CN111598671B - Commodity recommendation method based on human-computer interaction - Google Patents
Commodity recommendation method based on human-computer interaction Download PDFInfo
- Publication number
- CN111598671B CN111598671B CN202010696007.7A CN202010696007A CN111598671B CN 111598671 B CN111598671 B CN 111598671B CN 202010696007 A CN202010696007 A CN 202010696007A CN 111598671 B CN111598671 B CN 111598671B
- Authority
- CN
- China
- Prior art keywords
- information
- target user
- commodity
- acquiring
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003993 interaction Effects 0.000 title claims abstract description 38
- 230000002452 interceptive effect Effects 0.000 claims abstract description 61
- 230000001815 facial effect Effects 0.000 claims abstract description 57
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 230000008451 emotion Effects 0.000 claims description 84
- 230000008859 change Effects 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000002996 emotional effect Effects 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 230000008921 facial expression Effects 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 3
- 210000001747 pupil Anatomy 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Development Economics (AREA)
- Human Computer Interaction (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a commodity recommendation method based on human-computer interaction, which comprises the following steps: acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set; acquiring interactive information of a target user and a merchant through electronic equipment based on a shopping platform, and generating an interactive information set; according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through electronic equipment, and generating a facial information set; analyzing an input information set, an interactive information set and a face information set of a target user to obtain commodity recommendation information of the target user; transmitting commodity information to electronic equipment of a target user according to the commodity recommendation information; therefore, commodity recommendation to the target user is achieved, meanwhile, the function of personalized recommendation to the target user according to commodity preference of the target user is achieved, and experience effects of the target user based on a shopping platform are further improved.
Description
Technical Field
The invention relates to the technical field of information push, in particular to a commodity recommendation method based on human-computer interaction.
Background
The online shopping platform is used for retrieving commodity information through the Internet, sending a shopping request through an electronic purchase order, filling a private check account number or a credit card number, and delivering goods by a manufacturer in a mail order mode or delivering goods to the home through an express company.
With the development of network technology, more and more people select to purchase goods through online shopping platforms; currently, for pushing commodity information, related commodity information is still pushed to a target user according to a historical purchase record of the target user, and when the target user has no historical purchase record or the information amount of the historical purchase record is small, commodity recommendation to the target user cannot be achieved.
Therefore, a commodity recommendation method based on human-computer interaction is urgently needed.
Disclosure of Invention
In order to solve the technical problem, the invention provides a commodity recommendation method based on human-computer interaction, which is used for realizing commodity recommendation to a target user.
The embodiment of the invention provides a commodity recommendation method based on human-computer interaction, which comprises the following steps:
acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set;
acquiring interactive information of a target user and a merchant through the electronic equipment based on the shopping platform, and generating an interactive information set;
according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through the electronic equipment, and generating a facial information set;
analyzing the input information set, the interaction information set and the face information set of the target user to obtain commodity recommendation information of the target user;
and transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information.
In one embodiment, the external monitoring device comprises a camera;
the face information comprises micro expression information of the target user and pupil attention information of the target user.
In one embodiment, the steps of: acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set; acquiring interactive information of a target user and a merchant through the electronic equipment based on the shopping platform, and generating an interactive information set; according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through the electronic equipment, and generating a facial information set; the method specifically comprises the following steps:
acquiring time information corresponding to the input information;
transmitting the input information and the time information corresponding to the input information set;
acquiring time information corresponding to the interaction information;
transmitting the interactive information and the time information corresponding to the interactive information set;
acquiring time information corresponding to the face information;
transmitting the face information and time information corresponding to the face information set;
the steps are as follows: according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through the electronic equipment, and generating a facial information set; then, the method further comprises the following steps:
acquiring time information of a target user based on the operation of the shopping platform;
dividing the time information of the target user based on the shopping platform operation into a plurality of time period information according to a preset time interval;
comparing the time period information with the time information in the input information set to acquire the input information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the interactive information set to acquire the interactive information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the face information set to acquire the face information corresponding to the time information which is the same as the time period information;
drawing a time axis of the time information operated by the target user based on the shopping platform according to the time period information; and marking the input information, the interactive information and the face information which are acquired according to the time period information on the time axis to acquire the time axis after marking processing.
In one embodiment, the steps of: analyzing the input information set, the interaction information set and the face information set of the target user to obtain commodity recommendation information of the target user; the method specifically comprises the following steps:
acquiring face change information of a target user based on the time axis after the marking processing;
acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user;
segmenting the marked time axis according to the time nodes to obtain a plurality of sub time axes;
acquiring the input information, the interaction information and the face information corresponding to the sub-timeline;
matching the face information with information in a face database to acquire emotion information of a target user in time information corresponding to the sub-time axis;
storing the input information, the interaction information and the facial information corresponding to the sub-timeline in an emotion database corresponding to the emotion information according to the emotion information;
acquiring the commodity recommendation information of a target user according to the input information, the interaction information and the facial information in the emotion database;
the emotional information comprises annoyance, joy, fear, anger and apprehension;
the emotion database comprises an annoyance database, a pleasure database, a fear database, an anger database and an apprehension database.
In one embodiment, the steps of: acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user; then, the method further comprises the following steps:
acquiring the input information and the interaction information before and after the time node based on the marked time axis;
comparing and analyzing the input information and the interactive information before and after the time node to obtain reason information of the change of the facial expression of the target user before and after the time node;
the steps are as follows: acquiring the commodity recommendation information of a target user according to the input information, the interaction information and the facial information in the emotion database; the method specifically comprises the following steps:
acquiring a preset recommendation model;
acquiring commodity display information in the interactive information;
taking the input information and the facial information in the emotion database as input data of the preset recommendation model, taking the commodity display information as output data of the preset recommendation model, training the preset recommendation model, and acquiring a commodity recommendation model of a target user;
optimizing the commodity recommendation model according to the reason information to obtain an optimized commodity recommendation model;
the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information.
In one embodiment, the steps of: optimizing the commodity recommendation model according to the reason information to obtain an optimized commodity recommendation model; the method specifically comprises the following steps:
acquiring emotion change information of the target user before and after the time node;
when the emotion change information is positive-negative emotion information, acquiring a negative factor which enables the emotion of a target user to be negatively changed in the reason information;
when the emotion change information is negative-positive emotion information, acquiring positive factors which enable the emotion of the target user to be positively changed in the reason information;
according to the negative factors, the commodity recommendation model sets parameters causing the negative factors, and the negative factors are suppressed; and setting parameters causing the positive factors by the commodity recommendation model according to the positive factors, and gaining the positive factors.
In one embodiment, the steps of: transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information; then, also include
Acquiring facial information of a target user when the target user receives the commodity information through the external monitoring equipment;
comparing the face information with the information in the face database to obtain emotion information when the target user receives the commodity information;
judging whether the emotion information received by the target user is positive emotion; when judging that the emotion information when the target user receives the commodity information is positive emotion, acquiring attribute information in the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity recommending module corresponding to a target user;
when the emotion information received by the target user is judged to be a negative emotion, acquiring attribute information of the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity shielding module corresponding to a target user;
the steps are as follows: the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information; then, the method further comprises the following steps:
comparing the optimized commodity recommendation information output by the commodity recommendation model with the commodity information in the commodity recommendation module and the information of the related commodities, and preferentially pushing the commodity information which is compared with the information in the commodity recommendation module in the commodity recommendation information to a target user when the commodity recommendation information is compared with the information in the commodity recommendation module;
and comparing the optimized commodity recommendation information output by the commodity recommendation model with the commodity information in the commodity shielding module and the information of the related commodities, deleting the commodity information which is compared with the information in the commodity shielding module in the commodity recommendation information when the commodity recommendation information is compared with the information in the commodity shielding module, and pushing the deleted commodity recommendation information to a target user.
In one embodiment, the attribute information of the commodity information includes category information, price information, and manufacturer information of a commodity corresponding to the commodity information.
In one embodiment, the steps of: transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information; further comprising:
acquiring purchase information in the interactive information;
according to the purchase information, acquiring the shopping time information of the target user based on the shopping platform;
according to the shopping time information, acquiring date information of the target user based on shopping of the shopping platform; intelligently analyzing the date information to acquire the attribute characteristics of the date information;
acquiring a date with the attribute characteristics based on an electronic calendar according to the attribute characteristics of the date information, and taking the date as a commodity recommended date;
according to the shopping time information, acquiring time information of the target user for shopping based on the shopping platform; analyzing the time information to acquire shopping period information of the target user;
and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information at the time corresponding to the shopping period information in the commodity recommendation date.
In one embodiment, the steps of: according to the external monitoring equipment, when the target user operates on the shopping platform through the electronic equipment, the facial information of the target user is obtained, and in the process of generating a facial information set, the method comprises the following steps:
monitoring the working logs of N cameras arranged in the external monitoring equipment, and acquiring the working load information of the N cameras according to the working logs;
according to the working load information, before the face information of the target user is obtained, load balancing distribution is carried out on the N cameras based on a load distribution rule, and meanwhile whether the load balancing distribution is reasonable or not is judged according to the following formula;
wherein S represents a calculation result of load balancing distribution; i represents the ith camera in the N cameras;
the load workload corresponding to the working stage of the ith camera at the high and medium human flow rate every day is represented;
representing the total load workload of the ith camera working each day;
the rated load workload distributed to the ith camera based on the load distribution rule is represented;
a position weight value representing the current shooting position of the ith camera;
when the S is larger than the preset value, the distribution is reasonable, the N cameras which are subjected to load balancing distribution are controlled to respectively shoot the target user, N groups of shooting sets are obtained, and the N groups of shooting sets correspond to the N cameras one by one;
otherwise, indicating that the distribution is unreasonable, adjusting the load balance distribution, and respectively shooting the target user according to N cameras corresponding to the adjusted load balance distribution to obtain N groups of shooting sets;
and obtaining the face information of the target user according to the obtained N groups of shooting sets.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
Fig. 1 is a schematic structural diagram of a commodity recommendation method based on human-computer interaction according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides a commodity recommendation method based on human-computer interaction, which comprises the following steps of:
acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set;
acquiring interactive information of a target user and a merchant through electronic equipment based on a shopping platform, and generating an interactive information set;
according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through electronic equipment, and generating a facial information set;
analyzing an input information set, an interactive information set and a face information set of a target user to obtain commodity recommendation information of the target user;
and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information.
The working principle of the method is as follows: acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set; acquiring interactive information of a target user and a merchant through electronic equipment based on a shopping platform, and generating an interactive information set; according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through electronic equipment, and generating a facial information set; analyzing the acquired input information set, the interactive information set and the facial information set to acquire commodity recommendation information of a target user; and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information.
The method has the beneficial effects that: the input information set generation is realized through the input information which is acquired based on the shopping platform and transmitted by the target user through the electronic equipment; the interactive information of the target user and the merchant through the electronic equipment is acquired based on the shopping platform, so that the interactive information set is generated; when the target user is monitored by the external monitoring equipment and operates on the basis of the shopping platform through the electronic equipment, the facial information of the target user is acquired, and the generation of a facial information set is realized; the acquired input information set, the interactive information set and the facial information set are analyzed, and the commodity recommendation information of the target user is acquired; according to the commodity recommendation information, transmitting commodity information to the electronic equipment of the target user to realize commodity recommendation to the target user; compared with the prior art, the method acquires the commodity recommendation information by acquiring the input information, the interaction information and the face information of the target user, and further recommends the commodity information to the target user; the method and the device solve the defect that the related commodity information is pushed to the target user completely depending on the historical purchase record of the target user in the prior art, and analyze input information and interactive information based on the shopping platform and facial information of the target user acquired by external monitoring equipment according to information interaction between the target user and communication equipment, so that commodity recommendation to the target user is realized, meanwhile, the function of personalized recommendation to the target user according to commodity preference of the target user is realized, and the experience effect of the target user based on the shopping platform is further improved.
In one embodiment, an external monitoring device includes a camera; according to the technical scheme, the external monitoring equipment acquires the face information of the target user through the camera.
And the face information comprises micro expression information of the target user and pupil attention information of the target user.
In one embodiment, the steps of: acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set; acquiring interactive information of a target user and a merchant through electronic equipment based on a shopping platform, and generating an interactive information set; according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through electronic equipment, and generating a facial information set; the method specifically comprises the following steps:
acquiring time information corresponding to the input information;
transmitting the input information and the time information corresponding to the input information to an input information set;
acquiring time information corresponding to the interactive information;
transmitting the interactive information and the time information corresponding to the interactive information to an interactive information set;
acquiring time information corresponding to the face information;
transmitting the face information and time information corresponding to the face information to a face information set;
the method comprises the following steps: according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through electronic equipment, and generating a facial information set; then, the method further comprises the following steps:
acquiring time information of a target user based on shopping platform operation;
dividing time information of a target user based on shopping platform operation into a plurality of time period information according to a preset time interval;
comparing the time period information with the time information in the input information set to acquire input information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the interactive information set to acquire interactive information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the face information set to obtain face information corresponding to the time information which is the same as the time period information;
drawing a time axis of the time information operated by the target user based on the shopping platform according to the time period information; and marking the input information, the interactive information and the face information acquired according to the time period information on a time axis to acquire the time axis after marking processing. In the technical scheme, time information corresponding to input information, interactive information and face information respectively is obtained and is transmitted to an input information set, an interactive information set and a face information set respectively; dividing the time information of the target user based on the shopping platform operation into a plurality of time period information according to a preset time interval (for example, the preset time interval is 20 seconds); comparing the time period information with the time information in the input information set, the interactive information set and the face information set respectively to obtain the input information, the interactive information and the face information corresponding to the time information which is the same as the time period information; and the acquired input information, the acquired interaction information and the acquired facial information are marked on a time axis of the time information of the target user based on the shopping platform operation, so that the commodity preference of the target user can be analyzed based on the time axis in the subsequent steps, and the acquisition of the commodity recommendation information is realized.
In one embodiment, the steps of: analyzing an input information set, an interactive information set and a face information set of a target user to obtain commodity recommendation information of the target user; the method specifically comprises the following steps:
acquiring face change information of a target user based on the marked time axis;
acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user;
segmenting the marked time axis according to the time nodes to obtain a plurality of sub time axes;
acquiring input information, interactive information and face information corresponding to the sub-time axis;
matching the face information with information in a face database to acquire emotion information of a target user in time information corresponding to a sub-time axis;
storing input information, interactive information and facial information corresponding to the sub-time axis in an emotion database corresponding to the emotion information according to the emotion information;
acquiring commodity recommendation information of a target user according to input information, interactive information and facial information in an emotion database;
emotional information, including annoyance, pleasure, fear, anger, and apprehension;
emotion databases including an annoyance database, a pleasure database, a fear database, an anger database, and an apprehension database. According to the technical scheme, a time node corresponding to the face change information of the target user is obtained according to the face change information of the target user; segmenting the marked time axis according to the time nodes to acquire a plurality of sub time axes; matching the face information corresponding to the sub-time axis with the information in the face database, so that the emotion information of the target user is acquired; establishing an emotion database corresponding to the sub-time axis according to the acquired emotion information, and storing input information, interactive information and facial information corresponding to the sub-time axis in the emotion database; and the acquisition of the commodity recommendation information of the target user is realized according to the input information, the interaction information and the face information in the emotion database.
In one embodiment, the steps of: acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user; then, the method further comprises the following steps:
acquiring input information and interactive information before and after a time node based on the marked time axis;
comparing and analyzing the input information and the interactive information before and after the time node to obtain the reason information of the change of the facial expression of the target user before and after the time node;
the method comprises the following steps: acquiring commodity recommendation information of a target user according to input information, interactive information and facial information in an emotion database; the method specifically comprises the following steps:
acquiring a preset recommendation model;
acquiring commodity display information in the interactive information;
taking input information and face information in an emotion database as input data of a preset recommendation model, taking commodity display information as output data of the preset recommendation model, training the preset recommendation model, and obtaining a commodity recommendation model of a target user;
optimizing the commodity recommendation model according to the reason information to obtain the optimized commodity recommendation model;
the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information. In the technical scheme, the input information and the face information in the emotion database are used as the input data of the preset recommendation model, the commodity display information is used as the output data of the preset recommendation model, and the preset recommendation model is trained, so that the commodity recommendation model of the target user is obtained; the commodity recommendation model is optimized according to the reason information obtained by comparing the input information and the interactive information before and after the time node, so that the optimized commodity recommendation model is obtained; the input information, the interaction information and the face information are output to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information, so that the commodity recommendation information of the target user can be acquired according to the input information, the interaction information and the face information.
In one embodiment, the steps of: optimizing the commodity recommendation model according to the reason information to obtain the optimized commodity recommendation model; the method specifically comprises the following steps:
acquiring emotion change information of a target user before and after a time node;
when the emotion change information is positive-negative emotion information, acquiring a negative factor which enables the emotion of the target user to generate negative change in the reason information;
when the emotion change information is negative-positive emotion information, acquiring positive factors which enable the emotion of the target user to be positively changed in the reason information;
according to the negative factors, the commodity recommendation model sets parameters causing the negative factors, and the negative factors are suppressed; according to the positive factors, the commodity recommendation model sets parameters causing the positive factors, and the positive factors are gained. According to the technical scheme, the emotion change information of the target user before and after the time node is obtained, when the emotion change information changes from positive emotion to negative emotion, the negative factors in the reason information are obtained, and the parameters causing the negative factors in the commodity recommendation model are set according to the negative factors to suppress the negative factors; when the emotion change information changes from negative emotion to positive emotion, the positive factors in the reason information are obtained, parameters which cause the positive factors in the commodity recommendation model are set according to the positive factors, the negative factors are increased, optimization processing of the commodity recommendation model is achieved, further, commodity recommendation information output by the commodity recommendation model is enabled to be more in line with the preference of a target user, and therefore shopping experience of the target user based on a shopping platform is effectively improved.
In one embodiment, the steps of: transmitting commodity information to electronic equipment of a target user according to the commodity recommendation information; then, also include
Acquiring face information of a target user when the target user receives commodity information through external monitoring equipment;
comparing the face information with information in a face database to obtain emotion information when the target user receives commodity information;
judging whether the emotion information of the target user when receiving the commodity information is positive emotion; when judging that the emotion information when the target user receives the commodity information is positive emotion, acquiring attribute information in the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity recommending module corresponding to the target user;
when judging that the emotion information when the target user receives the commodity information is a negative emotion, acquiring attribute information of the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity shielding module corresponding to a target user;
the method comprises the following steps: the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information; then, the method further comprises the following steps:
comparing the commodity recommendation information output by the optimized commodity recommendation model with the commodity information in the commodity recommendation module and the information of related commodities, and preferentially pushing the commodity information which is compared with the information in the commodity recommendation module and is consistent in the commodity recommendation information to a target user when the comparison is consistent;
and comparing the commodity recommendation information output by the optimized commodity recommendation model with the commodity information in the commodity shielding module and the information of the related commodities, deleting the commodity information which is compared with the information in the commodity shielding module in the commodity recommendation information when the commodity recommendation information is compared with the information in the commodity shielding module, and pushing the deleted commodity recommendation information to a target user. According to the technical scheme, when a target user receives transmitted commodity information through electronic equipment, the current facial information of the target user is obtained through external monitoring equipment; comparing the face information with information in a face database to obtain current emotion information of the target user; when the emotion information of the target user is positive emotion, storing the commodity information and information of related commodities of the commodities corresponding to the commodity information, which is acquired according to the attribute information of the commodity information, in a commodity recommendation module corresponding to the target user; when the emotion information of the target user is a negative emotion, the commodity information and the information of the relevant commodities of the commodities corresponding to the commodity information, which is acquired according to the attribute information of the commodity information, are stored in a commodity shielding module corresponding to the target user; comparing the commodity recommendation information of the target user acquired later with the information in the commodity recommendation module and the commodity shielding module respectively, and preferentially pushing the commodity information which is compared with the information in the commodity recommendation module and is consistent with the information in the commodity recommendation module in the commodity recommendation information to the target user when the commodity recommendation information is compared with the information in the commodity recommendation module; when the commodity recommendation information is consistent with the information in the commodity shielding module in comparison, deleting the commodity information which is consistent with the information in the commodity shielding module in comparison in the commodity recommendation information, and pushing the deleted commodity recommendation information to a target user; therefore, personalized commodity recommendation for the target user is realized, and the experience effect of the target user is improved.
In one embodiment, the attribute information of the commodity information includes the type information, price information and manufacturer information of the commodity corresponding to the commodity information. According to the technical scheme, the related commodities of the commodities corresponding to the commodity information are acquired through the attribute information of the commodity information.
In one embodiment, the steps of: transmitting commodity information to electronic equipment of a target user according to the commodity recommendation information; further comprising:
acquiring purchase information in the interactive information;
acquiring shopping time information of a target user based on a shopping platform according to the shopping information;
according to the shopping time information, acquiring date information of shopping of a target user based on a shopping platform; intelligently analyzing the date information to obtain the attribute characteristics of the date information;
acquiring a date with the attribute characteristics based on the electronic calendar according to the attribute characteristics of the date information, and taking the date as a commodity recommended date;
according to the shopping time information, acquiring time information of shopping of a target user based on a shopping platform; analyzing the time information to obtain the shopping time interval information of the target user;
and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information at the time corresponding to the shopping period information in the commodity recommendation date. According to the technical scheme, the shopping time information of the target user based on the shopping platform is acquired through the purchasing information; the date information in the shopping time information is intelligently analyzed, so that the attribute characteristics of the date information are acquired; taking the date with the attribute characteristics as a commodity recommended date in the electronic calendar; analyzing the time information in the shopping time information to acquire the shopping time interval information of the target user; and transmitting the commodity information to the electronic equipment of the target user at the time corresponding to the shopping period information in the commodity recommendation date.
In one embodiment, the attribute characteristics of the date information in the shopping time information of the target user are holiday and "dueleven"; the shopping period information of the target user is 8 o 'clock to 12 o' clock at night; and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information at 8 o 'clock to 12 o' clock in the evening of the holiday or the activity day of the shopping platform so as to realize the commodity recommendation of the target user.
In one embodiment, the steps of: according to the external monitoring equipment, when a target user operates on the basis of a shopping platform through the electronic equipment, the facial information of the target user is obtained, and in the process of generating a facial information set, the method comprises the following steps:
monitoring working logs of N cameras arranged in external monitoring equipment, and acquiring working load information of the N cameras according to the working logs;
according to the working load information, before the face information of the target user is obtained, load balancing distribution is carried out on the N cameras based on a load distribution rule, and meanwhile whether the load balancing distribution is reasonable or not is judged according to the following formula;
wherein S represents a calculation result of load balancing distribution; i represents the ith camera in the N cameras;
the load workload corresponding to the working stage of the ith camera at the high and medium human flow rate every day is represented;
representing the total load workload of the ith camera working each day;
the rated load workload distributed to the ith camera based on the load distribution rule is represented;
a position weight value representing the current shooting position of the ith camera;
when the S is larger than the preset value, the distribution is reasonable, the N cameras which are subjected to load balancing distribution are controlled to respectively shoot the target user, N groups of shooting sets are obtained, and the N groups of shooting sets correspond to the N cameras one by one;
otherwise, indicating that the distribution is unreasonable, adjusting the load balance distribution, and respectively shooting the target user according to N cameras corresponding to the adjusted load balance distribution to obtain N groups of shooting sets;
and obtaining the face information of the target user according to the obtained N groups of shooting sets.
In this embodiment, the work log includes energy consumption of the camera, shooting orientation, effective capturing time related to the facial information of the target user captured in the shooting process, and the like;
in this embodiment, the load balancing distribution is performed on the cameras, so that centralized monitoring can be performed, and multi-energy distribution is performed on the cameras corresponding to the centralized monitoring.
The beneficial effects of the above technical scheme are: the cameras in the external monitoring equipment are subjected to load balancing distribution, so that effective operation of the cameras is convenient to guarantee, the effective service life of the cameras is prolonged, in the shooting process, due to the fact that the energy loss of shooting of each camera is different, the working load information is determined according to the working logs, the cameras are subjected to load balancing distribution according to the load distribution rule, whether the distribution result is reasonable or not is calculated and judged through the formula, effective shooting of a target user is achieved, and more complete facial information is obtained.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A commodity recommendation method based on human-computer interaction is characterized by comprising the following steps:
acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set;
acquiring interactive information of a target user and a merchant through the electronic equipment based on the shopping platform, and generating an interactive information set;
according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through the electronic equipment, and generating a facial information set;
analyzing the input information set, the interaction information set and the face information set of the target user to obtain commodity recommendation information of the target user;
transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information;
acquiring input information transmitted by a target user through electronic equipment based on a shopping platform, and generating an input information set; acquiring interactive information of a target user and a merchant through the electronic equipment based on the shopping platform, and generating an interactive information set; according to the external monitoring device, when the target user operates based on the shopping platform through the electronic device, the facial information of the target user is obtained, and the generation of the facial information set comprises the following steps:
acquiring time information corresponding to the input information;
transmitting the input information and the time information corresponding to the input information set;
acquiring time information corresponding to the interaction information;
transmitting the interactive information and the time information corresponding to the interactive information set;
acquiring time information corresponding to the face information;
transmitting the face information and time information corresponding to the face information set;
the steps are as follows: according to external monitoring equipment, acquiring facial information of a target user when the target user operates on the shopping platform through the electronic equipment, and generating a facial information set; then, the method further comprises the following steps:
acquiring time information of a target user based on the operation of the shopping platform;
dividing the time information of the target user based on the shopping platform operation into a plurality of time period information according to a preset time interval;
comparing the time period information with the time information in the input information set to acquire the input information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the interactive information set to acquire the interactive information corresponding to the time information which is the same as the time period information; comparing the time period information with the time information in the face information set to acquire the face information corresponding to the time information which is the same as the time period information;
drawing a time axis of the time information operated by the target user based on the shopping platform according to the time period information; and marking the input information, the interactive information and the face information which are acquired according to the time period information on the time axis to acquire the time axis after marking processing.
2. The method of claim 1,
the external monitoring equipment comprises a camera;
the face information comprises micro expression information of the target user and pupil attention information of the target user.
3. The method of claim 1, wherein the steps of: analyzing the input information set, the interaction information set and the face information set of the target user to obtain commodity recommendation information of the target user; the method specifically comprises the following steps:
acquiring face change information of a target user based on the time axis after the marking processing;
acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user;
segmenting the marked time axis according to the time nodes to obtain a plurality of sub time axes;
acquiring the input information, the interaction information and the face information corresponding to the sub-timeline;
matching the face information with information in a face database to acquire emotion information of a target user in time information corresponding to the sub-time axis;
storing the input information, the interaction information and the facial information corresponding to the sub-timeline in an emotion database corresponding to the emotion information according to the emotion information;
acquiring the commodity recommendation information of a target user according to the input information, the interaction information and the facial information in the emotion database;
the emotional information comprises annoyance, joy, fear, anger and apprehension;
the emotion database comprises an annoyance database, a pleasure database, a fear database, an anger database and an apprehension database.
4. The method of claim 3, wherein the steps of: acquiring a time node corresponding to the face change information of the target user according to the face change information of the target user; then, the method further comprises the following steps:
acquiring the input information and the interaction information before and after the time node based on the marked time axis;
comparing and analyzing the input information and the interactive information before and after the time node to obtain reason information of the change of the facial expression of the target user before and after the time node;
the steps are as follows: acquiring the commodity recommendation information of a target user according to the input information, the interaction information and the facial information in the emotion database; the method specifically comprises the following steps:
acquiring a preset recommendation model;
acquiring commodity display information in the interactive information;
taking the input information and the facial information in the emotion database as input data of the preset recommendation model, taking the commodity display information as output data of the preset recommendation model, training the preset recommendation model, and acquiring a commodity recommendation model of a target user;
optimizing the commodity recommendation model according to the reason information to obtain an optimized commodity recommendation model;
the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information.
5. The method of claim 4, wherein the steps of: optimizing the commodity recommendation model according to the reason information to obtain an optimized commodity recommendation model; the method specifically comprises the following steps:
acquiring emotion change information of the target user before and after the time node;
when the emotion change information is positive-negative emotion information, acquiring a negative factor which enables the emotion of a target user to be negatively changed in the reason information;
when the emotion change information is negative-positive emotion information, acquiring positive factors which enable the emotion of the target user to be positively changed in the reason information;
according to the negative factors, the commodity recommendation model sets parameters causing the negative factors, and the negative factors are suppressed; and setting parameters causing the positive factors by the commodity recommendation model according to the positive factors, and gaining the positive factors.
6. The method of claim 4, wherein the steps of: transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information; then, also include
Acquiring facial information of a target user when the target user receives the commodity information through the external monitoring equipment;
comparing the face information with the information in the face database to obtain emotion information when the target user receives the commodity information;
judging whether the emotion information received by the target user is positive emotion; when judging that the emotion information when the target user receives the commodity information is positive emotion, acquiring attribute information in the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity recommending module corresponding to a target user;
when the emotion information received by the target user is judged to be a negative emotion, acquiring attribute information of the commodity information; according to the attribute information, related commodities of the commodities corresponding to the commodity information are obtained on the basis of the shopping platform, and the commodity information and the information of the related commodities are stored in a commodity shielding module corresponding to a target user;
the steps are as follows: the target user transmits the input information and the interaction information to the optimized commodity recommendation model, the external monitoring equipment transmits the facial information of the target user to the optimized commodity recommendation model, and the optimized commodity recommendation model outputs the commodity recommendation information; then, the method further comprises the following steps:
comparing the optimized commodity recommendation information output by the commodity recommendation model with the commodity information in the commodity recommendation module and the information of the related commodities, and preferentially pushing the commodity information which is compared with the information in the commodity recommendation module in the commodity recommendation information to a target user when the commodity recommendation information is compared with the information in the commodity recommendation module;
and comparing the optimized commodity recommendation information output by the commodity recommendation model with the commodity information in the commodity shielding module and the information of the related commodities, deleting the commodity information which is compared with the information in the commodity shielding module in the commodity recommendation information when the commodity recommendation information is compared with the information in the commodity shielding module, and pushing the deleted commodity recommendation information to a target user.
7. The method of claim 6,
the attribute information of the commodity information comprises the type information, price information and manufacturer information of the commodity corresponding to the commodity information.
8. The method of claim 1, wherein the steps of: transmitting commodity information to the electronic equipment of the target user according to the commodity recommendation information; further comprising:
acquiring purchase information in the interactive information;
according to the purchase information, acquiring the shopping time information of the target user based on the shopping platform;
according to the shopping time information, acquiring date information of the target user based on shopping of the shopping platform; intelligently analyzing the date information to acquire the attribute characteristics of the date information;
acquiring a date with the attribute characteristics based on an electronic calendar according to the attribute characteristics of the date information, and taking the date as a commodity recommended date;
according to the shopping time information, acquiring time information of the target user for shopping based on the shopping platform; analyzing the time information to acquire shopping period information of the target user;
and transmitting the commodity information to the electronic equipment of the target user according to the commodity recommendation information at the time corresponding to the shopping period information in the commodity recommendation date.
9. The method of claim 1, wherein the steps of: according to the external monitoring equipment, when the target user operates on the shopping platform through the electronic equipment, the facial information of the target user is obtained, and in the process of generating a facial information set, the method comprises the following steps:
monitoring the working logs of N cameras arranged in the external monitoring equipment, and acquiring the working load information of the N cameras according to the working logs;
according to the working load information, before the face information of the target user is obtained, load balancing distribution is carried out on the N cameras based on a load distribution rule, and meanwhile whether the load balancing distribution is reasonable or not is judged according to the following formula;
wherein S represents a calculation result of load balancing distribution; i represents the ith camera in the N cameras;
the load workload corresponding to the working stage of the ith camera at the high and medium human flow rate every day is represented;
representing the total load workload of the ith camera working each day;
the expression is based on the load distribution rule and is the ith cameraA rated load workload assigned;
a position weight value representing the current shooting position of the ith camera;
when the S is larger than the preset value, the distribution is reasonable, the N cameras which are subjected to load balancing distribution are controlled to respectively shoot the target user, N groups of shooting sets are obtained, and the N groups of shooting sets correspond to the N cameras one by one;
otherwise, indicating that the distribution is unreasonable, adjusting the load balance distribution, and respectively shooting the target user according to N cameras corresponding to the adjusted load balance distribution to obtain N groups of shooting sets;
and obtaining the face information of the target user according to the obtained N groups of shooting sets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696007.7A CN111598671B (en) | 2020-07-20 | 2020-07-20 | Commodity recommendation method based on human-computer interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696007.7A CN111598671B (en) | 2020-07-20 | 2020-07-20 | Commodity recommendation method based on human-computer interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598671A CN111598671A (en) | 2020-08-28 |
| CN111598671B true CN111598671B (en) | 2020-10-30 |
Family
ID=72183049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010696007.7A Active CN111598671B (en) | 2020-07-20 | 2020-07-20 | Commodity recommendation method based on human-computer interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598671B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348640B (en) * | 2020-11-12 | 2021-08-13 | 北京科技大学 | Online shopping system and method based on facial emotion state analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247759A (en) * | 2017-05-31 | 2017-10-13 | 深圳正品创想科技有限公司 | A kind of Method of Commodity Recommendation and device |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| WO2019023929A1 (en) * | 2017-08-01 | 2019-02-07 | 深圳市益廷科技有限公司 | Hotel shopping method |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103826160A (en) * | 2014-01-09 | 2014-05-28 | 广州三星通信技术研究有限公司 | Method and device for obtaining video information, and method and device for playing video |
-
2020
- 2020-07-20 CN CN202010696007.7A patent/CN111598671B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247759A (en) * | 2017-05-31 | 2017-10-13 | 深圳正品创想科技有限公司 | A kind of Method of Commodity Recommendation and device |
| WO2019023929A1 (en) * | 2017-08-01 | 2019-02-07 | 深圳市益廷科技有限公司 | Hotel shopping method |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598671A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104731895B (en) | The method and apparatus of automatic-answering back device | |
| CN108021929A (en) | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system | |
| CN109902708A (en) | A kind of recommended models training method and relevant apparatus | |
| CN101359995B (en) | Method and apparatus providing on-line service | |
| CN105843825A (en) | Influencer score | |
| CN109388697A (en) | Handle the method, apparatus and electric terminal of question and answer corpus | |
| CN111222410A (en) | Shop and merchant consumption behavior analysis guiding marketing system based on face recognition | |
| US20180218432A1 (en) | Recommendation integrated online digital sales service chat system | |
| CN114331512B (en) | Visual data modeling and big data portrayal method | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN114722281B (en) | Training course configuration method and device based on user portrait and user course selection behavior | |
| CN113313271A (en) | Power system fault repair method and device based on remote customer service | |
| CN111598671B (en) | Commodity recommendation method based on human-computer interaction | |
| CN106294676A (en) | A kind of data retrieval method of ecommerce government system | |
| CN116757270A (en) | Data processing method and server based on man-machine interaction model or large model | |
| CN109711703A (en) | The line loss querying method and system of power distribution network | |
| CN109840826A (en) | Internet sales ordering system | |
| WO2020098669A1 (en) | Expression input method and apparatus, and device and storage medium | |
| CN107480703A (en) | Transaction fault detection method and device | |
| CN111695625A (en) | Mobile application popularity prediction method based on multi-level attention mechanism network | |
| CN116738293A (en) | Service evaluation processing method and device and electronic equipment | |
| CN110348807A (en) | A kind of information processing method and relevant apparatus | |
| CN115953080A (en) | Engineer service level determination method, apparatus and storage medium | |
| CN115563176A (en) | Electronic commerce data processing system and method | |
| CN111414609B (en) | Object verification method and device |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211206 Address after: Room 084, No. 1-309, 3rd floor, commercial building, No. 9 Wangjing street, Chaoyang District, Beijing 100102 Patentee after: Beijing Daily Youxian Technology Co.,Ltd. Address before: 100102 room 801, 08 / F, building 7, yard 34, Chuangyuan Road, Chaoyang District, Beijing Patentee before: BEIJING MISSFRESH E-COMMERCE Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231109 Address after: 518000 807, No. 121, Minsheng Avenue, Shangcun Community, Gongming Street, Guangming District, Shenzhen, Guangdong Patentee after: Shenzhen Zhuanxin Intellectual Property Service Co.,Ltd. Address before: Room 084, No. 1-309, 3rd floor, commercial building, No. 9 Wangjing street, Chaoyang District, Beijing 100102 Patentee before: Beijing Daily Youxian Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240418 Address after: 550025 National (Guizhou) Hub Node of National Integrated Computing Power Network in Huchao Township, Gui'an New District, Guiyang City, Guizhou Province. Room 207-1085, 2nd Floor, Building 2, Computing Power Operation and Dispatch Center Patentee after: Xunfeng Technology (Guizhou) Co.,Ltd. Country or region after: China Address before: 518000 807, No. 121, Minsheng Avenue, Shangcun Community, Gongming Street, Guangming District, Shenzhen, Guangdong Patentee before: Shenzhen Zhuanxin Intellectual Property Service Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |