CN111429174A - Commodity recommendation method, device, equipment and medium based on video analysis - Google Patents
Commodity recommendation method, device, equipment and medium based on video analysis Download PDFInfo
- Publication number
- CN111429174A CN111429174A CN202010177173.6A CN202010177173A CN111429174A CN 111429174 A CN111429174 A CN 111429174A CN 202010177173 A CN202010177173 A CN 202010177173A CN 111429174 A CN111429174 A CN 111429174A
- Authority
- CN
- China
- Prior art keywords
- commodity
- consumer
- association
- interest
- potential
- 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 57
- 238000004458 analytical method Methods 0.000 title claims abstract description 47
- 230000000295 complement effect Effects 0.000 claims abstract description 30
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity recommendation method based on video analysis, which comprises the following steps: establishing a commodity field body, and representing commodity categories, commodity examples and commodity associations in a form of graphs; representing a potential consumer model through consumer basic information, a consumer interest ontology and a consumer interest degree; obtaining a scored commodity example in a commodity field body according to a consumer interest body; through similar association, complementary association and scenario association among commodities and by combining commodity association rule data, commodities associated with the scored commodity examples in the consumer interest ontology are obtained in the commodity field ontology to form a recommended commodity candidate set; and predicting the interest degree of the commodity examples according to the similar association, complementary association and scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommending the commodity examples to potential consumers according to the interest degree. The invention also discloses a device, equipment and a medium. The invention can realize effective recommendation of commodities.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for recommending a commodity based on video analysis.
Background
In recent years, with the rapid development of communication networks, electronic trading platforms, and social media technologies, a great amount of information is generated on network platforms. For consumers, the lack of information makes the decisions irrational, and the excess information also makes the decisions difficult, so that it is necessary to improve the efficiency of information query and analysis for consumers.
Through the recommendation system and the navigation function thereof, a decision maker can quickly search commodities meeting the self demand in a large amount of network commodity information, so that the information searching cost is saved, and the decision maker is helpful for a consumer to get rid of the decision dilemma caused by 'information overload'. The method can cause the accuracy of similarity calculation between the user interest ontology and the recommended object instance to be influenced, different objects in the music field and the building field and semantic association relations among the objects are analyzed, a directed graph, namely a cross-field semantic concept model is constructed, the semantic association relations among the objects in the different fields are analyzed and knowledge reasoning is carried out on the basis of the directed graph, the objects or knowledge in the different fields are recommended to consumers, and cross-field recommendation is achieved.
However, conventionally, recommendation of complementary related objects is ignored, and comprehensive analysis of problems is not performed from the perspective of complementary correlation and contextual correlation between recommended objects, so that most recommended commodities are not commodities of users' minds, and some commodity recommendation systems search information of users at will without user consent, infringe on the rights and interests of users, and therefore improvement is needed.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a cloud computing automatic commodity recommendation method based on video analysis to solve the above-mentioned problems.
Based on the above purpose, one aspect of the present invention provides a method for recommending a commodity based on video analysis, including:
establishing a commodity field body, and representing commodity categories, commodity examples and commodity associations in a form of graphs;
establishing a potential consumer model, and expressing the potential consumer model through consumer basic information, a consumer interest body and a consumer interest degree;
obtaining a scored commodity example in a commodity field body according to a consumer interest body;
acquiring commodities associated with the scored commodity examples in the consumer interest body from the commodity field body through similar association, complementary association and scenario association among the commodities and combining commodity association rule data, and forming a recommended commodity candidate set;
and predicting the interest degree of the potential consumer to the commodity example according to the similar association, complementary association and scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommending the commodity example to the potential consumer according to the interest degree.
In some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
the consumer interest ontology is represented by a set of concepts of interest to the potential consumers, social network relationships between the potential consumers, attribute relationships between concepts or between the potential consumers, and a set of instances of goods of interest to the potential consumers.
In some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
the consumer interest level of the commodity instance by the potential consumer is represented by a value of the preference of the potential consumer for the commodity instance.
In some embodiments of the video analysis-based commodity recommendation method of the present invention, predicting interest level of a potential consumer in a commodity example according to similarity association, complementary association, and scenario association of commodities in a recommended commodity candidate set and a consumer interest ontology, and recommending the commodity example to the potential consumer according to the interest level further includes:
and respectively obtaining the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree through the similarity association, the complementary association and the scenario association among the commodity examples, and predicting the interest degree of the potential consumer in the commodity examples through the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree.
In some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
and calculating to obtain the hierarchical similarity according to the hierarchical relationship between the commodity examples, calculating to obtain the corresponding attribute similarity according to the attribute characteristics between the commodity examples, and obtaining the comprehensive commodity similarity according to the hierarchical similarity and the corresponding attribute similarity.
In another aspect of the embodiments of the present invention, there is also provided a commodity recommendation device based on video analysis, the device including:
the commodity field body building module is configured to build a commodity field body and express commodity categories, commodity examples and commodity associations in a form of graphs;
the potential consumer model building module is configured to build a potential consumer model, and the potential consumer model is represented by consumer basic information, a consumer interest body and a consumer interest degree;
the system comprises a scored commodity example acquisition module, a scoring commodity example acquisition module and a scoring module, wherein the scored commodity example acquisition module is configured to acquire a scored commodity example in a commodity field body according to a consumer interest body;
the system comprises a recommended commodity candidate set forming module, a recommended commodity candidate set forming module and a recommended commodity candidate set forming module, wherein the recommended commodity candidate set forming module is configured to acquire commodities related to scored commodity examples in a consumer interest body from a commodity field body through similar association, complementary association and scenario association among the commodities in combination with commodity association rule data and form a recommended commodity candidate set;
and the commodity example recommending module is configured to predict the interest degree of the potential consumer for the commodity example according to the similar association, complementary association and scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommend the commodity example to the potential consumer according to the interest degree.
In some embodiments of the video analytics-based item recommendation device of the present invention, the device further comprises:
a consumer interest ontology module configured to represent a consumer interest ontology through a set of concepts of interest to potential consumers, social network relationships between potential consumers, attribute relationships between concepts or between potential consumers, and a set of instances of merchandise of interest to potential consumers.
In some embodiments of the video analytics-based item recommendation device of the present invention, the device further comprises:
a consumer interest level module configured to represent the consumer interest level of the potential consumer in the instance of the good by a preference value of the potential consumer in the instance of the good.
In another aspect of the embodiments of the present invention, there is also provided a computer device, including:
at least one processor; and
and the memory stores a computer program capable of running on the processor, and the processor executes the program to execute the commodity recommending method based on the video analysis.
In another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided, where a computer program is stored, and is characterized in that when being executed by a processor, the computer program performs the aforementioned commodity recommendation method based on video analysis.
The invention has at least the following beneficial technical effects: the commodity recommendation method based on the commodity field ontology is beneficial to recommending commodities really needed by a user, searches all scored commodity examples in the commodity field ontology according to the commodity category, formalizes a potential consumer model, calculates the similarity of the commodities, predicts the interest of the consumer on the commodities according to the similarity, complementary correlation and situation correlation of the commodity examples and the scored commodities in the consumer interest ontology, predicts the interest of the consumer on the commodities according to the comprehensive commodity similarity of the commodity example type and the consumer interest ontology, and then recommends the consumer, so that the commodity with a mental appearance can be further recommended to the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by using the drawings without creative efforts.
FIG. 1 shows a schematic block diagram of an embodiment of a video analytics based item recommendation method in accordance with the present invention;
fig. 2 is a schematic structural diagram illustrating an embodiment of a video analysis-based goods recommendation method according to the present invention;
fig. 3 is a schematic diagram showing a single chip microcomputer structure of a central processing unit of an embodiment of a video analysis-based commodity recommendation device according to the present invention;
FIG. 4 is a schematic diagram illustrating the recommendation degree based on the similarity of commodities in different situations according to an embodiment of the commodity recommendation device based on video analysis of the present invention;
FIG. 5 is a schematic diagram illustrating a recommendation degree based on an association relationship between commodities according to an embodiment of the commodity recommendation device based on video analysis of the present invention;
fig. 6 is a schematic diagram illustrating a product example classification structure of an embodiment of a product recommendation device based on video analysis according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it is understood that "first" and "second" are only used for convenience of description and should not be construed as limiting the embodiments of the present invention, and the descriptions thereof in the following embodiments are omitted.
In view of the above, a first aspect of the embodiments of the present invention provides an embodiment of a commodity recommendation method based on video analysis. Fig. 1 is a schematic diagram illustrating an embodiment of a product recommendation method based on video analysis according to the present invention. In the embodiment shown in fig. 1, the method comprises at least the following steps:
s100, establishing a commodity field body, and representing commodity categories, commodity examples and commodity associations in a graph form;
s200, establishing a potential consumer model, and representing the potential consumer model through consumer basic information, a consumer interest body and a consumer interest degree;
s300, obtaining a scored commodity example in the commodity field body according to the consumer interest body;
s400, obtaining commodities associated with the scored commodity examples in the consumer interest body from the commodity field body through similar association, complementary association and scenario association among the commodities and commodity association rule data, and forming a recommended commodity candidate set;
s500, predicting interest degree of the potential consumers to the commodity examples according to similar association, complementary association and scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommending the commodity examples to the potential consumers according to the interest degree.
In some embodiments of the present invention, an automatic commodity recommendation method based on video analysis is provided, which predicts the interest level of a consumer in a commodity field ontology Dom _ O by modeling, plotting commodity categories, formalizing potential consumers (Customers) models, representing the basic information of the consumers by Customers _ Info, calculating the similarity of commodities, predicting the interest level of the consumer in the commodity field ontology cum _ O according to the commodity number Customers id in the Customers interest ontology Customers _ DOI, predicting the interest level of the consumer in the commodity according to the similarity, complementary correlation and scenario correlation of the commodity examples and the scored commodities in the Customers interest ontology cumbersto, predicting the interest level of the consumer in the commodity according to the comprehensive commodity similarity, comprehensive commodity complementary and scenario correlation of the types of the commodity examples and the Customers interest ontology, predicting the interest level of the consumer in the commodity examples according to the comprehensive commodity similarity, comprehensive commodity complementary level and commodity scenario correlation of the types of the commodity examples and the Customers interest ontology, and then, the consumer is recommended, which is beneficial to recommending the commodities really needed by the user.
The method specifically comprises the following steps:
firstly, modeling is carried out: respectively modeling the commodity and the potential consumer based on a domain ontology method, and establishing a commodity domain ontology Dom _ O and a potential consumer Model PC _ Model; the commodity domain ontology is represented as: dom _ O ═ { G, RH, RP, RS, RC, P }, where G represents a set of information in the domain having a certain hierarchical structure; RH refers to hierarchical associations between information or goods; RP refers to attribute association between concepts or between instances, which organizes different concepts and different instances into an organic whole; RC refers to the complementary relationship between concepts or instances; RS refers to a contextual relationship between concepts or between instances of a commodity; p refers to a collection of instances of a good, representing a particular collection of entities of a certain category. Drawing commodity types, commodity examples and the association thereof, presenting the commodity types, the commodity examples and the association in a graphic form, and sending the commodity types, the commodity examples and the association to a large market screen and a user side; formalizing a potential consumer (Customers) model as a triple: customers _ Model (Customers _ Info, Customers _ DOI, Customers _ Onto), which represents the basic information of the consumer, and is expressed as Customers _ Info { CustomersID, CName, CSex, CBirth, CPro-session }, which is used to represent the basic information of the consumer; customers _ Onto represents a consumer interest ontology; customers _ DOI represents consumer interest.
Then, calculating the similarity of the commodities: the similar association of the commodities refers to the association relationship generated by the similarity or similarity of categories, functions, attributes and the like among the commodities; if the commodity examples pi and pj belong to the same class or similar classes, the hierarchical similarity association between the pi and the pj is called; fig. 6 is a schematic diagram illustrating a classification structure of an example of a product according to an embodiment of the product recommendation device based on video analysis of the present invention, and as shown in fig. 6, the deeper the branch depth of the product example hierarchy intersecting path is, the farther the node is from the nearest common class, and the smaller the hierarchy similarity between them; the deeper the depth of the recent public class is, the more concrete the commodity examples pi and pj are, and the greater the hierarchical similarity between the commodity examples pi and pj is; d (pi) and D (pj) represent the depths of the commodity examples pi and pj, D (A) is the depth of the intersection node in the hierarchical intersection association, D represents the corresponding total depth, and then the hierarchical similarity between the commodity examples pi and pj is represented as:
if the commodity examples pi and pj respectively have x and y attributes and have k similar attributes, the attribute intersection correlation exists between the pi and the pj, the attribute similarity between the examples is reflected, when the more the attributes of the two commodity examples are the same, the larger k is, the more the categories of the two commodity examples are close, and the more the attribute values of the commodity examples are similar, the smaller the semantic correlation length L (PJAi) is, the larger the attribute similarity of the two commodity examples is, the corresponding attribute similarity is calculated according to the attribute characteristics between the commodity examples, and finally the comprehensive similarity of the commodity examples is obtained through synthesis.
Searching all scored commodity examples in a domain ontology Dom _ O according to a commodity number CustomersID in a consumer interest ontology Customers _ DOI; according to the similar association, complementary association and scenario association among the commodity examples and the association rule data in the actual sale of the commodity, all commodities associated with the scored commodity example in Customers _ Onto are found in Dom _ O, and a recommended commodity candidate set CS is formed, wherein the recommended commodity candidate set CS is respectively marked as PSim { p1Sim, p2Sim, …, pn1Sim }, PCom { p1Com, p2Com, …, pn2Com and PSce } { p1Sce, p2Sce, … and pn3Sce }.
FIG. 4 is a schematic diagram illustrating the recommendation degree based on the similarity of the product under different conditions according to the embodiment of the product recommendation device based on video analysis of the present invention; fig. 5 is a schematic diagram illustrating a recommendation degree based on an association relationship between commodities according to an embodiment of the commodity recommendation device based on video analysis of the present invention. As shown in fig. 4 and 5, the corresponding hierarchical similarity may be calculated according to the hierarchical relationship between the product examples, and the interest level of the consumer in the product may be predicted according to the similar association, complementary association, and scenario association between the product examples and the scored product in Customers _ Onto; and finally, predicting the interest degree of the consumer to the commodity example according to the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree of the commodity example type and the consumer interest ontology, and recommending the consumer.
According to some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
the consumer interest ontology is represented by a set of concepts of interest to the potential consumers, social network relationships between the potential consumers, attribute relationships between concepts or between the potential consumers, and a set of instances of goods of interest to the potential consumers.
In some embodiments of the present invention, Customers _ Onto represents a user interest ontology, denoted as Customers _ Onto { C, RN, RP, P }, where C represents a set of concepts in which consumers are interested, RN represents a Social Network Relationship (Social Network Relationship) between consumers, RP represents an attribute Relationship between concepts or between consumers, and P represents a set of instances of goods in which users are interested.
According to some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
the consumer interest level of the commodity instance by the potential consumer is represented by a value of the preference of the potential consumer for the commodity instance.
In some embodiments of the invention, Customers _ DOI represents consumer interest, denoted as Customers _ DOI ═ Customers ID, pi, Di (t), t, where pi (1 ≦ i ≦ n) is used to represent the ith commodity instance in consumer interest ontology P, Di (t) (-1 ≦ Di (t) ≦ 1) represents the consumer's preference for commodity instance pi at time t, when the consumer is interested in the commodity, Di (t) is positive, otherwise negative; the value of di (t) will change over time.
According to some embodiments of the video analysis-based commodity recommendation method of the present invention, predicting interest level of a potential consumer in a commodity example according to similarity association, complementary association, and scenario association of commodities in a recommended commodity candidate set and a consumer interest ontology, and recommending the commodity example to the potential consumer according to the interest level further includes:
and respectively obtaining the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree through the similarity association, the complementary association and the scenario association among the commodity examples, and predicting the interest degree of the potential consumer in the commodity examples through the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree.
In some embodiments of the invention, the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree are respectively obtained through the similarity association, the complementary association and the scenario association between the commodity examples, and then the interestingness of the consumer to the commodity example is predicted according to the comprehensive commodity similarity, the comprehensive commodity complementation degree and the commodity scenario association degree of the commodity example type and the consumer interest ontology respectively, and then the consumer is recommended.
According to some embodiments of the video analysis-based merchandise recommendation method of the present invention, the method further comprises:
and calculating to obtain the hierarchical similarity according to the hierarchical relationship between the commodity examples, calculating to obtain the corresponding attribute similarity according to the attribute characteristics between the commodity examples, and obtaining the comprehensive commodity similarity according to the hierarchical similarity and the corresponding attribute similarity.
In some embodiments of the present invention, the similar association of the commodities refers to an association relationship between the commodities due to the same or similar categories, functions, attributes, and the like; the corresponding hierarchical similarity can be calculated according to the hierarchical relationship among the commodity examples, the corresponding attribute similarity is calculated according to the attribute characteristics among the commodity examples, and finally the comprehensive similarity of the commodity examples is obtained through synthesis. A plurality of similar commodities can be provided for the user, and the selectivity of the user is greatly enriched.
In some embodiments of the present invention, fig. 2 is a schematic structural diagram illustrating an embodiment of a video analysis-based product recommendation method according to the present invention. As shown in fig. 2, the system for carrying the video-analysis-based product recommendation method of the present invention includes a central processing unit and a power supply unit, the central processing unit is electrically connected to a picture data processing unit, and preferably, the picture data processing unit includes product data analysis, product data statistics, product data synthesis, and product data classification. The system comprises a network cloud, a merchant, a central processing unit, a user terminal and a display unit, wherein the merchant sends commodity images to the network cloud, the central processing unit is in signal connection with the user terminal and the display unit through a wireless signal receiving and sending unit, commodity information is displayed in the display unit, needed commodities are recommended to the user terminal, and preferably, the display unit comprises a large market screen and a Web page. The user terminal can provide the identity information and the records of the browsed commodities to the central processing unit voluntarily, and the product can be conveniently recommended to the user terminal without violating the will of the user. The power supply unit supplies power to the central processing unit.
Preferably, fig. 3 is a schematic diagram of a single chip microcomputer structure of a central processing unit according to an embodiment of the video analysis-based commodity recommendation device of the present invention, as shown in fig. 3, the central processing unit is an AT89C51 single chip microcomputer, the AT89C51 single chip microcomputer is programmed with a BP neural network algorithm, a data fusion technology is a new technology developed in recent years, the neural network is applied to various fields as a data fusion method, the neural network has induction, summarization, extraction, memory, association and fault tolerance, and the purpose of processing information is achieved by adjusting the interconnection relationship among a large number of internal nodes depending on the complexity of the system.
Preferably, for the network security of the user terminal and the system, the user management and the authority management of the application system should fully utilize the security of the operating system and the database; the program writing of the application system should take security into consideration, and any place where a user may input needs to be checked by an input security unit, so that the data input by the user is guaranteed to be legal and effective; mobile client software security considerations; the mobile client software is bound, only the verified mobile device can enter the system, and the unbound device denies access.
In another aspect of the embodiments of the present invention, an embodiment of a commodity recommendation device based on video analysis is provided. The device includes:
the commodity field body building module is configured to build a commodity field body and express commodity categories, commodity examples and commodity associations in a form of graphs;
the potential consumer model building module is configured to build a potential consumer model, and the potential consumer model is represented by consumer basic information, a consumer interest body and a consumer interest degree;
the system comprises a scored commodity example acquisition module, a scoring commodity example acquisition module and a scoring module, wherein the scored commodity example acquisition module is configured to acquire a scored commodity example in a commodity field body according to a consumer interest body;
the system comprises a recommended commodity candidate set forming module, a recommended commodity candidate set forming module and a recommended commodity candidate set forming module, wherein the recommended commodity candidate set forming module is configured to acquire commodities related to scored commodity examples in a consumer interest body from a commodity field body through similar association, complementary association and scenario association among the commodities in combination with commodity association rule data and form a recommended commodity candidate set;
and the commodity example recommending module is configured to predict the interest degree of the potential consumer for the commodity example according to the similar association, complementary association and scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommend the commodity example to the potential consumer according to the interest degree.
According to some embodiments of the video analytics-based item recommendation device of the present invention, the device further comprises:
a consumer interest ontology module configured to represent a consumer interest ontology through a set of concepts of interest to potential consumers, social network relationships between potential consumers, attribute relationships between concepts or between potential consumers, and a set of instances of merchandise of interest to potential consumers.
According to some embodiments of the video analytics-based item recommendation device of the present invention, the device further comprises:
a consumer interest level module configured to represent the consumer interest level of the potential consumer in the instance of the good by a preference value of the potential consumer in the instance of the good.
In view of the above object, another aspect of the embodiments of the present invention further provides a computer device, including: at least one processor; and a memory storing a computer program operable on the processor, the processor executing the program to perform the aforementioned video-analysis-based merchandise recommendation method.
In another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided, where a computer program is stored, and is characterized in that when being executed by a processor, the computer program performs the aforementioned commodity recommendation method based on video analysis.
As such, those skilled in the art will appreciate that all of the embodiments, features and advantages set forth above with respect to the video analytics based merchandise recommendation method according to the present invention apply equally to the apparatus, computer device and media according to the present invention. For the sake of brevity of the present disclosure, no repeated explanation is provided herein.
It should be particularly noted that, the steps in the above-mentioned various embodiments of the method, apparatus, device and medium for recommending goods based on video analysis may be mutually intersected, replaced, added and deleted, so that these reasonable permutations and combinations of the method, apparatus, device and medium for recommending goods based on video analysis should also belong to the scope of the present invention, and should not limit the scope of the present invention to the embodiments.
Finally, it should be noted that, as one of ordinary skill in the art can appreciate that all or part of the processes of the methods of the above embodiments can be implemented by a computer program to instruct related hardware, and the program of the method for recommending goods based on video analysis can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the methods described above. The storage medium of the program may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like. The embodiments of the computer program may achieve the same or similar effects as any of the above-described method embodiments.
Furthermore, the methods disclosed according to embodiments of the present invention may also be implemented as a computer program executed by a processor, which may be stored in a computer-readable storage medium. Which when executed by a processor performs the above-described functions defined in the methods disclosed in embodiments of the invention.
Further, the above method steps and system elements may also be implemented using a controller and a computer readable storage medium for storing a computer program for causing the controller to implement the functions of the above steps or elements.
Further, it should be understood that the computer-readable storage media (e.g., memory) herein may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory, by way of example and not limitation, nonvolatile memory may include Read Only Memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory volatile memory may include Random Access Memory (RAM), which may serve as external cache memory, by way of example and not limitation, RAM may be available in a variety of forms, such as synchronous RAM (DRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link DRAM (S L DRAM, and Direct Rambus RAM (DRRAM).
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as software or hardware depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments of the present invention.
The various illustrative logical blocks, modules, and circuits described in connection with the disclosure herein may be implemented or performed with the following components designed to perform the functions herein: a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP, and/or any other such configuration.
The steps of a method or algorithm described in connection with the disclosure herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
In one or more exemplary designs, the functions may be implemented in hardware, software, firmware, or any combination thereof.A computer readable medium includes a computer storage medium and a communication medium including any medium that facilitates transfer of a computer program from one location to another.A storage medium may be any available medium that can be accessed by a general purpose or special purpose computer.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (10)
1. A commodity recommendation method based on video analysis is characterized by comprising the following steps:
establishing a commodity field body, and representing commodity categories, commodity examples and commodity associations in a form of graphs;
establishing a potential consumer model, and representing the potential consumer model through consumer basic information, a consumer interest body and a consumer interest degree;
obtaining the scored commodity examples in the commodity field ontology according to the consumer interest ontology;
obtaining commodities associated with the scored commodity examples in the consumer interest ontology from the commodity field ontology through similar association, complementary association and scenario association among the commodities in combination with commodity association rule data, and forming a recommended commodity candidate set;
and predicting the interest degree of a potential consumer to the commodity example according to the similar association, the complementary association and the scenario association of the commodities in the recommended commodity candidate set and the consumer interest ontology, and recommending the commodity example to the potential consumer according to the interest degree.
2. The video analysis-based commodity recommendation method according to claim 1, further comprising:
the consumer interest ontology is represented by the set of concepts interested by the potential consumers, social network relationships among the potential consumers, attribute relationships among the concepts or among the potential consumers, and the set of merchandise instances interested by the potential consumers.
3. The video analysis-based commodity recommendation method according to claim 1, further comprising:
the value of the consumer interest of the potential consumer in the commodity instance is represented by the value of the preference of the potential consumer in the commodity instance.
4. The video analysis-based commodity recommendation method according to claim 1, wherein the predicting interest level of a potential consumer in the commodity instance according to the similarity association, the complementary association and the scenario association of the commodities and the consumer interest ontology in the recommended commodity candidate set, and recommending the commodity instance to the potential consumer according to the interest level further comprises:
and respectively obtaining comprehensive commodity similarity, comprehensive commodity complementation and commodity scenario association through the similarity association, the complementary association and the scenario association among the commodity examples, and predicting the interest degree of potential consumers in the commodity examples through the comprehensive commodity similarity, the comprehensive commodity complementation and the commodity scenario association.
5. The video analysis-based commodity recommendation method according to claim 4, further comprising:
and calculating to obtain the hierarchical similarity according to the hierarchical relationship between the commodity examples, calculating to obtain the corresponding attribute similarity according to the attribute characteristics between the commodity examples, and obtaining the comprehensive commodity similarity according to the hierarchical similarity and the corresponding attribute similarity.
6. An apparatus for recommending goods based on video analysis, said apparatus comprising:
the system comprises a commodity field body establishing module, a commodity field body establishing module and a commodity association module, wherein the commodity field body establishing module is configured to establish a commodity field body and express commodity categories, commodity examples and commodity associations in a graphic form;
a potential consumer model building module configured to build a potential consumer model, the potential consumer model being represented by consumer basic information, a consumer interest ontology, and a consumer interest degree;
a scored commodity example obtaining module configured to obtain the scored commodity example in the commodity field ontology according to the consumer interest ontology;
a recommended commodity candidate set forming module, configured to obtain commodities associated with the scored commodity examples in the consumer interest ontology from the commodity field ontology by combining similar association, complementary association and scenario association among the commodities with commodity association rule data, and form a recommended commodity candidate set;
a commodity example recommending module configured to predict interest degrees of potential consumers for the commodity examples according to the similar associations, the complementary associations and the scenario associations of the commodities in the recommended commodity candidate set and consumer interest ontologies, and recommend the commodity examples to the potential consumers according to the interest degrees.
7. The video analysis-based item recommendation device of claim 6, further comprising:
a consumer interest ontology module configured to represent a consumer interest ontology through the set of concepts of interest to the potential consumers, social network relationships between the potential consumers, attribute relationships between the concepts or between the potential consumers, and the set of instances of merchandise of interest to the potential consumers.
8. The video analysis-based item recommendation device of claim 6, further comprising:
a consumer interestingness module configured to represent the consumer interestingness of the commodity instance by the potential consumer's preference value for the commodity instance.
9. A computer device, comprising:
at least one processor; and
memory storing a computer program operable on the processor, wherein the processor, when executing the program, performs the method of any of claims 1-5.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010177173.6A CN111429174B (en) | 2020-03-13 | 2020-03-13 | Commodity recommendation method, device, equipment and medium based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010177173.6A CN111429174B (en) | 2020-03-13 | 2020-03-13 | Commodity recommendation method, device, equipment and medium based on video analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111429174A true CN111429174A (en) | 2020-07-17 |
| CN111429174B CN111429174B (en) | 2022-06-03 |
Family
ID=71546519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010177173.6A Active CN111429174B (en) | 2020-03-13 | 2020-03-13 | Commodity recommendation method, device, equipment and medium based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111429174B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781174A (en) * | 2021-09-13 | 2021-12-10 | 内蒙古师范大学 | Recommendation method and system for promoting consumers to obtain favorite commodities |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150379609A1 (en) * | 2014-06-30 | 2015-12-31 | Kobo Incorporated | Generating recommendations for unfamiliar users by utilizing social side information |
| CN107251075A (en) * | 2015-09-08 | 2017-10-13 | 深圳市赛亿科技开发有限公司 | A kind of merchandise news method for pushing |
| CN108198041A (en) * | 2018-01-23 | 2018-06-22 | 重庆裕嘉隆大数据产业有限公司 | A kind of Method of Commodity Recommendation based on time attenuator, terminal and medium |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
-
2020
- 2020-03-13 CN CN202010177173.6A patent/CN111429174B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150379609A1 (en) * | 2014-06-30 | 2015-12-31 | Kobo Incorporated | Generating recommendations for unfamiliar users by utilizing social side information |
| CN107251075A (en) * | 2015-09-08 | 2017-10-13 | 深圳市赛亿科技开发有限公司 | A kind of merchandise news method for pushing |
| CN108198041A (en) * | 2018-01-23 | 2018-06-22 | 重庆裕嘉隆大数据产业有限公司 | A kind of Method of Commodity Recommendation based on time attenuator, terminal and medium |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781174A (en) * | 2021-09-13 | 2021-12-10 | 内蒙古师范大学 | Recommendation method and system for promoting consumers to obtain favorite commodities |
| CN113781174B (en) * | 2021-09-13 | 2023-09-22 | 内蒙古师范大学 | Recommendation method and system for improving preference commodity obtained by consumer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111429174B (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Talón-Ballestero et al. | Using big data from customer relationship management information systems to determine the client profile in the hotel sector | |
| US10725981B1 (en) | Analyzing big data | |
| Couldry et al. | Real social analytics: A contribution towards a phenomenology of a digital world | |
| Bobadilla et al. | Recommender systems survey | |
| KR101419504B1 (en) | System and method providing a suited shopping information by analyzing the propensity of an user | |
| US9361320B1 (en) | Modeling big data | |
| Su et al. | Risk assessment for global supplier selection using text mining | |
| Ortega et al. | Artificial intelligence scientific documentation dataset for recommender systems | |
| Chen et al. | Dynamic clustering collaborative filtering recommendation algorithm based on double-layer network | |
| CN114118192A (en) | Training method, prediction method, device and storage medium of user prediction model | |
| De Maio et al. | Social media marketing through time‐aware collaborative filtering | |
| Dareshiri et al. | A recommender geoportal for geospatial resource discovery and recommendation | |
| CN112257959A (en) | User risk prediction method and device, electronic equipment and storage medium | |
| Arora | Big data analytics: The underlying technologies used by organizations for value generation | |
| Ramkumar et al. | A survey on mining multiple data sources | |
| Zhang et al. | The construction of a domain knowledge graph and its application in supply chain risk analysis | |
| Kim et al. | Topic-Driven SocialRank: Personalized search result ranking by identifying similar, credible users in a social network | |
| CN111429174B (en) | Commodity recommendation method, device, equipment and medium based on video analysis | |
| Yu et al. | A novel framework to alleviate the sparsity problem in context-aware recommender systems | |
| Zhang et al. | The approaches to contextual transaction trust computation in e‐Commerce environments | |
| Li | [Retracted] An Advertising Recommendation Algorithm Based on Deep Learning Fusion Model | |
| Billot et al. | Introduction to big data and its applications in insurance | |
| CN116401456A (en) | Portrayal method, system, equipment and storage medium | |
| Yoshida et al. | New performance index “attractiveness factor” for evaluating websites via obtaining transition of users’ interests | |
| Madaan et al. | Big data analytics: A literature review paper |
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 |