970B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- product recommendation
- target user
- time period
- 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.)
- Active
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to data processing, and discloses a product recommendation method based on biological information, which comprises the following steps: acquiring basic information of a target user, and constructing a user portrait of the target user based on the basic information; inputting the user portrait into a product recommendation model to obtain initial product recommendation information corresponding to a target user; acquiring original biological information and original environment information when a target user browses the initial product recommendation information, and performing emotion recognition based on the original biological information and the original environment information; and updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information. The invention also provides a product recommendation device, electronic equipment and a medium based on the biological information. The invention improves the real-time performance and accuracy of product recommendation.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a product recommendation method and apparatus based on biometric information, an electronic device, and a medium.
Background
With the development of product diversification, how to quickly and accurately recommend interesting products to users becomes a key point of attention. Currently, a product list to be recommended is determined for a user according to historical search data and historical purchase data of the user, however, the product list determined in this way has certain delay and is not high in accuracy.
Disclosure of Invention
In view of the above, there is a need to provide a product recommendation method based on biological information, aiming to improve the real-time performance and accuracy of product recommendation.
The invention provides a product recommendation method based on biological information, which comprises the following steps:
responding to a product recommendation request aiming at a target user sent by a client, acquiring basic information of the target user from a first database, and constructing a user portrait of the target user based on the basic information of the target user;
inputting the user portrait of the target user into a product recommendation model to obtain initial product recommendation information corresponding to the target user, and sending the initial product recommendation information to a target terminal;
acquiring original biological information and original environment information of the target user when the target user browses the initial product recommendation information at the target terminal, and performing emotion recognition on the target user based on the original biological information and the original environment information;
and updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information.
Optionally, the original biological information and original environment information carry browsing timestamps, and performing emotion recognition on the target user based on the original biological information and the original environment information includes:
splitting the original biological information and the original environment information according to a preset time period to obtain biological information sets and environment information sets corresponding to a plurality of time periods;
calculating the average value of each factor in each biological information set and each factor in the environment information set to obtain target biological information and target environment information corresponding to each time period;
and performing emotion recognition based on the target biological information and the target environment information to obtain emotion recognition results of the target user in each time period.
Optionally, the performing emotion recognition based on the target biological information and the target environment information to obtain an emotion recognition result of the target user in each time period includes:
selecting target biological information and target environment information corresponding to a time period, and performing feature processing on the selected target biological information and the selected target environment information to obtain a first feature sequence of the target user in the selected time period;
acquiring a first sample set carrying emotion category marking information from a second database, and determining the neighborhood of the target user in the selected time period based on the first sample set;
extracting a preset number of samples from the neighborhood to obtain a second sample set, and acquiring a second characteristic sequence of each sample in the second sample set;
determining a target emotion category for the target user at the selected time period based on the first and second feature sequences.
Optionally, the determining the target emotion category of the target user in the selected time period based on the first feature sequence and the second feature sequence includes:
calculating a first membership degree of each sample in the second sample set and each emotion category;
calculating the similarity between the second characteristic sequence of each sample in the second sample set and the first characteristic sequence;
determining second membership degrees of the first feature sequence and each emotion category based on the first membership degrees and the similarity degrees;
and taking the emotion category with the maximum second membership as the target emotion category of the target user in the selected time period.
Optionally, the emotion recognition result includes pleasure, relaxation, boredom and aversion, the updating the initial product recommendation information based on the emotion recognition result, and the obtaining the target product recommendation information includes:
when the emotion recognition result of a certain specified time period is happy or relaxed, acquiring first product information browsed by the target user in the specified time period, and adding product information of the same type as the first product information in the initial product recommendation information to obtain target product recommendation information;
and if the emotion recognition result in a certain specified time period is boring or boring, acquiring second product information browsed by the target user in the specified time period, reducing the same type of product information as the second product information in the initial product recommendation information, and increasing product information with low correlation degree with the second product information to obtain target product recommendation information.
Optionally, the basic information includes a plurality of indicator items and an indicator value corresponding to each indicator item in the plurality of indicator items, and the constructing the user representation of the target user based on the basic information of the target user includes:
acquiring a mapping relation between the index value corresponding to each index item and the label from a third database;
determining target labels corresponding to all index items in the basic information of the target user based on the mapping relation;
and taking the set of target labels as a user representation of the target user.
Optionally, the original biological information includes information of skin impedance, skin temperature, blood pressure, blood oxygen, pulse, electrocardiogram, and brain wave, and the original environmental information includes information of a GPS location, an environmental temperature, an environmental humidity, and an environmental brightness.
In order to solve the above problems, the present invention also provides a product recommendation apparatus based on biological information, the apparatus including:
the system comprises a construction module, a first database and a second database, wherein the construction module is used for responding to a product recommendation request aiming at a target user sent by a client, acquiring basic information of the target user from the first database, and constructing a user portrait of the target user based on the basic information of the target user;
the sending module is used for inputting the user portrait of the target user into a product recommendation model to obtain initial product recommendation information corresponding to the target user, and sending the initial product recommendation information to a target terminal;
the identification module is used for acquiring original biological information and original environment information of the target user when the target user browses the initial product recommendation information at the target terminal and carrying out emotion identification on the target user based on the original biological information and the original environment information;
and the updating module is used for updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a product recommendation program executable by the at least one processor, the product recommendation program being executable by the at least one processor to enable the at least one processor to perform the above-described biometric-information-based product recommendation method.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having a product recommendation program stored thereon, the product recommendation program being executable by one or more processors to implement the above-mentioned biometric-information-based product recommendation method.
Compared with the prior art, the method comprises the steps of firstly obtaining basic information of a target user, and constructing a user portrait of the target user based on the basic information; then, inputting the user portrait into a product recommendation model to obtain initial product recommendation information corresponding to the target user; then, acquiring original biological information and original environment information of a target user when the target user browses the initial product recommendation information at a target terminal, and performing emotion recognition on the target user based on the original biological information and the original environment information, wherein the emotion recognition result is more accurate; and finally, updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information, and adjusting the product recommendation information in real time according to the emotion recognition result so that the target product recommendation information is higher in real time and more accurate. Therefore, the invention improves the real-time performance and accuracy of product recommendation.
Drawings
Fig. 1 is a flowchart illustrating a method for recommending a product based on biometric information according to an embodiment of the present invention;
FIG. 2 is a block diagram of a product recommendation device based on biometric information according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device implementing a product recommendation method based on biological information according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides a product recommendation method based on biological information. Referring to fig. 1, a flowchart of a method for recommending a product based on biometric information according to an embodiment of the present invention is shown. The method may be performed by an electronic device, which may be implemented by software and/or hardware.
In this embodiment, the product recommendation method based on biological information includes:
s1, responding to a product recommendation request aiming at a target user sent by a client, acquiring basic information of the target user from a first database, and constructing a user portrait of the target user based on the basic information of the target user.
In this embodiment, the client may be an intelligent device of a product popularization party, the basic information includes a plurality of index items and an index value corresponding to each of the plurality of index items, and the index items include age, gender, address, occupation, and the like.
The characteristics of the user in each index item can be determined through the index value, and further the user portrait can be constructed.
The constructing the user representation of the target user based on the basic information of the target user comprises:
a11, acquiring a mapping relation between an index value corresponding to each index item and a label from a third database;
the embodiment takes the age and the address of the index item as an example to illustrate the mapping relationship between the index value and the label.
The mapping relation between the index value corresponding to the age and the label is as follows:
youngsters, under 18 years old;
18-30 years old, young;
age 31-50, middle aged;
over 50 years old, elderly.
The mapping relation between the index value corresponding to the address and the label is as follows:
beijing, shanghai, guangzhou, shenzhen, the first-line city;
xiamen, wuxi, kunming, wenzhou, changchun, nanning, jinhua, \ 8230, zhuhai, second-line city;
……
a12, determining target labels corresponding to all index items in the basic information of the target user based on the mapping relation;
if the target user's basic information includes the age of 25 years, the gender of women, the address of Shanghai, and the occupation of foreign enterprises and employees, the labels corresponding to the target user's index items are youth, women, first-line city, and white-collar.
And A13, taking the set of target labels as the user portrait of the target user.
And summarizing the labels corresponding to the index items to obtain the user portrait of the target user.
S2, inputting the user portrait of the target user into a product recommendation model to obtain initial product recommendation information corresponding to the target user, and sending the initial product recommendation information to a target terminal.
In this embodiment, the product recommendation model is configured to recommend a product to a user according to a user figure, the initial product recommendation information may be an advertisement poster or a poster of the product to be recommended, and the target terminal may be a computer connected to the acquisition instrument.
The construction process of the product recommendation model comprises the following steps:
b11, acquiring basic information and historical purchase data of a plurality of users from a fourth database;
the fourth database may be a database used by the shopping platform to store data.
B12, constructing a user portrait of each user based on basic information of each user in the plurality of users;
the process of constructing the user image is the same as step S1, and is not described herein again.
B13, determining a preferred product of each user based on the historical purchase data;
and taking the product with the most purchase frequency in the historical purchase data of each user as the preference product of each user, for example, if the product with the most purchase frequency in the historical purchase data of the user 1 is a cosmetic, the preference product of the user 1 is a cosmetic.
B14, inputting the user portrait of each user into an initial recommendation model to obtain a product to be recommended of each user;
in this embodiment, the initial recommendation model may be a neural network model, or may be a support vector machine or a random forest model.
And B15, adjusting the structural parameters of the initial recommendation model by minimizing the loss value between the product to be recommended and the preference product to obtain the product recommendation model.
The calculation formula of the loss value is as follows:
wherein q is i For the ith user's product to be recommended, p i Preferred products for the ith user, c total number of users, loss (q) i ,p i ) The loss value between the product to be recommended and the preferred product of the ith user.
S3, collecting original biological information and original environment information of the target user when the target terminal browses the initial product recommendation information, and performing emotion recognition on the target user based on the original biological information and the original environment information.
In this embodiment, the collection instrument can be data of 1 second collection, and the collection instrument includes wireless wearable equipment (like earphone, bracelet, helmet, neck ring etc.) and environment collection appearance, wireless wearable equipment is used for gathering user's original biological information, and the environment collection appearance is used for gathering the original environmental information of the environment that the user was located.
The original biological information comprises skin impedance, skin temperature, blood pressure, blood oxygen, pulse, electrocardio and brain wave information, and the original environment information comprises information of a GPS position, environment temperature, environment humidity and environment brightness.
In order to determine the identity of the collected user, in this embodiment, before collecting information, identity information of the user to be collected needs to be entered.
The original biological information and the original environment information carry browsing timestamps, and the emotion recognition of the target user based on the original biological information and the original environment information comprises the following steps:
c11, splitting the original biological information and the original environment information according to a preset time period to obtain biological information sets and environment information sets corresponding to a plurality of time periods;
for example, if the time for the target user to browse the initial product recommendation information is 15 seconds, and if the preset time period is 3 seconds, the biological information set and the environmental information set corresponding to 5 time periods can be obtained by splitting.
C12, calculating the average value of each factor in each biological information set and each environmental information set to obtain target biological information and target environmental information corresponding to each time period;
for example, an average value of skin impedance in a set of biological information corresponding to a certain time period is calculated to obtain a value of skin impedance in target biological information corresponding to the time period.
If the pulse in the biological information set corresponding to the first time period is 75, 72, or 79, respectively, the value of the pulse in the target biological information corresponding to the first time period is (75 +74+ 79)/3 =76.
If the environmental humidities in the environmental information set corresponding to the third time period are 60.1%, 60.3%, and 60.2%, respectively, the value of the environmental humidity in the target environmental information corresponding to the third time period is (60.1% +60.3% + 60.2%)/3 =60.2%.
And C13, performing emotion recognition based on the target biological information and the target environment information to obtain emotion recognition results of the target user in each time period.
The biological information can reflect the emotional state of the user, and the environmental information can also influence the emotion of the user to a certain extent.
And the emotion recognition result is the recognized emotion category, including joy, aversion, boredom and relaxation.
The emotion recognition based on the target biological information and the target environment information to obtain the emotion recognition result of the target user in each time period comprises the following steps of D11-D14:
d11, selecting target biological information and target environment information corresponding to a time period, and performing feature processing on the selected target biological information and the selected target environment information to obtain a first feature sequence of the target user in the selected time period;
the present embodiment describes the emotion recognition process for one time period as an example.
The step of performing feature processing on the selected target biological information and the target environment information to obtain a first feature sequence of the target user in a selected time period includes steps E11 to E12:
e11, splicing all factors in the selected target biological information and the selected target environment information according to a preset sequence to obtain a characteristic factor sequence;
in this embodiment, the preset sequence is a sequence in which the variation range of each factor is from large to small when the emotion of the sample data is changed from one emotion to another emotion, for example, when the emotion of the user is changed from relaxed to happy in the sample data, the average variation range of the pulse is larger than the average variation range of the blood pressure, the average variation range of the blood pressure is larger than the variation range of the skin temperature, the pulse is arranged in front of the blood pressure and the skin temperature in the preset sequence, and the blood pressure is arranged in front of the skin temperature.
And E12, filling the product of the weight of each factor and the corresponding numerical value in the selected target biological information and the target environment information into the characteristic factor sequence to obtain a first characteristic sequence of the target user in the selected time period.
In this embodiment, the weight corresponding to each factor is preset, the weight of the factor is multiplied by the value of the factor in the selected time period, and the product is input into the feature factor sequence, so as to obtain the first feature sequence of the target user in the selected time period.
D12, acquiring a first sample set carrying emotion category marking information from a second database, and determining a neighborhood of the target user in the selected time period based on the first sample set;
in this embodiment, the emotion classification label information includes an emotion classification name, an arousal level, and a performance.
The relationship between mood category and arousal and performance is: when the arousal degree and the efficiency are high, the emotion category is happy; when the arousal degree and the efficiency are lower, the emotion category is boring; the emotional category is aversion when arousal is high and potency is low; the emotional category is relaxed when arousal is low and performance is high.
Said determining a neighborhood of said target user in said selected time period based on said first sample set comprises steps F11-F12:
f11, determining a concentration threshold based on the electroencephalogram of each sample in the first sample set and the awakening degree in the emotion category marking information;
in this embodiment, the process of converting the brain waves into the concentration degree first is the prior art (fourier transform is performed on the brain waves first, and then frequency analysis is performed on the fourier transform result, and the brain waves are split into α, β, and γ waves, where the β waves are the concentration degree), which is not described herein again.
The concentration threshold comprises an upper concentration limit and a lower concentration limitLimit, when concentration is greater than a certain threshold T up When the corresponding samples are all high arousal degree samples (i.e. the emotion types are aversion and pleasure), the upper limit of concentration is T up (ii) a When the concentration degree is less than a certain threshold value T down When the corresponding samples are all low arousal samples (i.e. the emotion category is boring and relaxing), the lower limit of concentration is T down 。
And F12, determining the neighborhood of the target user in the selected time period based on the concentration threshold.
The calculation formula of the neighborhood is as follows:
when the concentration of the target user in the selected time period is greater than the concentration upper limit, the neighborhood of the target user in the selected time period is a high arousal sample (a sample of aversion and pleasure emotions); when the concentration of the target user in the selected time period is less than the lower concentration limit, the neighborhood of the target user in the selected time period is a low arousal sample (a sample of boring and relaxing emotions); when the concentration of the target user is less than the upper concentration limit and greater than the lower concentration limit for the selected time period, the target user's neighborhood for the selected time period is all samples (samples of dislike, joy, boring, and relaxing emotions).
In the embodiment, the emotion category of the target user is determined by the neighbor, and the calculation formula of the neighborhood can reduce the range of the neighborhood and reduce subsequent calculation amount.
D13, extracting a preset number of samples from the neighborhood to obtain a second sample set, and obtaining a second characteristic sequence of each sample in the second sample set;
the process of determining the second signature sequence is the same as the process of determining the first signature sequence, and is not described herein again.
And D14, determining a target emotion category of the target user in the selected time period based on the first feature sequence and the second feature sequence.
And determining the association relation between the second characteristic sequence and the emotion category by knowing the second characteristic sequence of each sample in the second sample set and the emotion category marking information of each sample in the second sample set, and further determining the emotion category corresponding to the first characteristic sequence.
In this embodiment, the determining the target emotion category of the target user in the selected time period based on the first feature sequence and the second feature sequence includes G11 to G14:
g11, calculating a first membership degree of each sample in the second sample set and each emotion category;
the calculation formula of the first membership degree is as follows:
wherein u is ij Is the first degree of membership of the ith sample and the jth emotion class in the second sample set, k is the number of samples in the second sample set, n j Number of samples whose emotion classification in the second sample set is labeled with information of jth emotion classification, c i And marking the emotion category in the emotion category information of the ith sample in the second sample set.
G12, calculating the similarity of the second characteristic sequence of each sample in the second sample set and the first characteristic sequence;
the calculation formula of the similarity is as follows:
wherein s is i Similarity between the second characteristic sequence of the ith sample in the second sample set and the first characteristic sequence, t is the first characteristic sequence, t i Is the second signature sequence of the ith sample in the second sample set, and k is the number of samples in the second sample set.
G13, determining second membership degrees of the first feature sequence and each emotion class based on the first membership degrees and the similarity degrees;
the calculation formula of the second membership degree is as follows:
wherein v is j Second degree of membership, s, of the first signature sequence to the jth emotion class i Is the similarity between the second signature sequence of the ith sample in the second sample set and the first signature sequence, u ij And the first membership degree of the ith sample and the jth emotion class in the second sample set, k is the number of samples in the second sample set, and T is a matrix formed by second characteristic sequences of the samples in the second sample set.
And G14, taking the emotion category with the maximum second membership as the target emotion category of the target user in the selected time period.
And calculating a second membership degree of the first characteristic sequence and each emotion category according to a calculation formula of the second membership degree, and taking the emotion category with the maximum second membership degree as a target emotion category of the target user in a selected time period.
And S4, updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information.
And determining whether the target user is satisfied with the initial product recommendation information according to the emotion recognition result, and further adjusting the initial product recommendation information to obtain the target product recommendation information. By the aid of the method and the device, attitude of the target user to the initial product recommendation information can be acquired in real time, and the initial product recommendation information is adjusted in real time, so that the target product recommendation information is high in instantaneity and accurate.
Updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information comprises:
h11, when the emotion recognition result in a certain specified time period is happy or relaxed, acquiring first product information browsed by the target user in the specified time period, and adding product information of the same type as the first product information in the initial product recommendation information to obtain target product recommendation information;
when the emotion recognition result corresponding to a time period is happy or relaxed, the target user is indicated to be satisfied with the first product information browsed in the time period, and at the moment, the product information of the same type as the first product information can be added to obtain target product recommendation information.
And H12, if the emotion recognition result in a certain specified time period is boring or disgust, acquiring second product information browsed by the target user in the specified time period, reducing the product information with the same type as the second product information in the initial product recommendation information, and increasing the product information with low correlation degree with the second product information to obtain target product recommendation information.
If the emotion recognition result corresponding to the time slot is boring or boring, the target user is not satisfied with the second product information browsed in the time slot, at the moment, the product information of the same type as the second product information can be reduced, the product information with low association degree with the second product information is added, and the target product recommendation information is obtained.
According to the embodiment, the product recommendation method based on the biological information, provided by the invention, comprises the steps of firstly, obtaining basic information of a target user, and constructing a user portrait of the target user based on the basic information; then, inputting the user portrait into a product recommendation model to obtain initial product recommendation information corresponding to the target user; then, acquiring original biological information and original environment information of a target user when the target user browses the initial product recommendation information at a target terminal, and carrying out emotion recognition on the target user based on the original biological information and the original environment information, wherein the emotion recognition result is more accurate; and finally, updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information, and adjusting the product recommendation information in real time according to the emotion recognition result so that the target product recommendation information is higher in real time and more accurate. Therefore, the invention improves the real-time performance and accuracy of product recommendation.
Fig. 2 is a schematic block diagram of a product recommendation apparatus based on biometric information according to an embodiment of the present invention.
The biometric information based product recommendation apparatus 100 according to the present invention may be installed in an electronic device. According to the implemented functions, the biometric-information-based product recommendation apparatus 100 may include a construction module 110, a transmission module 120, an identification module 130, and an update module 140. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and are stored in a memory of the electronic device.
In the present embodiment, the functions of the respective modules/units are as follows:
the building module 110 is configured to respond to a product recommendation request sent by a client for a target user, obtain basic information of the target user from a first database, and build a user portrait of the target user based on the basic information of the target user.
The constructing the user representation of the target user based on the basic information of the target user comprises:
a21, acquiring a mapping relation between an index value corresponding to each index item and a label from a third database;
a22, determining target labels corresponding to all index items in the basic information of the target user based on the mapping relation;
and A23, taking the set of target labels as a user portrait of the target user.
And the sending module 120 is configured to input the user portrait of the target user into a product recommendation model, obtain initial product recommendation information corresponding to the target user, and send the initial product recommendation information to a target terminal.
The construction process of the product recommendation model comprises the following steps:
b21, acquiring basic information and historical purchase data of a plurality of users from a fourth database;
b22, constructing a user portrait of each user based on basic information of each user in the plurality of users;
b23, determining the preference product of each user based on the historical purchase data;
b24, inputting the user portrait of each user into an initial recommendation model to obtain a product to be recommended of each user;
and B25, adjusting the structural parameters of the initial recommendation model by minimizing the loss value between the product to be recommended and the preference product to obtain the product recommendation model.
The identification module 130 is configured to collect original biological information and original environment information of the target user when the target terminal browses the initial product recommendation information, and perform emotion identification on the target user based on the original biological information and the original environment information.
The original biological information and the original environment information carry browsing timestamps, and the emotion recognition of the target user based on the original biological information and the original environment information comprises the following steps:
c21, splitting the original biological information and the original environment information according to a preset time period to obtain biological information sets and environment information sets corresponding to a plurality of time periods;
c22, calculating the average value of each factor in each biological information set and each environmental information set to obtain target biological information and target environmental information corresponding to each time period;
and C23, performing emotion recognition based on the target biological information and the target environment information to obtain emotion recognition results of the target user in each time period.
The emotion recognition based on the target biological information and the target environment information to obtain the emotion recognition result of the target user in each time period comprises the following steps:
d21, selecting target biological information and target environment information corresponding to a time period, and performing feature processing on the selected target biological information and the selected target environment information to obtain a first feature sequence of the target user in the selected time period;
d22, acquiring a first sample set carrying emotion category marking information from a second database, and determining a neighborhood of the target user in the selected time period based on the first sample set;
d23, extracting a preset number of samples from the neighborhood to obtain a second sample set, and obtaining a second characteristic sequence of each sample in the second sample set;
and D24, determining a target emotion category of the target user in the selected time period based on the first characteristic sequence and the second characteristic sequence.
The performing feature processing on the selected target biological information and the target environment information to obtain a first feature sequence of the target user in a selected time period includes:
e21, splicing all factors in the selected target biological information and the selected target environment information according to a preset sequence to obtain a characteristic factor sequence;
and E22, filling the product of the weight of each factor and the corresponding numerical value of the weight in the selected target biological information and the target environment information into the characteristic factor sequence to obtain a first characteristic sequence of the target user in the selected time period.
Said determining a neighborhood of the target user over the selected time period based on the first sample set comprises:
f21, determining a concentration threshold based on the electroencephalogram of each sample in the first sample set and the awakening degree in the emotion category marking information;
and F22, determining the neighborhood of the target user in the selected time period based on the concentration threshold.
The determining a target emotion category for the target user for the selected time period based on the first and second feature sequences comprises:
g21, calculating a first membership degree of each sample in the second sample set and each emotion category;
g22, calculating the similarity of the second characteristic sequence of each sample in the second sample set and the first characteristic sequence;
g23, determining second membership degrees of the first feature sequence and each emotion class based on the first membership degrees and the similarity degrees;
and G24, taking the emotion category with the maximum second membership as the target emotion category of the target user in the selected time period.
And the updating module 140 is configured to update the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information.
Updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information comprises:
h21, when the emotion recognition result in a certain specified time period is happy or relaxed, acquiring first product information browsed by the target user in the specified time period, and adding product information of the same type as the first product information in the initial product recommendation information to obtain target product recommendation information;
and H22, if the emotion recognition result in a certain specified time period is boring or disgusting, acquiring second product information browsed by the target user in the specified time period, reducing the product information of the same type as the second product information in the initial product recommendation information, and increasing the product information with low correlation degree with the second product information to obtain target product recommendation information.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a product recommendation method based on biometric information according to an embodiment of the present invention.
The electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a command set or stored in advance. The electronic device 1 may be a computer, or may be a single network server, a server group composed of a plurality of network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing, where cloud computing is one of distributed computing and is a super virtual computer composed of a group of loosely coupled computers.
In the present embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which are communicatively connected to each other through a system bus, wherein the memory 11 stores a product recommendation program 10, and the product recommendation program 10 is executable by the processor 12. While FIG. 3 shows only the electronic device 1 with the components 11-13 and the product recommendation program 10, those skilled in the art will appreciate that the configuration shown in FIG. 3 does not constitute a limitation of the electronic device 1, and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
The storage 11 includes a memory and at least one type of readable storage medium. The memory provides cache for the operation of the electronic equipment 1; the readable storage medium may be a storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the non-volatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk provided on the electronic device 1, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. In this embodiment, the readable storage medium of the memory 11 is generally used for storing an operating system and various application software installed in the electronic device 1, for example, codes of the product recommendation program 10 in an embodiment of the present invention. Further, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 12 is generally configured to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 12 is configured to run the program codes stored in the memory 11 or process data, such as running the product recommendation program 10.
The network interface 13 may comprise a wireless network interface or a wired network interface, and the network interface 13 is used for establishing a communication connection between the electronic device 1 and a client (not shown).
Optionally, the electronic device 1 may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The product recommendation program 10 stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when the processor 12 runs, the product recommendation method based on the biological information may be implemented, and specifically, the processor 12 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the product recommendation program 10, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or non-volatile. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM).
The computer-readable storage medium has stored thereon a product recommendation program 10, and the product recommendation program 10 is executable by one or more processors to implement the above-described biometric-information-based product recommendation method.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it will be obvious that the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the same, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (8)
1. A method for product recommendation based on biometric information, the method comprising:
responding to a product recommendation request aiming at a target user sent by a client, acquiring basic information of the target user from a first database, and constructing a user portrait of the target user based on the basic information of the target user;
inputting the user portrait of the target user into a product recommendation model to obtain initial product recommendation information corresponding to the target user, and sending the initial product recommendation information to a target terminal;
acquiring original biological information and original environment information of the target user when the target terminal browses the initial product recommendation information, and performing emotion recognition on the target user based on the original biological information and the original environment information;
updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information;
wherein the performing emotion recognition on the target user based on the original biological information and the original environmental information comprises:
splitting the original biological information and the original environmental information according to a preset time period to obtain biological information sets and environmental information sets corresponding to a plurality of time periods;
calculating the average value of each factor in each biological information set and each environmental information set to obtain target biological information and target environmental information corresponding to each time period;
performing emotion recognition based on the target biological information and the target environment information to obtain emotion recognition results of the target user in each time period, wherein the emotion recognition results comprise: selecting target biological information and target environment information corresponding to a time period, and performing feature processing on the selected target biological information and the selected target environment information to obtain a first feature sequence of the target user in the selected time period; acquiring a first sample set carrying emotion category marking information from a second database, and determining the neighborhood of the target user in the selected time period based on the first sample set; extracting a preset number of samples from the neighborhood to obtain a second sample set, and obtaining a second characteristic sequence of each sample in the second sample set; calculating a first membership degree of each sample in the second sample set and each emotion category, calculating a similarity degree of a second feature sequence of each sample in the second sample set and the first feature sequence, determining a second membership degree of the first feature sequence and each emotion category based on the first membership degree and the similarity degree, and taking the emotion category with the maximum second membership degree as a target emotion category of the target user in the selected time period;
wherein, the calculation formula of the neighborhood is as follows:
beta represents the concentration degree of the brain wave conversion of the target user in the selected time period, T up Represents the upper limit of concentration, T down Indicating a lower concentration limit.
2. The biometric-information-based product recommendation method of claim 1, wherein the original biometric information and the original environment information carry browsing time stamps.
3. The biometric-information-based product recommendation method of claim 1, wherein the emotion recognition result includes pleasure, relaxation, boredom, and the updating the initial product recommendation information based on the emotion recognition result to obtain the target product recommendation information comprises:
when the emotion recognition result of a certain specified time period is happy or relaxed, acquiring first product information browsed by the target user in the specified time period, and adding product information of the same type as the first product information in the initial product recommendation information to obtain target product recommendation information;
and if the emotion recognition result in a certain specified time period is boring or disgusting, acquiring second product information browsed by the target user in the specified time period, reducing the product information with the same type as the second product information in the initial product recommendation information, and adding product information with low correlation with the second product information to obtain target product recommendation information.
4. The method of claim 1, wherein the basic information comprises a plurality of index items and an index value corresponding to each of the plurality of index items, and wherein constructing the user representation of the target user based on the basic information of the target user comprises:
acquiring a mapping relation between the index value corresponding to each index item and the label from a third database;
determining target labels corresponding to all index items in the basic information of the target user based on the mapping relation;
and taking the set of target labels as a user representation of the target user.
5. The bioinformation-based product recommendation method according to claim 1, wherein the raw bioinformation includes information of skin impedance, skin temperature, blood pressure, blood oxygen, pulse, electrocardiogram and brain wave, and the raw environmental information includes information of GPS location, ambient temperature, ambient humidity and ambient brightness.
6. A product recommendation apparatus based on biometric information, the apparatus comprising:
the system comprises a construction module, a first database and a second database, wherein the construction module is used for responding to a product recommendation request aiming at a target user sent by a client, acquiring basic information of the target user from the first database, and constructing a user portrait of the target user based on the basic information of the target user;
the sending module is used for inputting the user portrait of the target user into a product recommendation model to obtain initial product recommendation information corresponding to the target user, and sending the initial product recommendation information to a target terminal;
the identification module is used for acquiring original biological information and original environment information of the target user when the target terminal browses the initial product recommendation information, and performing emotion identification on the target user based on the original biological information and the original environment information;
the updating module is used for updating the initial product recommendation information based on the emotion recognition result to obtain target product recommendation information;
wherein the performing emotion recognition on the target user based on the original biological information and the original environmental information comprises:
splitting the original biological information and the original environment information according to a preset time period to obtain biological information sets and environment information sets corresponding to a plurality of time periods;
calculating the average value of each factor in each biological information set and each environmental information set to obtain target biological information and target environmental information corresponding to each time period;
performing emotion recognition based on the target biological information and the target environment information to obtain emotion recognition results of the target user in each time period, wherein the emotion recognition results comprise: selecting target biological information and target environment information corresponding to a time period, and performing feature processing on the selected target biological information and the selected target environment information to obtain a first feature sequence of the target user in the selected time period; acquiring a first sample set carrying emotion category marking information from a second database, and determining the neighborhood of the target user in the selected time period based on the first sample set; extracting a preset number of samples from the neighborhood to obtain a second sample set, and acquiring a second characteristic sequence of each sample in the second sample set; calculating a first membership degree of each sample in the second sample set and each emotion category, calculating a similarity degree of a second feature sequence of each sample in the second sample set and the first feature sequence, determining a second membership degree of the first feature sequence and each emotion category based on the first membership degree and the similarity degree, and taking the emotion category with the maximum second membership degree as a target emotion category of the target user in the selected time period;
wherein, the calculation formula of the neighborhood is as follows:
beta represents the concentration degree obtained by the brain wave conversion of the target user in the selected time period, T up Represents the upper limit of concentration, T down Indicating the lower concentration limit.
7. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a product recommendation program executable by the at least one processor to enable the at least one processor to perform the biometric-information-based product recommendation method of any one of claims 1-5.
8. A computer-readable storage medium having a product recommendation program stored thereon, the product recommendation program being executable by one or more processors to implement the biological information based product recommendation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110701968.7A CN113435970B (en) | 2021-06-23 | 2021-06-23 | Product recommendation method and device based on biological information, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110701968.7A CN113435970B (en) | 2021-06-23 | 2021-06-23 | Product recommendation method and device based on biological information, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113435970A CN113435970A (en) | 2021-09-24 |
| CN113435970B true CN113435970B (en) | 2023-02-28 |
Family
ID=77753744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110701968.7A Active CN113435970B (en) | 2021-06-23 | 2021-06-23 | Product recommendation method and device based on biological information, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113435970B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113946752A (en) * | 2021-10-28 | 2022-01-18 | 平安银行股份有限公司 | Financial product recommendation method, device, equipment and storage medium based on big data |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016085409A1 (en) * | 2014-11-24 | 2016-06-02 | Agency For Science, Technology And Research | A method and system for sentiment classification and emotion classification |
| CN108154398A (en) * | 2017-12-27 | 2018-06-12 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
| CN110046540A (en) * | 2018-12-29 | 2019-07-23 | 广州二元科技有限公司 | A method of user emotion is judged according to browsing history and Expression Recognition |
| CN112330400A (en) * | 2020-11-02 | 2021-02-05 | 泰康保险集团股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
| CN112581230A (en) * | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332263B (en) * | 2011-09-23 | 2012-11-07 | 浙江大学 | Close neighbor principle based speaker recognition method for synthesizing emotional model |
| US11636365B2 (en) * | 2018-09-13 | 2023-04-25 | International Business Machines Corporation | State of emotion time series |
-
2021
- 2021-06-23 CN CN202110701968.7A patent/CN113435970B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016085409A1 (en) * | 2014-11-24 | 2016-06-02 | Agency For Science, Technology And Research | A method and system for sentiment classification and emotion classification |
| CN108154398A (en) * | 2017-12-27 | 2018-06-12 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
| CN110046540A (en) * | 2018-12-29 | 2019-07-23 | 广州二元科技有限公司 | A method of user emotion is judged according to browsing history and Expression Recognition |
| CN112330400A (en) * | 2020-11-02 | 2021-02-05 | 泰康保险集团股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
| CN112581230A (en) * | 2020-12-24 | 2021-03-30 | 安徽航天信息科技有限公司 | Commodity recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113435970A (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022141861A1 (en) | Emotion classification method and apparatus, electronic device, and storage medium | |
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| WO2019095417A1 (en) | Real-time advertisement recommendation method and apparatus, and terminal device and storage medium | |
| CN113435970B (en) | Product recommendation method and device based on biological information, electronic equipment and medium | |
| US20140278939A1 (en) | Advertisement extraction device and advertisement extraction method | |
| CN106095842B (en) | Online course searching method and device | |
| WO2021114936A1 (en) | Information recommendation method and apparatus, electronic device and computer readable storage medium | |
| CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
| CN110727860A (en) | User portrait method, device, equipment and medium based on internet beauty platform | |
| CN111666415A (en) | Topic clustering method and device, electronic equipment and storage medium | |
| CN115048583A (en) | Information pushing method, system, equipment and storage medium based on user portrait | |
| CN115659008B (en) | Information pushing system, method, electronic equipment and medium for big data information feedback | |
| CN113836131A (en) | Big data cleaning method and device, computer equipment and storage medium | |
| CN107809370B (en) | User recommendation method and device | |
| CN112507230B (en) | Webpage recommendation method and device based on browser, electronic equipment and storage medium | |
| CN113051480A (en) | Resource pushing method and device, electronic equipment and storage medium | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN114862520A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN111696656A (en) | Doctor evaluation method and device of Internet medical platform | |
| CN113706253A (en) | Real-time product recommendation method and device, electronic equipment and readable storage medium | |
| CN114706985A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN114398560A (en) | Marketing interface setting method, device, equipment and medium based on WEB platform | |
| CN111403011B (en) | Registration department pushing method, device and system, electronic equipment and storage medium | |
| CN109948040A (en) | Storage, recommended method and the system of object information, equipment and storage medium | |
| CN113254623B (en) | Data processing method, device, server, medium and product |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |