CN113469773A - Intelligent terminal and object recommendation method - Google Patents
Intelligent terminal and object recommendation method Download PDFInfo
- Publication number
- CN113469773A CN113469773A CN202010506756.9A CN202010506756A CN113469773A CN 113469773 A CN113469773 A CN 113469773A CN 202010506756 A CN202010506756 A CN 202010506756A CN 113469773 A CN113469773 A CN 113469773A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- target user
- transaction
- target
- 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 34
- 238000012545 processing Methods 0.000 claims description 37
- 230000009467 reduction Effects 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 12
- 238000004590 computer program Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 239000002453 shampoo Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000013585 weight reducing agent Substances 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
Abstract
The application provides an intelligent terminal and an object recommendation method, relates to the technical field of intelligent home, and aims to improve object recommendation accuracy. The method comprises the steps that at least one user set to which a target user belongs is determined from a plurality of user sets which are constructed in advance, wherein the user sets are constructed according to object features of user transaction objects on a plurality of transaction platforms, and the user sets comprise users of the same type and user features determined according to the objects corresponding to the users; determining users similar to the target user in at least one user set to which the target user belongs according to the user characteristics of the target user; and recommending the target user according to the user transaction record of the user similar to the target user. And object recommendation is performed for the target user according to the objects of the users similar to the target user in the plurality of trading platforms, so that the object recommendation accuracy is improved.
Description
Technical Field
The application relates to the technical field of intelligent home furnishing, and provides an intelligent terminal and an object recommendation method.
Background
When a user carries out object transaction on a certain transaction platform, the transaction platform records transaction information of the user, determines the preference of the user according to the transaction information, and recommends an object for the user according to the preference of the user when the user carries out transaction on the transaction platform again. However, the current terminal for object recommendation to the user cannot master the transaction records of the user on all transaction platforms, and can only recommend the user according to the transaction records of the user on the current transaction platform, so that the accuracy rate of object recommendation to the user is low.
And because of the privacy protection of the user data, the data of the user transaction records on each transaction platform can not be intercommunicated, even if the data interaction of the user transaction records is carried out under a safe mode or protocol, the interaction is carried out one by one, which can damage the real-time performance of the recommendation and can not accurately recommend the user.
In summary, at present, there is no technical scheme for accurately recommending objects for users according to the objects in the user transaction records in the multi-transaction platform.
Disclosure of Invention
The embodiment of the application provides an intelligent terminal and an object recommendation method, which are applied to a scene of an intelligent home and used for recommending objects for a user according to the objects in user transaction records in a plurality of fused transaction platforms under the condition of protecting privacy information of the user, so that the object recommendation accuracy is improved.
In a first aspect, an embodiment of the present application provides an intelligent terminal, where the terminal includes: communication unit, memory, processor and display element, wherein:
a communication unit for communicating with at least one server;
a memory for storing software programs and data used in operation;
the processor is used for determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, wherein the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms; in at least one target user set, determining users similar to the target user; and recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
And the display unit is used for displaying the recommended objects.
The intelligent terminal can acquire objects in user transaction records on a plurality of transaction platforms, allocate corresponding users to different user sets according to object characteristics of the objects, find at least one target user set to which a target user belongs in the plurality of user sets, and determine users similar to the target user in the at least one target user set to which the target user belongs; recommending an object for the target user according to the object in the user transaction record of the user similar to the target user; according to the method and the device, the objects in the user transaction records on the multiple transaction platforms are fused, object recommendation is carried out on the target user according to the objects in the user transaction records of the users similar to the target user, accuracy of object recommendation is improved, when the objects in the user transaction records on the multiple transaction platforms are obtained, privacy information of the users cannot be obtained, only the object information of the user transaction records is obtained, and privacy safety of the users is guaranteed.
In one possible implementation, the processor is specifically configured to:
aiming at any target user set, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than the first preset value as the users similar to the target user.
The intelligent terminal further provides a technical scheme for determining the users similar to the target user in the target user set to which the target user belongs, according to the similarity between the object features corresponding to the users, the users with the similarity value larger than the preset value are used as the users similar to the target user, the accuracy of determining the users similar to the target user is improved, and the similarity of the users is further ensured, so that when object recommendation is performed according to the objects in the user transaction records of the similar users, the object recommendation is more accurately performed for the target user.
In one possible implementation, the processor constructs the plurality of user sets by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and according to the object characteristics of the objects in the user transaction records, setting the users with the object characteristic similarity larger than a second preset value in the same user set, wherein the second preset value is smaller than or equal to the first preset value.
The intelligent terminal provides a technical scheme for constructing the user set, specifically allocates users with similar object characteristics to the same user set according to the object characteristics, so that when object recommendation is performed, recommendation can be performed for a target user according to objects in user transaction records of the users with similar object characteristics, and accuracy of object recommendation is guaranteed.
In one possible implementation, the processor is further configured to:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than the dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, signature processing is carried out to obtain the object characteristics after the dimension reduction, and the users with the object characteristic similarity larger than a second preset value are arranged in the same user set according to the object characteristics after the dimension reduction.
According to the intelligent terminal, when the dimension of the object feature of the object in the user transaction record is determined to be high, the user set is set for the user according to the object feature, the process is complex, dimension reduction processing is carried out on the object feature in order to reduce processing difficulty, and the specific dimension reduction processing mode is given so that the user set can be set for the user quickly and accurately according to the object feature after dimension reduction processing.
In one possible implementation, the processor is further configured to:
after a plurality of user sets are built, aiming at any user set, the built user sets are corrected according to the similarity between the object features corresponding to the users in the user sets.
After a plurality of user sets are established, the intelligent terminal also determines the similarity between the object features in the user sets according to the object features corresponding to the users in the user sets, and corrects the user sets according to the similarity result so as to ensure the similarity between the objects corresponding to the users in the same user set, and further is more accurate when object recommendation is carried out according to the objects in the user sets as target objects.
In a second aspect, the present application provides a method for object recommendation, the method comprising:
determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, wherein the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms;
in at least one target user set, determining users similar to the target user;
and recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
In one possible implementation manner, determining users similar to the target user in at least one target user set includes:
aiming at any target user set, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than the first preset value as the users similar to the target user.
In one possible implementation, the plurality of user sets are constructed by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and according to the object characteristics of the objects in the user transaction records, setting the users with the object characteristic similarity larger than a second preset value in the same user set, wherein the second preset value is smaller than or equal to the first preset value.
In a possible implementation manner, before setting, according to the object features of the objects in the user transaction record, the user whose object feature similarity is greater than the second preset value in the same user set, the method further includes:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than the dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, signature processing is carried out to obtain the object features after the dimension reduction.
In a possible implementation manner, after constructing the plurality of user sets, the method further includes:
and aiming at any user set, correcting the constructed multiple user sets according to the similarity between the object features corresponding to the users in the user sets.
In a third aspect, an embodiment of the present application provides an apparatus for object recommendation, where the apparatus includes:
the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, and the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms;
a second determining module, configured to determine, in the at least one user set, users similar to the target user;
and the recommending module is used for recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the object recommendation method are implemented.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent terminal according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of another intelligent terminal provided in the embodiment of the present application;
fig. 4 is a flowchart of an object recommendation method according to an embodiment of the present application;
FIG. 5 is a diagram illustrating a set of users provided by an embodiment of the present application;
fig. 6 is a schematic diagram of performing dimension reduction processing on object features according to an embodiment of the present disclosure;
FIG. 7 is a flowchart of an overall method for object recommendation provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an object recommendation device according to an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solution and advantages of the present application more clearly and clearly understood, the technical solution in the embodiments of the present application will be described below in detail and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
In the embodiments of the present application, the word "exemplary" is used to mean "serving as an example, embodiment, or illustration. Any embodiment described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
The terms "first" and "second" are used herein for descriptive purposes only and are 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 one or more of that feature, and in the description of embodiments of the application, unless stated otherwise, "plurality" means two or more.
In order to solve the problems that in the prior art, due to protection of user privacy information, objects in user transaction records in multiple transaction platforms cannot be fused, and when object recommendation is performed on a target user, object recommendation can only be performed on the target user according to the target user transaction record recorded by the transaction platform where the target user is currently located, so that the object recommended for the target user is not accurate enough, the embodiment of the application provides an intelligent terminal and an object recommendation method.
In order to better understand the technical solution provided by the embodiment of the present application, some brief descriptions are provided below for application scenarios to which the technical solution provided by the embodiment of the present application is applicable, and it should be noted that the application scenarios described below are only used for illustrating the embodiment of the present application and are not limited. In specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to needs.
As shown in fig. 1, an application scenario provided in the embodiment of the present application is shown in fig. 1, where the application scenario includes a plurality of servers 100 and an intelligent terminal 110. The application scene can be a home scene, an office scene and the like.
The plurality of servers 100 are background servers corresponding to the plurality of trading platforms and are used for storing user trading records of different users in the trading platforms; the intelligent terminal 110 is an intelligent terminal capable of installing or operating a transaction platform; in application, the server 100 is communicatively connected to the intelligent terminal 110 through a network, which may be, but is not limited to, a local area network, a metropolitan area network, or a wide area network.
At present, due to a user privacy information protection mechanism, data in a plurality of trading platforms are not intercommunicated, and the intelligent terminal 110 cannot master the trading records of a user on all trading platforms, so that the intelligent terminal 110 can only recommend an object for the user according to the historical trading records in the trading platform where the user is currently located when the user recommends the object after acquiring the trading requirements of the user, so that limitation is caused when the user recommends the object, and the accuracy of the recommended object is reduced.
The intelligent terminal 110 provided by the present application may obtain and store objects in the user transaction records stored in the server 100 corresponding to the multiple transaction platforms, and at this time, only obtain the objects in the user transaction records in the multiple transaction platforms, and do not obtain corresponding user privacy information. Therefore, when recommending an object for a target user, the intelligent terminal 110 may recommend the object for the target user according to the objects acquired and stored from the servers 100 corresponding to the multiple trading platforms;
in one possible implementation, the object recommendations include, but are not limited to: goods recommendations (e.g., clothes recommendations, shoes recommendations, food recommendations, household items recommendations, etc.), service recommendations (e.g., home services recommendations, family education recommendations, courier services, etc.).
Taking the intelligent terminal 110 as an example in a home scene, for example, the intelligent terminal 110 finds that shampoo needs to be purchased through linkage of intelligent home devices, at this time, the intelligent terminal 110 determines shampoo historical transaction records according to user transaction records acquired and stored from the servers 100 corresponding to the multiple transaction platforms, and recommends shampoo for the user according to the shampoo historical transaction records, so as to recommend a specific object.
Certainly, the intelligent terminal 110 may also recommend an object of the same type as the object included in the search instruction to the user according to the search instruction input by the user in the search box of the trading platform display interface, so as to implement recommendation of a specific object; or
When a user starts a certain transaction platform but does not input a search instruction, the intelligent terminal 110 determines that the user has a transaction demand, and recommends an object for the user according to the object in the user transaction record acquired from the server 100 corresponding to the multiple transaction platforms, where the recommended object includes different types of objects.
In a possible implementation manner, after the objects in the user transaction records are obtained, the intelligent terminal 110 allocates the users corresponding to the user transaction records to different user sets according to the object features of the objects in each user transaction record, so as to ensure that the object features corresponding to the users in the same user set are similar. Therefore, when object recommendation is performed, objects in user transaction records of similar users are preferably recommended.
The intelligent terminal in the embodiment of the application can acquire the objects in the user transaction records in the transaction platforms, only the objects in the user transaction records are acquired at the moment, the privacy information of the user does not need to be acquired, and the privacy protection effect is achieved; corresponding users are classified into different user sets according to the object characteristics of the objects in the user transaction records, so that the object characteristics corresponding to the users in each user set are ensured to be similar, namely the users in the user sets are all similar users; and further determining alternative users except the target user in the target user set, selecting similar users more similar to the target user according to the object characteristics corresponding to the alternative users and the object characteristics corresponding to the target user, and recommending the object for the target user according to the object in the user transaction records of the similar users. When the target user is recommended, the objects corresponding to the user transaction records on the transaction platforms can be fused, object recommendation is performed on the target user according to the objects in the user transaction records of the similar users, and the recommendation accuracy is improved.
The following describes the intelligent terminal provided in the embodiment of the present application in detail.
Fig. 2 is a schematic structural diagram of an intelligent terminal 110 according to an embodiment of the present disclosure. The intelligent terminal 110 includes a communication unit 111, a memory 112, a processor 113 and a display unit 114, wherein:
a communication unit 111 for communicating with at least one server;
a memory 112 for storing software programs and data used in operation;
the processor 113 is used for determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, wherein the user sets are constructed according to object characteristics of objects in user transaction records on a plurality of transaction platforms; in at least one target user set, determining users similar to the target user; recommending an object for the target user according to the object in the user transaction record of the user similar to the target user;
and a display unit 114 for displaying the recommended object.
In one possible implementation, the processor 113 is specifically configured to:
aiming at any target user set to which a target user belongs, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than the first preset value as the users similar to the target user.
In one possible implementation, the processor 113 constructs the plurality of user sets by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and according to the object characteristics of the objects in the user transaction records, setting the users with the object characteristic similarity larger than a second preset value in the same user set, wherein the second preset value is smaller than or equal to the first preset value.
In one possible implementation, the processor 113 is further configured to:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than the dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, signature processing is carried out to obtain the object characteristics after the dimension reduction, and the users with the object characteristic similarity larger than a second preset value are arranged in the same user set according to the object characteristics after the dimension reduction.
In one possible implementation, the processor 113 is further configured to:
after a plurality of user sets are built, aiming at any user set, the built user sets are corrected according to the similarity between the object features corresponding to the users in the user sets.
It should be understood that the intelligent terminal 110 shown in fig. 2 is only one example. The smart terminal 110 provided in the present application may have more components than those shown in fig. 2, may combine two or more components, or may have a different configuration of components, in addition to the above-described structure.
Fig. 3 is a schematic structural diagram of another intelligent terminal 110 provided in the embodiment of the present application; the various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.
A block diagram of a hardware configuration of the smart terminal 110 according to an exemplary embodiment is exemplarily shown in fig. 3. As shown in fig. 3, the smart terminal 110 further includes: radio Frequency (RF) circuit 114, camera 115, sensor 116, audio circuit 117, Wireless Fidelity (Wi-Fi) module 118, bluetooth module 119, and power supply 120.
The RF circuit 114 may be used for receiving and transmitting signals during information transmission and reception or during a call, and may receive downlink data of a base station and then send the downlink data to the processor 113 for processing; the uplink data may be transmitted to the base station. In general, the RF circuitry 114 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
The memory 112 may be used to store software programs and data used during runtime. The memory 112 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. The memory 112 stores an operating system that enables the smart terminal 110 to operate. The memory 112 may store an operating system and various application programs, and may also store codes for executing the object recommendation method according to the embodiment of the present application.
The processor 113 executes various functions of the smart terminal 110 and data processing, such as methods recommended by the subject in the present application, by executing software programs stored in the memory 112 or data used in the execution.
The display unit 114 may be used to receive input numeric or character information and generate signal input related to user settings and function control of the smart terminal 110, and particularly, the display unit 114 may include a touch screen 1141 disposed on the front surface of the smart terminal 110 and configured to collect touch operations of a user thereon or nearby, such as clicking a button, dragging a scroll box, and the like.
The display unit 114 may also be used to display a Graphical User Interface (GUI) of information input by or provided to the user and various menus of the smart terminal 110. Specifically, the display unit 114 may include a display screen 1142 disposed on the front surface of the smart terminal 110. The display screen 1142 may be configured in the form of a liquid crystal display unit, a light emitting diode, or the like. The display unit 114 may display the recommended object of the present application through the display screen 142.
The touch screen 1141 may cover the display screen 1142, or the touch screen 1141 and the display screen 1142 may be integrated to implement the input and output functions of the intelligent terminal 110, and the integrated touch screen may be referred to as a touch display screen for short. The display unit 114 can display the application programs and the corresponding operation steps.
The camera 115 may be used to capture still images or video. The object generates an optical image through the lens and projects the optical image to the photosensitive element. The photosensitive element may be a Charge Coupled Device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The light sensing elements convert the light signals into electrical signals which are then passed to the processor 113 for conversion into digital image signals.
The smart terminal 110 may also include at least one sensor 116, such as an acceleration sensor 1161, a distance sensor 1162, a fingerprint sensor 1163, and a temperature sensor 1164. The smart terminal 110 may also be configured with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, light sensors, motion sensors, and the like.
The audio circuitry 117, speaker 1171, microphone 1172 can provide an audio interface between a user and the smart terminal 110. The audio circuit 117 may transmit the electrical signal converted from the received audio data to the speaker 1171, and convert the electrical signal into an audio signal by the speaker 1171 for output. The smart terminal 110 may also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 1172 converts the collected sound signals into electrical signals, converts the electrical signals into audio data after being received by the audio circuit 117, and then outputs the audio data to the RF circuit 114 to be transmitted to, for example, another terminal, or outputs the audio data to the memory 112 for further processing. The microphone 1172 of the present application can capture the user's voice.
Wi-Fi belongs to short-distance wireless transmission technology, and the intelligent terminal 110 can help a user to send and receive e-mails, browse webpages, access streaming media and the like through the Wi-Fi module 118, and provides wireless broadband internet access for the user.
The processor 113 is a control center of the intelligent terminal 110, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the intelligent terminal 110 and processes data by running or executing software programs stored in the memory 112 and calling data stored in the memory 112. In some embodiments, processor 113 may include one or more processing units; the processor 113 may also integrate an application processor, which mainly handles operating systems, user interfaces, applications, etc., and a baseband processor, which mainly handles wireless communications. It will be appreciated that the baseband processor described above may not be integrated into the processor 113. In the present application, the processor 113 may run an operating system, an application program, a user interface display, a touch response, and a processing method according to the embodiments of the present application. In addition, the processor 113 is coupled with the input unit 130 and the display unit 114.
And the Bluetooth module 119 is used for performing information interaction with other Bluetooth devices with Bluetooth modules through a Bluetooth protocol. For example, the smart terminal 110 may establish a bluetooth connection with a wearable electronic device (e.g., a smart watch) having a bluetooth module via the bluetooth module 181, so as to perform data interaction.
The smart terminal 110 also includes a power source 120 (such as a battery) to power the various components. The power supply may be logically connected to the processor 113 through a power management system to manage charging, discharging, and power consumption functions through the power management system. The intelligent terminal 110 may also be configured with a power button for powering on and off the terminal, and locking the screen.
The following describes in detail a specific implementation of the intelligent terminal 110 in the present application for object recommendation for a target user.
As shown in fig. 4, a flowchart of an object recommendation method provided in the embodiment of the present application is applied to the intelligent terminal 110 of the present application, and includes the following steps:
In the application, a plurality of user sets are constructed by the intelligent terminal according to the object characteristics of the objects in the user transaction records returned by the servers of a plurality of transaction platforms.
Therefore, the intelligent terminal of the application initiates collaborative recommendation requests to the servers of the multiple trading platforms, receives each server receiving the collaborative recommendation request, and returns the objects in the returned user trading records, namely all users trading on the trading platform a and all trading objects corresponding to all users after the server corresponding to a certain trading platform a receives the collaborative recommendation request.
For example, there are 10 users who have transacted on the transaction platform a. The number of times that the user 1 conducts transactions on the transaction platform A is 15, and the object of each transaction in the 15 transactions is recorded; the number of times of transaction of the user 2 on the transaction platform A is 18, and the object of each transaction in the 18 transactions is recorded; determining the transaction times of each user on the transaction platform A and the object of each transaction by analogy; at this time, the server corresponding to the trading platform a returns all the objects traded by 10 users on the trading platform to the intelligent terminal.
The server of the trading platform stores the trading records of all users who trade on the trading platform corresponding to the server, and the trading records include but are not limited to: time of transaction, object of transaction, etc.
The object characteristics are used for identifying the object, so that when the intelligent terminal acquires the object of the user transaction record, the intelligent terminal acquires the object characteristics of the object of the user transaction record.
In the application, when receiving objects in user transaction records sent by different transaction platforms, the intelligent terminal receives the objects in an object set form, and each object set represents a set of all objects of a user for transaction on a certain transaction platform;
for example, an object set 1 returned by a server corresponding to the trading platform a represents a set of all objects traded by the user 1 on the trading platform a, that is, the object set 1 includes all objects traded by the user 1 on the trading platform a; the object set 2 returned by the server corresponding to the trading platform B represents a set of all objects traded by the user 2 on the trading platform B, that is, the object set 2 includes all objects traded by the user 2 on the trading platform B. The user 1 and the user 2 may be the same user (i.e. the same user is a certain user who carries out a transaction on the transaction platform a and the transaction platform B), or may be different users (i.e. the user is a certain user who carries out a transaction on the transaction platform a, and the user is a certain user who carries out a transaction on the transaction platform B).
In the application, even if the user 1 and the user 2 are the same user, the intelligent terminal can treat the user 1 and the user 2 as different users, namely treat the user 1 and the user 2 as two users, and treat the users according to the object characteristics of transaction objects of the users on the transaction platform A and the transaction platform B to determine whether the users are similar users or non-similar users.
The intelligent terminal puts the received object aggregates returned by the trading platforms into the same storage pool S, so that the storage pool S contains a plurality of object aggregates.
For example, the storage pool S ═ { S1(u), S2(u), S3(u) … … sm (u) }, where S1(u) represents an object set corresponding to a transaction record of a user returned by a server of a certain transaction platform, so S1 may be used to represent a user, u represents a user vector of the user, and if u ═ is (b1, b2 … … bt), it represents that the user is a t-dimensional vector, where bt represents a transaction object of the user.
Taking the transaction platform as a commodity purchase transaction platform as an example, at this time, the object set S1 represents all commodities that the user 1 purchased on the commodity purchase transaction platform, and it should be noted that the user 1 represents only an unknown user and cannot be specifically limited to a specific user determined by privacy information such as an account number/a mobile phone number of the user.
The intelligent terminal constructs a plurality of user sets according to the plurality of object sets stored in the storage pool S, namely, the intelligent terminal distributes users corresponding to the object sets with similar object characteristics to the same user set according to the object characteristics of the objects in the object sets.
For example, the object characteristics of the objects in the object set S1 are similar to the object characteristics of the objects in the object set S3, and the users corresponding to the object set S1 and the users corresponding to the object set S3 are assigned to the same user set.
Specifically, in the present application, a hash function is used to allocate users corresponding to a plurality of object collections included in the storage pool S to different user collections.
The hash function is:
Fid＝0.618*2n
wherein u is the object feature vector of the object in the user transaction record corresponding to the object set Sm, decimal (u) is the data obtained by decimal the object feature vector of the object in the user transaction record corresponding to the corresponding set Sm, and m and n are target integer digits.
Assuming that n is 32, Sm (decimal (u) × 2654435769 > 28) mod16, where the hash conforms to the fibonacci hash, a more uniform hash distribution can be obtained than the remainder hash distribution.
For example, if m is 1, the above formula will be S1 ═ (decimal (u) × 2654435769 > 28) mod16, where decimal (u) is a known number obtained by decimal data of the object feature vector of the object in the user transaction record corresponding to the set S1. Assuming that S1 is determined to be 0 by the above formula, it is determined that the user corresponding to S1 is located in the user set corresponding to index 0.
Therefore, through the above hash function, the user corresponding to each object set is hashed into one of 0-15 index partitions or storage locations, and a user set diagram as shown in fig. 5 is formed.
It should be noted that each index partition or storage location corresponds to a user set, and 0-15 index partitions or storage locations are only exemplary.
It should be noted that the similarity between the object features corresponding to the users in the same user set is greater than the second preset value.
In a possible implementation manner, when determining which user set the user corresponding to the object set belongs to according to the object features in the object set, if the dimension of the object features is too high, before determining which user set the corresponding user belongs to according to the object features in the object set, dimension reduction processing needs to be further performed on the object features in the object set.
Fig. 6 is a schematic diagram of performing dimension reduction processing on object features according to an embodiment of the present application.
Fig. 6 shows that W objects are included in the object set, and each object has its own object feature, which is object feature 1 and object feature 2 … …, respectively.
First, each object feature is converted into a hash value by a hash algorithm, e.g., object feature 1 is converted into 1010101 by a hash algorithm, and object feature W is converted into 0011111 by a hash algorithm.
Further, the hash value generated after conversion is weighted to represent other factors of different objects, such as shipment volume, popularity, promotion strength and the like.
In the application, a product algorithm of a hash feature matrix and a weight matrix is adopted for weighting processing.
The product algorithm of the Hash characteristic matrix and the weight matrix is as follows:
where w represents a weight given by the weight and hash value represents a result value obtained by the multiplication algorithm.
And finally, respectively adding all the column values of the features after the weight reduction, and performing signature processing to obtain a signature value of the object set.
In the present application, a formula is used for signature processing
And performing, wherein sum _ sequnce is a result value of summation of characteristic column values.
And after the signature value of the object set is obtained, distributing the user corresponding to the object set to the user set by adopting the hash function according to the signature value of the object characteristic.
In the application, after the intelligent terminal determines the user set for the users corresponding to the object set according to the object characteristics of the objects in the object set returned by the servers of the multiple transaction platforms in the manner described above, the constructed user set can be corrected.
Specifically, the correction method of the present application is performed based on the constructed user sets, and the object features corresponding to the users in each user set are compared in similarity, and the user set of the user is determined again according to the object features of the object set of the user for the user with a large deviation of the similarity value.
In the application, the similarity between the object features is calculated by adopting the hamming distance, and the specific calculation formula is as follows:
Hamming_distance＝Count1(Xor(Si,Sx))
wherein Hamming _ distance represents the similarity between object features, Count1(Xor(Si,Sx) Function represents the input judgment in bits, Xor (S)i,Sx) For an XOR function, pair SiAnd SxCarry out bitwise XOR, SiAnd SxSignatures for the ith and xth users, respectively.
It needs to be noted that the user set in the application may be updated periodically, or when it is determined that the user has a need, the multi-transaction platform collaborative recommendation request may be triggered, and the update may be performed according to the object characteristics of the object in the user transaction record returned by the multi-transaction platform.
And step 410, determining users similar to the target user in at least one target user set to which the target user belongs.
As shown in the user set diagram of fig. 5, a total of 16 user sets, which are respectively the user set 0-the user set 15, each user set includes a plurality of users, and it is assumed that the target user is a user corresponding to S1, and the target user set to which the target user belongs is the user set 0.
Because the same user in the user set may correspond to different object sets, the same user may also be located in different user sets. Therefore, the target user may also be the user corresponding to S7, that is, the user corresponding to S1 and the user corresponding to S7 are both target users, and S1 and S7 may be sets of objects in user transaction records of the target users on different transaction platforms.
Therefore, the target user sets to which the target users belong are the user set 0 and the user set 2.
At this time, for the users in the user set 0 and the user set 2, according to the similarity between the object feature corresponding to the target user and the object feature corresponding to the alternative user in the user set, the user similar to the target user is determined, wherein the object feature corresponding to the target user is calculated by the intelligent terminal according to the object in the collected and recorded relevant transaction record of the target user, and the like.
In the application, the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users in the user set is calculated in a cosine distance calculation mode, and the alternative users corresponding to the similarity values larger than the first preset value are used as the users similar to the target user.
In the present application, a user similar to a target user is specifically determined by the following formula:
for i in (1, n): selecting an alternative user from the user set, wherein when i is 3, the alternative user is the user corresponding to the S3;
score＝similarity(Star(u)，Si(u)), calculating the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users, wherein score represents the similarity value between the object features, Star(u) object characteristics corresponding to the target user, Si(u) representing object features corresponding to the alternative users;
if score > threshold, comparing the similarity value with a first preset value, and if the similarity value is greater than or equal to the first preset value, determining that the alternative user is a user similar to the target user;
else selects other user sets to which the target user belongs and jumps to the for loop.
And step 420, recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
In the method and the device, after the user similar to the target user is determined, object recommendation is performed on the target user according to the object in the object set corresponding to the transaction record of the determined similar user.
When object recommendation is carried out, objects corresponding to similar users can be screened according to the requirements of the users, and only objects which belong to the same type as the objects required by the users are selected.
In a possible implementation manner, when object recommendation is performed for a target user, the objects may also be ranked and recommended for the target user according to the ranking order.
As shown in fig. 7, an overall method flowchart for object recommendation provided in the embodiment of the present application includes the following steps:
And 703, performing dimension reduction processing on the object features to obtain the object features after the dimension reduction processing.
And step 707, recommending the object for the target user according to the object in the user transaction record corresponding to the user similar to the target user.
Based on the same inventive concept, the embodiment of the invention also provides an object recommendation device, and as the device is a device for implementing the object recommendation method of the application, and the principle of the device for solving the problem is similar to the method, the implementation of the device can refer to the implementation of the method, and repeated parts are not described again.
As shown in fig. 8, a structure diagram of an object recommendation apparatus provided in an embodiment of the present application, the object recommendation apparatus 800 includes a first determining module 801, a second determining module 802, and a recommending module 803, where:
a first determining module 801, configured to determine at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, where the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms;
a second determining module 802, configured to determine, in at least one target user set to which a target user belongs, users similar to the target user;
and the recommending module 803 is used for recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
In a possible implementation manner, the second determining module 802 is specifically configured to:
aiming at any target user set to which a target user belongs, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than the first preset value as the users similar to the target user.
In one possible implementation, the first determining module 801 constructs the plurality of user sets by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and according to the object characteristics of the objects in the user transaction records, setting the users with the object characteristic similarity larger than a second preset value in the same user set, wherein the second preset value is smaller than or equal to the first preset value.
In one possible implementation, the first determining module 801 is further configured to:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than the dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, signature processing is carried out to obtain the object characteristics after the dimension reduction, and the users with the object characteristic similarity larger than a second preset value are arranged in the same user set according to the object characteristics after the dimension reduction.
In one possible implementation, the first determining module 801 is further configured to:
after a plurality of user sets are built, aiming at any user set, the built user sets are corrected according to the similarity between the object features corresponding to the users in the user sets.
An embodiment of the present application further provides a computer-readable non-volatile storage medium, which includes program code, when the program code runs on a terminal only, the program code is configured to enable an intelligent terminal to execute any one of the steps of the object recommendation method.
The present application is described above with reference to block diagrams and/or flowchart illustrations of methods, apparatus (systems) and/or computer program products according to embodiments of the application. It will be understood that one block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, and/or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and/or other programmable data processing apparatus, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.
Accordingly, the subject application may also be embodied in hardware and/or in software (including firmware, resident software, micro-code, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. In the context of this application, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. The utility model provides an intelligent terminal, its characterized in that, this intelligent terminal includes: communication unit, memory, processor and display element, wherein:
the communication unit is used for communicating with at least one server;
the memory is used for storing software programs and data used in operation;
the processor is used for determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, wherein the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms; in the at least one target user set, determining users similar to the target user; recommending an object for the target user according to the object in the user transaction record of the user similar to the target user;
the display unit is used for displaying the recommended object.
2. The intelligent terminal of claim 1, wherein the processor is specifically configured to:
aiming at any target user set, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than a first preset value as the users similar to the target user.
3. The intelligent terminal of claim 1, wherein the processor constructs the plurality of user sets by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and setting users with object feature similarity larger than a second preset value in the same user set according to the object features of the objects in the user transaction records, wherein the second preset value is smaller than or equal to the first preset value.
4. The intelligent terminal of claim 3, wherein the processor is further configured to:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than a dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, performing signature processing to obtain the object characteristics after the dimension reduction, and setting the users with the object characteristic similarity larger than a second preset value in the same user set according to the object characteristics after the dimension reduction.
5. The intelligent terminal of claim 3, wherein the processor is further configured to:
after the plurality of user sets are built, aiming at any user set, the built plurality of user sets are corrected according to the similarity between the object features corresponding to the users in the user set.
6. A method for object recommendation, the method comprising:
determining at least one target user set to which a target user belongs from a plurality of user sets constructed in advance, wherein the user sets are constructed according to object features of objects in user transaction records on a plurality of transaction platforms;
in the at least one target user set, determining users similar to the target user;
and recommending the object for the target user according to the object in the user transaction record of the user similar to the target user.
7. The method of claim 6, wherein said determining users similar to said target user in said at least one set of target users comprises:
aiming at any target user set, extracting all alternative users contained in the target user set;
and determining the similarity between the object features corresponding to the target user and the object features corresponding to the alternative users aiming at the alternative users, and taking the alternative users corresponding to the similarity larger than a first preset value as the users similar to the target user.
8. The method of claim 6, wherein the plurality of user sets are constructed by:
acquiring user transaction records in a plurality of transaction platforms corresponding to the multi-transaction platform collaborative recommendation request, and determining objects in the user transaction records;
and setting users with object feature similarity larger than a second preset value in the same user set according to the object features of the objects in the user transaction records, wherein the second preset value is smaller than or equal to the first preset value.
9. The method of claim 8, wherein before setting the users with object feature similarity greater than a second preset value in the same user set according to the object features of the objects in the user transaction records, further comprising:
for any user, after determining that the object feature dimension of the object in the user transaction record is higher than a dimension threshold, converting the object feature of each object in the user transaction record into a hash value through a hash algorithm, and performing weighting processing on the hash value;
and after the weighted results after the weighting processing are added, signature processing is carried out to obtain the object features after the dimension reduction.
10. The method of claim 8, wherein after the constructing the plurality of user sets, further comprising:
and aiming at any user set, correcting the constructed multiple user sets according to the similarity between the object features corresponding to the users in the user set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506756.9A CN113469773A (en) | 2020-06-05 | 2020-06-05 | Intelligent terminal and object recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506756.9A CN113469773A (en) | 2020-06-05 | 2020-06-05 | Intelligent terminal and object recommendation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113469773A true CN113469773A (en) | 2021-10-01 |
Family
ID=77868163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506756.9A Pending CN113469773A (en) | 2020-06-05 | 2020-06-05 | Intelligent terminal and object recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113469773A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108269117A (en) * | 2017-01-03 | 2018-07-10 | 阿里巴巴集团控股有限公司 | The push of data determines method and device, terminal |
| CN109241426A (en) * | 2018-08-31 | 2019-01-18 | 苏州大学 | A kind of object recommendation method, apparatus, equipment and readable storage medium storing program for executing |
| CN110232152A (en) * | 2019-05-27 | 2019-09-13 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, server and storage medium |
| CN110569446A (en) * | 2019-09-04 | 2019-12-13 | 第四范式（北京）技术有限公司 | Method and system for constructing recommended object candidate set |
| CN111143697A (en) * | 2020-01-02 | 2020-05-12 | 腾讯科技（深圳）有限公司 | Content recommendation method and related device |
-
2020
- 2020-06-05 CN CN202010506756.9A patent/CN113469773A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108269117A (en) * | 2017-01-03 | 2018-07-10 | 阿里巴巴集团控股有限公司 | The push of data determines method and device, terminal |
| CN109241426A (en) * | 2018-08-31 | 2019-01-18 | 苏州大学 | A kind of object recommendation method, apparatus, equipment and readable storage medium storing program for executing |
| CN110232152A (en) * | 2019-05-27 | 2019-09-13 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, server and storage medium |
| CN110569446A (en) * | 2019-09-04 | 2019-12-13 | 第四范式（北京）技术有限公司 | Method and system for constructing recommended object candidate set |
| CN111143697A (en) * | 2020-01-02 | 2020-05-12 | 腾讯科技（深圳）有限公司 | Content recommendation method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200258006A1 (en) | Prediction method, terminal, and server | |
| CN107464162B (en) | Commodity association method and device and computer-readable storage medium | |
| US20160044269A1 (en) | Electronic device and method for controlling transmission in electronic device | |
| JP2023505412A (en) | Block processing method, data retrieval method and apparatus based on blockchain | |
| CN113935813A (en) | Information display method and device, electronic equipment and storage medium | |
| CN111476629A (en) | Data prediction method and device, electronic equipment and storage medium | |
| CN111090877B (en) | Data generation and acquisition methods, corresponding devices and storage medium | |
| CN115345464A (en) | Service order dispatching method and device, computer equipment and storage medium | |
| CN114282587A (en) | Data processing method and device, computer equipment and storage medium | |
| CN111262744B (en) | Multimedia information transmitting method, backup server and medium | |
| CN110659975B (en) | Resource transfer method, device, equipment and storage medium based on block chain | |
| CN111475392A (en) | Method, apparatus, electronic device and computer readable medium for generating prediction information | |
| CN113469773A (en) | Intelligent terminal and object recommendation method | |
| CN110599158A (en) | Virtual card combination method, virtual card combination device and terminal equipment | |
| CN111191143A (en) | Application recommendation method and device | |
| CN115222483A (en) | Financial product recommendation method and device, electronic equipment and storage medium | |
| CN111062709B (en) | Resource transfer mode recommendation method and device, electronic equipment and storage medium | |
| CN107977842A (en) | Ideal money exchanging method, device and electronic equipment | |
| CN109313771A (en) | The degree of reiability of real-time auction | |
| CN109685561B (en) | Electronic certificate pushing method and device based on user behavior and electronic equipment | |
| CN107087119B (en) | Method and device for adjusting exposure and electronic equipment | |
| CN113098754A (en) | Group revocation method and device, electronic equipment and storage medium | |
| CN111476562A (en) | Virtual resource transfer method, device, electronic equipment and storage medium | |
| CN111191056A (en) | Multimedia recommendation method and device | |
| CN111818509A (en) | Resource conversion method, device and equipment |
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 |