CN112749996A - Automatic commodity recommendation method and system for unmanned lipstick vending machine - Google Patents
Automatic commodity recommendation method and system for unmanned lipstick vending machine Download PDFInfo
- Publication number
- CN112749996A CN112749996A CN202110134656.2A CN202110134656A CN112749996A CN 112749996 A CN112749996 A CN 112749996A CN 202110134656 A CN202110134656 A CN 202110134656A CN 112749996 A CN112749996 A CN 112749996A
- Authority
- CN
- China
- Prior art keywords
- lipstick
- user
- vector
- recommendation
- dimensions
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims abstract description 48
- 230000014509 gene expression Effects 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000002688 persistence Effects 0.000 claims description 6
- 230000003121 nonmonotonic effect Effects 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000019771 cognition Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 244000144730 Amygdalus persica Species 0.000 description 2
- 235000006040 Prunus persica var persica Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an automatic commodity recommendation method and system for an unmanned lipstick vending machine, and belongs to the technical field of artificial intelligence and computers. The method mainly comprises the following steps: establishing a user personal feature vector and a demand vector, and acquiring values of a user in different dimensions in the vectors; establishing lipstick attribute vectors and vector spaces thereof, and determining values in different dimensions in the vectors according to characteristics of the lipstick in different vending machines; determining a recommendation result on a lipstick dimension according to the combination of different user dimensions; and judging whether the recommendation result vector can be matched with the lipstick attribute vector space. The invention provides a recommendation method based on logical reasoning aiming at the characteristics that the types and the quantity of commodities of an offline unmanned lipstick vending machine are small, user preference information is difficult to mine, and the like.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence and computers, and relates to a method and a system for automatically recommending commodities for an unmanned lipstick vending machine.
Background
With the development of the application of the unmanned vending system based on the computer and the artificial intelligence technology, the commodity recommendation based on the unmanned vending system, which can be accurate, rapid and convenient, becomes one of the main extended functions of the application. The traditional recommendation method is based on application of big data, and related products are recommended by mining multiple times of purchase information and preference information of the same user. However, the number of the goods of the offline unmanned vending system, such as the unmanned lipstick vending machine, is small, and different random users are faced, so that the preference information of the users is difficult to be mined, and the goods can not be recommended accurately and conveniently.
Disclosure of Invention
The invention aims to overcome the defects in the background art and provide an automatic commodity recommendation method and system for an unmanned lipstick vending machine. The method meets the requirement that people receive quick, accurate and convenient commodity recommendation on the unmanned lipstick vending machine, and is suitable for the characteristic that the commodity attribute and the quantity of the vending machine are limited.
The technical problem of the invention is solved by the following technical scheme:
a commodity automatic recommendation method for an unmanned lipstick vending machine comprises the following steps:
1) establishing a user personal feature vector and a demand vector, and acquiring values of a user in different dimensions in the vectors; the vector is a description concept of related knowledge, the personal feature vector comprises four dimensions of age, lip shape, face shape and skin color, and the demand vector comprises five dimensions of occasion, persistence, lustering, budget and preference;
2) establishing lipstick attribute vectors and vector spaces thereof, and determining values in different dimensions in the vectors according to characteristics of the lipstick in different vending machines; the lipstick attribute vector comprises three dimensions of color, type and brand;
3) determining a recommendation result on a lipstick dimension according to the combination of different user dimensions; the value of the recommendation result is the value existing in the vector space in the step 2), and the recommendation results on different dimensions are combined into a recommendation result vector;
4) and judging whether the recommendation result vector can be matched with the lipstick attribute vector space, if so, taking the recommendation result vector as the final recommended lipstick description, and if not, feeding back the shortage of the vending machine.
The automatic commodity recommending method of the unmanned lipstick vending machine is characterized in that the establishment of the personal feature vector, the demand vector and the lipstick attribute vector of the user comprises the following steps: and mapping different user dimensions and lipstick dimensions into a logic program representation form of knowledge.
The automatic commodity recommending method of the unmanned lipstick vending machine is characterized in that the method for determining the recommending result on a lipstick dimension according to the combination of different user dimensions comprises the following steps:
firstly, determining an inference model: recommending a lipstick color according to age, lip shape, face shape and skin color when there is no user preference information; recommending types according to occasions, persistence and lustering; recommending brands according to budgets; when user preference information exists, recommending colors, types and brands according to corresponding preferences;
secondly, defining model specification by non-monotonic logic semantics:
establishing expression (1) A (X, a)n)←F(X,f0,f1...fn)&S (X) representation assumes that user X has no preferenceInformation S, determining values for different conclusions, F (X, F), based on the values of different conditions in the model0,f1...fn) Representing user X, a set of values in different user dimensions, A (X, a)n) Representing the result recommended to user X in a lipstick dimension, anRepresents the corresponding value; establishing expression (2) A (X, a)n)←S(X)&P(pn) Indicates that the user X has preference information, determines a value, P (P), recommended to the user X in a lipstick dimension, based on the value in the preference dimensionn) Representing a user's value p in a preference dimensionn(ii) a Describing the specific problems in the inference model by the form of the expression;
and finally, mapping the problem description of the model into a representation form of a logic program rule statement, and determining a recommendation result by solving the logic program.
The automatic commodity recommending method of the unmanned lipstick vending machine is characterized in that the judgment of whether the recommendation result vector can be matched with the lipstick attribute vector space comprises the following steps: determining values which cannot be established simultaneously in different lipstick dimensions according to lipstick characteristics in different vending machines; and mapping the values into a representation form of the constraint by a logic program, and automatically judging a matching result by a solving program.
An automatic commodity recommendation system of an unmanned lipstick vending machine is characterized by comprising: the acquisition module is used for extracting the characteristics and the demand information in the user input instruction, symbolizing the characteristics and the demand information and storing the symbolized information into a knowledge base, wherein the knowledge base is a self-defined database and is used for storing the characteristics, the demand and the lipstick attribute information of the user; the management updating module is used for adding and deleting the lipstick attribute information and the logic rules, adding the new lipstick attribute information into the knowledge base, mapping the rule updating into corresponding logic program statements and delivering the corresponding logic program statements to the reasoning module; the reasoning module is used for converting the contents in the knowledge base and the obtained logic program sentences into a logic program main body, generating a file form which can be identified by a solver, automatically generating a result by the solver, and delivering the result to the result conversion module, wherein the solver is an execution system for solving the logic program and is used for realizing the rules and the method; and the result conversion module is used for converting the received solving result into a natural language form and feeding back the natural language form to the user.
Has the advantages that:
the invention provides a recommendation method based on logical reasoning and an implementation system thereof aiming at the characteristics that the types and the quantity of commodities of an offline unmanned lipstick vending machine are small, user preference information is difficult to mine and the like. The logic rule established by the recommendation method comprises non-monotonous logic semantics, so that the vending machine can continuously adjust the recommendation result when new information of a user appears, and the contradiction between the recommendation result and the product shortage is avoided. Meanwhile, the implementation system of the invention acquires information through interaction with the user, the system does not depend on repeated information purchase of the user, namely, the problem of cold start does not exist, the system has fillability, and according to the characteristic of information symbolization in the implementation of the recommendation method, a manager can add and delete new lipstick attributes and logic rules through a corresponding engine interface of the system so as to adapt to the dynamic changes of the lipstick attributes and the public cognition in the vending machine.
Description of the drawings:
FIG. 1 is a knowledge framework diagram of the present invention.
FIG. 2 is a diagram of a preferred embodiment of the present invention.
FIG. 3 is a flow chart of a recommendation method of the present invention.
Fig. 4 is a functional block diagram of a recommendation system according to the present invention.
Fig. 5 is a view showing an operation structure of the present invention applied to an unmanned lipstick dispenser.
Detailed Description
Example 1 knowledge framework of the invention
The knowledge framework network of the present invention is shown in fig. 1. The knowledge is described by using a frame representation method, and the knowledge frame of the method integrates information of the personal characteristics of the user, the requirements of the user, the lipstick attributes and common knowledge, wherein the common knowledge is similar to the description of expert knowledge and comprises the following steps: the young is suitable for the light color, the matte lipstick is not suitable for users with high requirements on glossiness, and the like, the condition establishment range is narrowed through a plurality of pieces of common knowledge in the logic rules, for example, the young is suitable for the light color, the after-sale machine has red color, peach color, pink color, and black skin is not suitable for the peach color and the pink color, so the recommended result is basically locked in the red color. The specific threshold values and the characteristics of the rule conditions in different dimensions can be adjusted according to the selling conditions of different vending machines and local public cognition. Meanwhile, according to the characteristic that the commodity performance range of the vending machine is small, the method defines the dimension for recommendation, the user dimension comprises nine dimensions represented in a knowledge frame, such as age, lip shape, skin color, persistence, lustering and the like, and the lipstick dimension comprises three dimensions of color, type and brand.
Example 2 recommendation model of the invention
The recommendation model of the present invention is shown in fig. 2. When no user preference exists, the lipstick color is recommended according to the age, the lip shape, the face shape and the skin color of the user, the lipstick type is recommended according to the requirements of occasions, the persistence degree and the glossiness degree, the lipstick brand is recommended according to the budget, and when the user preference exists, the color, the type and the brand are recommended according to the corresponding preference. There may be multiple values of user preferences, such as color only preference, or color and brand preference, but type no preference, and type is recommended according to other user dimensions. The value of the recommendation result can only be the value of the lipstick attribute existing in the vending machine. For example, the vending machine does not have a black lipstick, the color recommendation for which is not valued as black. Finally, combining the lipstick characteristics to be recommended according to the recommendation results on different lipstick dimensions, comparing the lipstick characteristics with the lipstick characteristics existing in the vending machine, judging whether the lipstick characteristics are matched, for example, the vending machine has red lipstick and the brands of the lancome, but does not have red lancome, namely, the combination of the inference results is not matched with the lipstick characteristics of the vending machine, and feeding back the shortage of goods.
The definition of the model specification contains non-monotonic logic semantics, for example, according to the traditional logic semantics, the user is less than 18 years old, the skin is white, the lips are thin, the face is sharp, red lipstick should be recommended according to the feature combination, but the user indicates that the preference of the user for the color is pink, which can overturn the existing knowledge and rules. And conflict resolution is realized by non-monotonic logic semantics, such as logic expressions < math > a \ b, not-c < math >, which indicate that c can be assumed to be false without generating contradiction, and at the same time, if b is true, the conclusion that a is true is concluded. When the method defines the model specification, the established expression is used for uniformly describing the problem of lipstick recommendation on the vending machine into the semantic form, and finally the inference rule is realized through a logic program. For example, describing the problem of recommending a lipstick color, color (X, red) ← F (X,18, white, thin, sharp) & -s (X), indicating that the user X has no preference information, recommending a lipstick of red color according to her age of 18, white skin, thin lip and sharp face, the above rule cannot be established when the user has preference information, and the expression color (X, pink) ← s (X) & p (pink) indicates that the user X has a preference, and the value of the preference is a preference for the lipstick color, which is a corresponding value, that is, pink. The order and description of the values in the expression are not limited, the form of the expression meets the non-monotonic logic semantics and can be mapped into a logic program to solve, namely, the model specification of the invention is met.
Example 3 recommendation method flow of the invention
The flow of the recommendation method of the present invention is shown in fig. 3. Firstly, describing knowledge by establishing different vectors, namely defining different dimensions considered in an inference model, wherein the specific method for describing the knowledge is to map the different dimensions into a representation form of the logic program on the knowledge. For example, age (X, a0) represents the age dimension, the value of user X is abstracted as a0, and the program is instantiated by acquiring the corresponding information of the user. The method for mapping into the logic program comprises the step of realizing the expression form of the logic program through an editor.
And then, describing rules according to a recommendation model, namely determining a recommendation result on one lipstick dimension according to the combination of different user dimensions, wherein the value of the recommendation result cannot exceed the lipstick characteristics of the vending machine, combining the recommendation results on different dimensions into a recommendation result vector, and generating different recommendation result vectors. For example, the budget of the user is 200 yuan, and according to the specific situation of the vending machine, lipstick brands corresponding to 170 yuan and 210 yuan are both used as brand recommendation results, so that two recommendation results can be combined, whether the two recommendation results can be established or not is judged respectively, and if the two recommendation results are established, the results are all fed back to the user to be selected. The generation of the recommendation result is implemented according to an inference model, the problems in the inference model are described according to model specifications, corresponding logic program rule statements are designed, and the logic program is solved;
and finally, determining values which cannot be simultaneously established in different lipstick dimensions according to the characteristic conditions of the lipstick of the vending machine, and formulating corresponding logic program constraint rules by taking the values as conditions to realize the judgment of matching between the recommendation result and the lipstick in the vending machine. For example, the vending machine has red lipstick and matte lipstick, but has no red matte lipstick, that is, "red" and "matte" are values that cannot be established simultaneously in different lipstick dimensions, so if the recommendation result includes red and matte, it is restricted by the constraint rule and cannot be recommended as lipstick, and only can reflect that the vending machine is out of stock, and this process is also implemented by the logic program body.
Embodiment 4 functional structure of recommendation system of the present invention
The functional structure of the recommendation system of the present invention is shown in fig. 4. The functional structure of the recommendation system comprises: the system comprises an acquisition module, a management updating module, an inference module, a result conversion module and a knowledge base. The knowledge base is an autonomously defined database, and stores user characteristic information, user demand information and lipstick attribute information by establishing corresponding data tables and fields. The realization of each functional module of the method can carry out component development through the specific statement of the python program.
An acquisition module: and the user-oriented system is used for analyzing the information input by the user, extracting the value on the corresponding dimension of the user and storing the value in a knowledge base. The acquisition mode can be form data or voice input, but the user is prompted to input complete information according to different dimensions of the method, incomplete or unmatched information can be detected, and if the condition occurs, the user is led to describe again.
A management update module: facing to the administrator, the system is used for adding and deleting the lipstick attribute information and the logic rules, storing the lipstick attribute information into a knowledge base, mapping the logic rules into specific logic statements and delivering the logic statements to the reasoning module. The mapping method can be realized through the file reading and writing function of the python program. The module can dynamically add rules according to the declarative and symbolic characteristics of the logic program, and adapt to the changes of vending machines and public cognition.
An inference module: the system is used for converting the contents in the knowledge base and the obtained logic program sentences into a logic program main body, generating a file form which can be identified by a solver, automatically generating a result by the solver, and delivering the result to a result conversion module. The generation of the recognizable file form can still be realized by reading and writing the file through the python statement, and the automatic solving of the logic program can be realized through the programming of the answer set. The solver is an execution system for solving logic programs, and is similar to an open-source answer set solver clingo and the like, and the execution of the solver comprises processes of instantiation and automatic result generation.
A result conversion module: and the device is used for converting the result generated by the solver into a representation form which can be understood by natural language and feeding back the representation form to a user. The conversion process can be realized by corresponding natural language processing statements and functions.
Embodiment 5 working structure of the invention applied to an unmanned lipstick vending machine
The working structure of the invention applied to the unmanned lipstick vending machine is shown in fig. 5, a user inputs information to a recommendation system in an internet of things cloud server platform through a recommendation function interface of an intelligent mobile terminal, and the recommendation system recommends lipstick to the user through solving. After the user successfully pays, the background server analyzes and sends the message to the long connection server, and the long connection server keeps long connection with the vending system terminal and sends a control instruction to the vending system terminal. Meanwhile, the staff implement logic knowledge and rule updating in the recommendation method by the intelligent mobile terminal and the management updating module facing the recommendation system. The intelligent mobile terminal is a mobile phone APP or other client side small programs, the Internet of things cloud server platform is a network server platform containing a recommendation system, a background server side and a long connection server side program, and the vending system terminal is an intelligent hardware platform capable of receiving instructions and controlling goods delivery.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention. In the above embodiments, the architecture of the server and the writing of the specific program script are conventional in the art, and on the basis of the design idea provided by the present invention, a person skilled in the art can select a corresponding programming language according to the programming habit of the person skilled in the art to implement.
Claims (5)
1. A commodity automatic recommendation method for an unmanned lipstick vending machine comprises the following steps:
1) establishing a user personal feature vector and a demand vector, and acquiring values of a user in different dimensions in the vectors; the vector is a description concept of related knowledge, the personal feature vector comprises four dimensions of age, lip shape, face shape and skin color, and the demand vector comprises five dimensions of occasion, persistence, lustering, budget and preference;
2) establishing lipstick attribute vectors and vector spaces thereof, and determining values in different dimensions in the vectors according to characteristics of the lipstick in different vending machines; the lipstick attribute vector comprises three dimensions of color, type and brand;
3) determining a recommendation result on a lipstick dimension according to the combination of different user dimensions; the value of the recommendation result is the value existing in the vector space in the step 2), and the recommendation results on different dimensions are combined into a recommendation result vector;
4) and judging whether the recommendation result vector can be matched with the lipstick attribute vector space, if so, taking the recommendation result vector as the final recommended lipstick description, and if not, feeding back the shortage of the vending machine.
2. The method for automatically recommending commodities of an unmanned lipstick vending machine as claimed in claim 1, wherein the step 1) specifically comprises: and mapping different user dimensions and lipstick dimensions into a logic program representation form of knowledge.
3. The method for automatically recommending commodities for an unmanned lipstick vending machine as claimed in claim 1, wherein the step 3) specifically comprises:
firstly, determining an inference model: recommending a lipstick color according to age, lip shape, face shape and skin color when there is no user preference information; recommending types according to occasions, persistence and lustering; recommending brands according to budgets; when user preference information exists, recommending colors, types and brands according to corresponding preferences;
secondly, defining model specification by non-monotonic logic semantics:
establishing a first expression: a (X, a)n)←F(X,f0,f1...fn)&S (X) means that assuming that the user X does not have preference information S, values for different conclusions are determined from the values of different conditions in the model, F (X, F)0,f1...fn) Representing user X, a set of values in different user dimensions, A (X, a)n) Representing the result recommended to user X in a lipstick dimension, anRepresents the corresponding value; establishing an expression II: a (X, a)n)←S(X)&P(pn) Indicates that the user X has preference information, determines a value, P (P), recommended to the user X in a lipstick dimension, based on the value in the preference dimensionn) Representing a user's value p in a preference dimensionn(ii) a Describing the specific problems in the inference model by the form of the expression;
and finally, mapping the problem description of the model into a representation form of a logic program rule statement, and determining a recommendation result by solving the logic program.
4. The method as claimed in claim 1, wherein said determining whether the recommendation vector matches the lipstick attribute vector space in step 4) comprises: determining values which cannot be established simultaneously in different lipstick dimensions according to lipstick characteristics in different vending machines; and mapping the values into a representation form of the constraint by a logic program, and automatically judging a matching result by a solving program.
5. The method as claimed in claim 1, wherein the method is implemented in an automatic product recommendation system of an unmanned lipstick vending machine, the recommendation system comprises: the system comprises an acquisition module, a management updating module, an inference module and a result conversion module;
the acquisition module is used for extracting the characteristics and the requirement information in the user input instruction, symbolizing the characteristics and the requirement information and storing the symbolized information into a knowledge base, wherein the knowledge base is a self-defined database and is used for storing the characteristics, the requirement and the lipstick attribute information of the user;
the management updating module is used for adding and deleting lipstick attribute information and logic rules, adding new lipstick attribute information into a knowledge base, mapping the rule updating into corresponding logic program statements and delivering the corresponding logic program statements to the reasoning module;
the reasoning module is used for converting the contents in the knowledge base and the obtained logic program sentences into a logic program main body, generating a file form which can be identified by a solver, automatically generating a result by the solver, and delivering the result to the result conversion module, wherein the solver is an execution system for solving the logic program;
and the result conversion module is used for converting the received solving result into a natural language form and feeding back the natural language form to the user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110134656.2A CN112749996B (en) | 2021-01-29 | 2021-01-29 | Automatic commodity recommendation method and system for unmanned lipstick vending machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110134656.2A CN112749996B (en) | 2021-01-29 | 2021-01-29 | Automatic commodity recommendation method and system for unmanned lipstick vending machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112749996A true CN112749996A (en) | 2021-05-04 |
CN112749996B CN112749996B (en) | 2024-02-20 |
Family
ID=75653466
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110134656.2A Active CN112749996B (en) | 2021-01-29 | 2021-01-29 | Automatic commodity recommendation method and system for unmanned lipstick vending machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112749996B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116523608A (en) * | 2023-07-03 | 2023-08-01 | 苏州大学 | Article sequence recommending method based on probability logic reasoning |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
CN107092516A (en) * | 2017-03-29 | 2017-08-25 | 东南大学 | A kind of inference method for combining body and default program |
CN107944093A (en) * | 2017-11-02 | 2018-04-20 | 广东数相智能科技有限公司 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
CN108376352A (en) * | 2017-02-01 | 2018-08-07 | 拉宜客株式会社 | The cosmetics of color with suitable user provide device and method |
CN108537566A (en) * | 2018-01-30 | 2018-09-14 | 深圳市阿西莫夫科技有限公司 | Commodity selling method, device and the cosmetics shelf of cosmetics shelf |
CN109597877A (en) * | 2018-11-08 | 2019-04-09 | 国家电网公司 | A kind of knowledge-based reasoning method and device |
CN110163715A (en) * | 2019-04-03 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Information recommendation method, device, equipment and system |
CN110659421A (en) * | 2019-09-26 | 2020-01-07 | 重庆集创家科技有限公司 | Commodity recommendation system of retail cabinet |
CN112017015A (en) * | 2020-10-30 | 2020-12-01 | 腾讯科技(深圳)有限公司 | Commodity information recommendation method, related device, equipment and storage medium |
CN112132660A (en) * | 2020-09-25 | 2020-12-25 | 尚娱软件(深圳)有限公司 | Commodity recommendation method, system, device and storage medium |
-
2021
- 2021-01-29 CN CN202110134656.2A patent/CN112749996B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
CN108376352A (en) * | 2017-02-01 | 2018-08-07 | 拉宜客株式会社 | The cosmetics of color with suitable user provide device and method |
CN107092516A (en) * | 2017-03-29 | 2017-08-25 | 东南大学 | A kind of inference method for combining body and default program |
CN107944093A (en) * | 2017-11-02 | 2018-04-20 | 广东数相智能科技有限公司 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
CN108537566A (en) * | 2018-01-30 | 2018-09-14 | 深圳市阿西莫夫科技有限公司 | Commodity selling method, device and the cosmetics shelf of cosmetics shelf |
CN109597877A (en) * | 2018-11-08 | 2019-04-09 | 国家电网公司 | A kind of knowledge-based reasoning method and device |
CN110163715A (en) * | 2019-04-03 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Information recommendation method, device, equipment and system |
CN110659421A (en) * | 2019-09-26 | 2020-01-07 | 重庆集创家科技有限公司 | Commodity recommendation system of retail cabinet |
CN112132660A (en) * | 2020-09-25 | 2020-12-25 | 尚娱软件(深圳)有限公司 | Commodity recommendation method, system, device and storage medium |
CN112017015A (en) * | 2020-10-30 | 2020-12-01 | 腾讯科技(深圳)有限公司 | Commodity information recommendation method, related device, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
夏杰: ""扩展的动态逻辑程序及其在产品信息个性化推荐中的应用"", 《中国优秀硕士学位论文全文数据库》, no. 3, pages 9 - 14 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116523608A (en) * | 2023-07-03 | 2023-08-01 | 苏州大学 | Article sequence recommending method based on probability logic reasoning |
CN116523608B (en) * | 2023-07-03 | 2023-08-29 | 苏州大学 | Article sequence recommending method based on probability logic reasoning |
Also Published As
Publication number | Publication date |
---|---|
CN112749996B (en) | 2024-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11501763B2 (en) | Machine learning tool for navigating a dialogue flow | |
US10725827B2 (en) | Artificial intelligence based virtual automated assistance | |
US11188928B2 (en) | Marketing method and apparatus based on deep reinforcement learning | |
US20180053234A1 (en) | Description information generation and presentation systems, methods, and devices | |
CN108664651B (en) | Pattern recommendation method, device and storage medium | |
CN111368789B (en) | Image recognition method, device, computer equipment and storage medium | |
CN112632403A (en) | Recommendation model training method, recommendation device, recommendation equipment and recommendation medium | |
CN107766853B (en) | Image text information generation and display method and electronic equipment | |
US20230107213A1 (en) | Method of generating virtual character, electronic device, and storage medium | |
CN112749996B (en) | Automatic commodity recommendation method and system for unmanned lipstick vending machine | |
US20200110771A1 (en) | Systems and methods for electronic communication, communication node classification, and communication node affinity mapping using machine learning | |
CN111310035A (en) | Recommendation method and device based on psychological and behavioral characteristics | |
CN113032676B (en) | Recommendation method and system based on micro-feedback | |
CN112307166B (en) | Intelligent question-answering method and device, storage medium and computer equipment | |
US20230119860A1 (en) | Matching system, matching method, and matching program | |
Hu et al. | Research on the brand image of iOS and Android smart phone operating systems based on mixed methods | |
US20230419139A1 (en) | Dynamic schema mapping between microservices | |
CN111445263A (en) | Information processing method, device, computer system and medium | |
CN113722577A (en) | Feedback information processing method, device, equipment and storage medium | |
CN113129093A (en) | Recommendation method and device for recommending commodities based on user data of smart community | |
KR20210041730A (en) | Method, apparatus and computer program for fashion item recommendation | |
CN113655895B (en) | Information recommendation method and device applied to input method and electronic equipment | |
CN115525448B (en) | Task processing method, device, equipment and medium based on heterogeneous platform | |
US20240177216A1 (en) | Digital avatar recommendation method and recommendation system | |
CN113220917B (en) | Background map recommendation method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |