CN114202390A - Commodity recommendation method and device, electronic equipment and storage medium - Google Patents

Commodity recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114202390A
CN114202390A CN202111601212.1A CN202111601212A CN114202390A CN 114202390 A CN114202390 A CN 114202390A CN 202111601212 A CN202111601212 A CN 202111601212A CN 114202390 A CN114202390 A CN 114202390A
Authority
CN
China
Prior art keywords
commodity
user
determining
information
behavior data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111601212.1A
Other languages
Chinese (zh)
Inventor
张鹏
宋德超
李绍斌
吴伟
詹培旋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gree Electric Appliances Inc of Zhuhai
Zhuhai Lianyun Technology Co Ltd
Original Assignee
Gree Electric Appliances Inc of Zhuhai
Zhuhai Lianyun Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Gree Electric Appliances Inc of Zhuhai, Zhuhai Lianyun Technology Co Ltd filed Critical Gree Electric Appliances Inc of Zhuhai
Priority to CN202111601212.1A priority Critical patent/CN114202390A/en
Publication of CN114202390A publication Critical patent/CN114202390A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0623—Item investigation
    • G06Q30/0625—Directed, with specific intent or strategy
    • G06Q30/0627—Directed, with specific intent or strategy using item specifications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application relates to a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium, which are applied to the technical field of intelligent recommendation, wherein the method comprises the following steps: acquiring behavior data of a user; when determining that a user needs to recommend commodities, determining the attributes of the commodities to be recommended according to user behavior data; determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph; and recommending the target commodity for the user. The commodity recommendation method and device solve the problems that in the prior art, the accuracy and the success rate of commodity recommendation are low, and user experience is reduced.

Description

Commodity recommendation method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of intelligent recommendation technologies, and in particular, to a method and an apparatus for recommending a commodity, an electronic device, and a storage medium.
Background
Along with the improvement of living standard of people, more and more commodity products are used. At present, various manufacturers in the market put out various electrical equipment with different functions and specifications for selection. However, how to select the device meeting the user's needs from the full-line product often requires the user to spend a lot of time to select and compare different products. This process is cumbersome and time consuming, and sometimes even takes a significant amount of time and still does not pick out a satisfactory product.
Generally, the commodities are sold on public or own e-commerce platforms, and commodity information in the e-commerce platforms is very messy. In the related art, the recommendation of the commodities is mostly to recommend the same or similar commodities for the user, for example, after the user purchases one air conditioner, the e-commerce platform can recommend other categories or brands of air conditioners, and the possibility of purchasing the air conditioner again is low for the common user, so that the precision and the success rate of the commodity recommendation are low, and the user experience is reduced.
Disclosure of Invention
The application provides a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium, which are used for solving the problems that in the prior art, the precision and the success rate of commodity recommendation are low, and the user experience is reduced.
In a first aspect, an embodiment of the present application provides a commodity recommendation method, including:
acquiring behavior data of a user;
when the user needs to recommend the commodity, determining the attribute of the commodity to be recommended according to the user behavior data;
determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph;
and recommending the target commodity for the user.
Optionally, the process of constructing the knowledge graph includes:
acquiring a commodity data set;
comparing the commodity data in the commodity data set with a preset node set to determine node information in the commodity data, wherein the preset node set comprises commodity names and commodity attributes;
acquiring relationship information among the node information in the preset node set;
and constructing the knowledge graph according to the node information and the relationship information.
Optionally, the determining, from a pre-constructed knowledge graph, a target product associated with the product attribute includes:
determining target node information corresponding to the commodity attributes from the knowledge graph;
and determining the commodity associated with the target node information in the knowledge graph as the target commodity.
Optionally, the behavior data includes voice information or text information, and determining an attribute of the to-be-recommended commodity according to the user behavior data includes:
performing semantic analysis on voice information or text information, and determining a control instruction indicated in the voice information or text information;
and extracting control information in the control instruction, and taking the control information as the commodity attribute.
Optionally, the determining that the user needs to recommend the commodity includes:
performing emotion analysis on the behavior data to obtain emotion information of the user;
and if the emotional information is positive emotion, determining that the user needs to recommend the commodity.
Optionally, the determining that the user needs to recommend the commodity includes:
and determining that the commodity needs to be recommended for the user when the current commodity does not meet the use requirement of the user according to the behavior data.
Optionally, the determining that the user usage requirement is not met according to the behavior data includes:
determining a control instruction indicated by the behavior data acquired each time;
determining the repetition times of the same control instruction in a preset time length;
and if the repetition coefficient is greater than the preset times, determining that the current used commodity does not meet the use requirement of the user.
In a second aspect, an embodiment of the present application provides a commodity recommendation device, including:
the acquisition module is used for acquiring behavior data of a user;
when the user needs to recommend the commodity, determining the attribute of the commodity to be recommended according to the user behavior data;
determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph;
and recommending the target commodity for the user.
Optionally, the article recommending apparatus further includes:
a first acquisition unit for acquiring a commodity data set;
the first determining unit is used for comparing the commodity data in the commodity data set with a preset node set to determine node information in the commodity data, wherein the preset node set comprises commodity categories and commodity functions;
the second acquisition unit is used for acquiring the relationship information among the node information in the preset node set;
and the construction unit is used for constructing the knowledge graph according to the node information and the relation information.
Optionally, the second determining module includes:
the second determining unit is used for determining target node information corresponding to the commodity attributes from the knowledge graph;
and the third determining unit is used for determining the commodity associated with the target node information in the knowledge graph as the target commodity.
Optionally, the behavior data includes voice information or text information, and the first determining module includes:
the fourth determining unit is used for performing semantic analysis on the voice information or the text information and determining a control instruction indicated in the voice information or the text information;
and the extraction unit is used for extracting the control information in the control instruction and taking the control information as the commodity attribute.
Optionally, the first determining module includes:
the analysis unit is used for carrying out emotion analysis on the behavior data to obtain emotion information of the user;
and the fifth determining unit is used for determining that the user needs to recommend the commodity if the emotion information is positive emotion.
Optionally, the first determining module includes:
and the sixth determining unit is used for determining that the commodity needs to be recommended by the user when the using requirement of the user is determined not to be met according to the behavior data.
Optionally, the sixth determining unit includes:
a seventh determining unit configured to determine a control instruction indicated by the behavior data acquired each time;
the eighth determining unit is used for determining the repetition times of the same control instruction in the preset time length;
and the ninth determining unit is used for determining that the use requirement of the user is not met if the repetition times are greater than the preset times.
In a third aspect, an embodiment of the present application provides an electronic device, including: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
and a processor for executing the program stored in the memory to implement the product recommendation method of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the article recommendation method of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: according to the method provided by the embodiment of the application, the behavior data of the user is acquired; when determining that a user needs to recommend commodities, determining the attributes of the commodities to be recommended according to user behavior data; determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph; and recommending the target commodity for the user. Therefore, the commodity attribute to be recommended is determined through the behavior data of the user, the target commodity associated with the commodity attribute can be determined through the pre-established knowledge graph, the repeated mode of recommending the same type of commodity for the user is avoided, the commodity recommending accuracy is improved, and the user experience is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
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 for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is an application scenario diagram of a commodity recommendation method according to an embodiment of the present application;
fig. 2 is a flowchart of a commodity recommendation method according to an embodiment of the present application;
fig. 3 is a structural diagram of a product recommendation device according to an embodiment of the present application;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Before further detailed description of the embodiments of the present invention, terms and expressions referred to in the embodiments of the present invention are described, and the terms and expressions referred to in the embodiments of the present invention are applicable to the following explanations.
The knowledge graph is a modern theory which achieves the aim of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing a visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects. The three elements of knowledge graph comprise entity, relation and attribute. Entity refers to things that exist objectively and can be distinguished from each other, and can be concrete people, things, or abstract concepts or connections. An entity is the most basic element in a knowledge-graph. In the knowledge graph, the edges represent the relationship in the knowledge graph and are used for representing a certain relation between different entities. The entities and relationships in the knowledge graph may have respective attributes.
According to an embodiment of the present application, a method for recommending a commodity is provided. Alternatively, in the embodiment of the present application, the product recommendation method may be applied to a hardware environment formed by the terminal 101 and the server 102 as shown in fig. 1. As shown in fig. 1, a server 102 is connected to a terminal 101 through a network, which may be used to provide services (such as video services, application services, etc.) for the terminal or a client installed on the terminal, and a database may be provided on the server or separately from the server for providing data storage services for the server 102, and the network includes but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, a home appliance, or the like.
The product recommendation method according to the embodiment of the present application may be executed by the server 102, the terminal 101, or both the server 102 and the terminal 101. The terminal 101 may be configured to execute the product recommendation method according to the embodiment of the present application, or may be configured to execute the product recommendation method by a client installed thereon.
Taking the example of the product recommendation method executed by the server in the embodiment of the present application as an example, fig. 2 is a schematic flowchart of an optional product recommendation method according to the embodiment of the present application, and as shown in fig. 2, the flow of the method may include the following steps:
step 201, acquiring behavior data of a user.
In some embodiments, the behavior data of the user may be collected by the home device and sent to the server, for example, a behavior collection unit is provided on the home device, and the behavior of the user is collected by the behavior collection unit.
The behavior data of the user may include, but is not limited to, voice information, text information, video information, and/or image information. The corresponding behavior acquisition unit on the household equipment comprises a voice acquisition unit, a character acquisition unit, a video acquisition unit and/or an image acquisition unit.
Step 202, when determining that the user needs to recommend the commodity, determining the attribute of the commodity to be recommended according to the user behavior data.
In some embodiments, after the home equipment acquires the behavior data of the user, the behavior data of the user is analyzed correspondingly, so that the original intention of the user is determined from the behavior data of the user. The commodity attribute may be information indicating a function of the commodity or information indicating performance (e.g., energy consumption, power, life) of the commodity.
For example, taking the behavior data of the user as the voice information, and when the voice information is "too hot", it can be known that the actual demand of the user is cooling, and thus, it is determined that "cooling" is the attribute of the goods to be recommended.
In an optional embodiment, the behavior data includes voice information or text information, and the determining of the attribute of the to-be-recommended commodity according to the user behavior data includes:
performing semantic analysis on the voice information or the text information, and determining a control instruction indicated in the voice information or the text information; and extracting the control information in the control command, and taking the control information as the commodity attribute.
Specifically, after the server acquires the voice information or the text information, the voice information may be converted into the text information, and the text information is subjected to semantic analysis, so as to determine the control instruction indicated in the voice information or the text information. And after the control instruction is obtained, the commodity attribute is obtained by extracting the control information in the control instruction.
There are various ways to convert voice information into text information, for example, an Automatic voice Recognition technology (Automatic Speech Recognition) may be used to convert the voice information of the user into text information.
Illustratively, the voice information is regarded as being "too hot", the control instruction indicated by the voice information is determined as a cooling instruction through semantic analysis, and the "cooling" in the cooling instruction is extracted as the commodity attribute, so that when the commodity is recommended, the commodity capable of achieving cooling is recommended.
The semantic analysis of the text information may be performed by a text classification method, in which the text information is pre-processed (the pre-processing mainly includes word segmentation, and removal of conjunctions and adverbs), feature extraction (using a TF-IDF text feature extraction method), and classified according to features (by constructing a classification model in advance), so as to determine a control instruction indicated in the speech information or the text information. It is understood that the semantic analysis method provided in the related art may also be adopted, and is not limited herein.
In some embodiments, the determination that the user needs to recommend the goods may be obtained by the user by triggering a relevant button on the home device. The method comprises the steps that a commodity information search box can be arranged on the household equipment, and after a user inputs related commodity information and triggers search, the fact that the user needs to recommend commodities is determined. Or, the user can determine that the user needs to recommend the goods through the behavior data of the user.
In an alternative embodiment, determining that the user needs to recommend the item includes:
performing emotion analysis on the behavior data to obtain emotion information of the user; and if the emotional information is positive emotion, determining that the user needs to recommend the commodity.
In some embodiments, the behavior data is analyzed for emotion, and a multi-modal emotion analysis method can be used to determine the emotion information of the user. For example, the behavior data includes text information and image information, and the text information and the image information are subjected to multimodal emotion analysis to obtain emotional information that never exists. Or, the emotion information of the user can be determined directly by acquiring the image information of the user and by means of image recognition, for example, the expression of the user in the acquired image is in the mouth-corner direction, and the volume emotion information of the user is determined to be positive emotion.
In an alternative embodiment, determining that the user needs to recommend the item includes:
and when the use requirement of the user is determined not to be met according to the behavior data, determining that the user needs to recommend the commodity.
In some embodiments, the server determines whether the commodity used by the current user meets the use requirement of the current user by acquiring the behavior data of the user, and determines that the user needs to recommend the commodity after the use requirement of the user is not met.
There are various ways to determine that the currently used goods do not meet the use requirements of the user, for example, the following ways are used:
determining a control instruction indicated by the behavior data acquired each time; determining the repetition times of the same control instruction in a preset time length; and if the repetition times are greater than the preset times, determining that the use requirements of the user are not met.
In some embodiments, after the server acquires the user behavior data each time, the server determines the control instruction indicated by the user behavior data according to the user behavior data, and sends the control instruction to the currently used commodity to execute the operation corresponding to the control instruction. In the preset time, the user may generate behavior data for many times, so that the currently used commodity is controlled for many times, and if the user issues a control instruction for more than the preset times in the preset time, the currently used commodity can be considered to be unable to meet the use requirement of the user.
For example, taking a currently used commodity as an air conditioner as an example, a user gives a cooling instruction to the air conditioner after speaking 4 times of "too hot" exceeds a preset number of times within half an hour, and after the voice information of the previous three times is sent out, if the user still sends out the cooling instruction after the three times, the current air conditioner does not meet the use requirement of the user.
Step 203, determining the target goods related to the goods attributes from the pre-constructed knowledge graph.
In some embodiments, after determining the product attributes, the target product associated with the product attributes may be determined from a pre-constructed knowledge graph.
The knowledge graph is constructed according to information such as the commodity attribute and the commodity name, so that after the commodity attribute is determined, the target commodity related to the commodity attribute can be determined from the knowledge graph.
In an alternative embodiment, the process of constructing a knowledge-graph comprises:
acquiring a commodity data set; comparing the commodity data in the commodity data set with a preset node set to determine node information in the commodity data, wherein the preset node set comprises commodity categories and commodity functions; acquiring relationship information among node information in a preset node set; and constructing to obtain the knowledge graph according to the node information and the relation information.
The commodity data set can be obtained from an e-commerce platform or a database inside a commodity company. Generally, the commodity data includes commodity names, commodity prices, commodity performances, commodity attributes, and the like.
Wherein, price, after-sales and energy efficiency are the attributes of the device itself, and can also be the attributes created by the node. Therefore, the preset nodes in the graph include: a device node and a function node. The equipment nodes comprise three attributes of price, after-sale and energy efficiency, such as air conditioner price 3000, after-sale for 10 years and first-level energy efficiency; attributes in a function node are interpretations of functions.
It should be noted that the preset node set in the present application is a set of entities in the knowledge graph, the node information is an entity in the knowledge graph, and the relationship information is a relationship between the entities.
After the commodity data set is obtained, each commodity data in the commodity data set is compared with a preset node, and therefore data, which are identical to the preset node, in the commodity data are used as node information of the commodity data.
Based on the related embodiment, after the node information in each commodity data is determined, the relationship information between the nodes in the commodity data can be determined through the acquired relationship information between the node information, so that the knowledge graph can be constructed and obtained according to the node information, the relationship information and the attribute information of the node information and the relationship information in the commodity data.
The node information and the attribute information of the relationship information can be acquired from the commodity data. For example, the commodity data is commodity data of an air conditioner, and includes "5 p cold and warm floor standing cabinets, a fixed speed 380V shop office, a household commercial cabinet air conditioner, dual functions of cooling and heating, and primary energy efficiency", then, the cabinet air conditioner and the cooling and heating are node information, and the 5 p, 380V, the shop, the office, and the household are all attribute information, and generally, the air conditioner can implement cooling and heating, and therefore, the implementation can be used as relationship information between the cabinet air conditioner and the cold and warm.
In an alternative embodiment, determining the target product associated with the product attribute from the pre-constructed knowledge-graph comprises:
determining target node information corresponding to the commodity attributes from the knowledge graph; and determining the commodity associated with the target node information in the knowledge graph as a target commodity.
In some embodiments, after the commodity attribute is obtained, the target node information consistent with the commodity attribute can be determined from the pre-constructed knowledge graph according to the commodity attribute, and then the commodity associated with the target node information can be found from the knowledge graph.
And step 204, recommending the target commodity for the user.
In some embodiments, after the target item is determined, the target item may be recommended to the user.
The method includes the steps that a plurality of modes of recommending target commodities to users exist, for example, the names of the target commodities can be played through currently used commodities in a voice broadcasting mode; or sending the commodity information of the target commodity to home equipment of the user, and displaying the commodity information through the home equipment so as to be selected and checked by the user.
Generally, an interactive entrance of a smart home is voice, and a user can recommend other devices after purchasing a device with a voice entrance. In a specific embodiment, the commodity recommendation method of the present application mainly includes: constructing an intelligent home knowledge graph; triggering of a recommendation system; the interpretable recommendation is introduced to provide a suitable reason for recommendation for the user. The following is introduced in three parts:
intelligent household knowledge graph construction
A complete smart home knowledge map contains a lot of professional knowledge, but the knowledge is not necessary for users, and the attributes concerned by the users are generally the following: function, price, after-market and energy efficiency. Where price, after-sales and energy efficiency are attributes of the device itself, as well as attributes of the node creation. The nodes in the graph therefore include: equipment nodes (including three attributes of price, after-sales and energy efficiency, such as air conditioner price 3000, after-sales 10 years, first level energy efficiency); function nodes (attribute is an explanation of function, e.g. a humidifier-humidifier can leave room air less dry, can protect your respiratory tract). Relationships include relationships between devices and functions, such as humidifier-humidification, fan-cooling, as well as devices that may have multiple functions, such as air conditioning-refrigeration, heating, and air sweeping. Complementary relations (auxiliary and energy-saving) also exist among functions, for example, if the 'air conditioner refrigeration' has 'automatic curtain for blocking sunlight' and 'fan blowing', the refrigeration is faster, and the power consumption of the air conditioner can also be reduced.
When the knowledge graph is established, functional nodes are established, and then the connection between equipment and functions is established, for example, the air conditioner and the fan have the function of cooling, and the curtain can block sunlight in summer and can also assist in cooling. When the user reveals the cooling requirement, the corresponding function label can be found from the knowledge graph, and then the corresponding commodity can be found according to the corresponding function.
(II) trigger Condition setting
The trigger condition may be considered from several points of view: the first method comprises the following steps: triggering according to the mood of the user. Multimodal (including speech information, text information, and image information) emotion analysis can be introduced, triggering recommendations only if the user's emotion is detected as positive. And the second method comprises the following steps: and according to the use requirements of the user, corresponding recommendation is carried out only when the current equipment does not meet the user requirements. For example, if the user says that the equipment is too hot, if the current equipment can meet the requirement by adjusting the temperature to be low, the recommendation is not needed, and when the user emphasizes that the equipment cannot meet the requirement due to too hot for many times or the equipment can meet the requirement but the power consumption cost is too high, the recommendation of a corresponding scheme, such as recommending 'automatic curtain + fan'.
Among them, from the semantic understanding point of view, "too hot" can be considered as a synonym for "lowering the temperature", but this must be a negative emotion when the user emphasizes the same instruction multiple times. It is not appropriate to emphasize emotion again at this time, and it is more appropriate to directly solve the problem and give effective advice.
(III) interpretable recommendations
Interpretable recommendations are reasons for providing recommendations to the user by combining the relationships between functions with the attributes of the functions and devices. Many explanatory replies can be set in advance, and triggering can be performed when a specific situation is met. For example, if a user has a cooling demand, and then inquires the knowledge graph, three devices with cooling functions are provided, namely an air conditioner, a fan and a curtain. Its cavity mediation fan has direct cooling function, and the (window) curtain has supplementary cooling function, and the answer language can be set for as follows: the air conditioner A and the fan B are combined for use, so that a better cooling effect can be achieved, a user can try no more, and a curtain C can be used for assisting in cooling.
It should be noted that the above-mentioned behavior data of the user is obtained under the condition that the user authorization is obtained.
Based on the same concept, the embodiment of the present application provides a commodity recommendation device, and specific implementation of the device may refer to the description of the method embodiment section, and repeated details are not repeated, as shown in fig. 3, the device mainly includes:
an obtaining module 301, configured to obtain behavior data of a user;
the first determining module 302 is configured to determine an attribute of a commodity to be recommended according to user behavior data when it is determined that a user needs to recommend the commodity;
a second determining module 303, configured to determine, from a pre-constructed knowledge graph, a target product associated with a product attribute;
and the recommending module 304 is used for recommending the target commodity for the user.
Based on the same concept, an embodiment of the present application further provides an electronic device, as shown in fig. 4, the electronic device mainly includes: a processor 401, a memory 402 and a communication bus 403, wherein the processor 401 and the memory 402 communicate with each other via the communication bus 403. The memory 402 stores a program executable by the processor 401, and the processor 401 executes the program stored in the memory 402, so as to implement the following steps:
acquiring behavior data of a user;
when determining that a user needs to recommend commodities, determining the attributes of the commodities to be recommended according to user behavior data;
determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph;
and recommending the target commodity for the user.
The communication bus 403 mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 403 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 4, but this does not indicate only one bus or one type of bus.
The Memory 402 may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the aforementioned processor 401.
The Processor 401 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc., and may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.
In still another embodiment of the present application, there is also provided a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the article recommendation method described in the above-described embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions according to the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The available media may be magnetic media (e.g., floppy disks, hard disks, tapes, etc.), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives), among others.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method for recommending an article, comprising:
acquiring behavior data of a user;
when the user needs to recommend the commodity, determining the attribute of the commodity to be recommended according to the user behavior data;
determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph;
and recommending the target commodity for the user.
2. The merchandise recommendation method according to claim 1, wherein the process of constructing the knowledge-graph comprises:
acquiring a commodity data set;
comparing the commodity data in the commodity data set with a preset node set to determine node information in the commodity data, wherein the preset node set comprises commodity names and commodity attributes;
acquiring relationship information among the node information in the preset node set;
and constructing the knowledge graph according to the node information and the relationship information.
3. The item recommendation method according to claim 1 or 2, wherein the determining the target item associated with the item attribute from the pre-constructed knowledge graph comprises:
determining target node information corresponding to the commodity attributes from the knowledge graph;
and determining the commodity associated with the target node information in the knowledge graph as the target commodity.
4. The commodity recommendation method of claim 1, wherein the behavior data includes voice information or text information, and the determining the attributes of the commodity to be recommended according to the user behavior data includes:
performing semantic analysis on voice information or text information, and determining a control instruction indicated in the voice information or text information;
and extracting control information in the control instruction, and taking the control information as the commodity attribute.
5. The item recommendation method according to claim 1, wherein said determining that the user needs to recommend an item comprises:
performing emotion analysis on the behavior data to obtain emotion information of the user;
and if the emotional information is positive emotion, determining that the user needs to recommend the commodity.
6. The item recommendation method according to claim 1, wherein said determining that the user needs to recommend an item comprises:
and determining that the commodity needs to be recommended for the user when the current commodity does not meet the use requirement of the user according to the behavior data.
7. The commodity recommendation method according to claim 6, wherein said determining that the currently used commodity does not meet the use requirement of the user according to the behavior data comprises:
determining a control instruction indicated by the behavior data acquired each time;
determining the repetition times of the same control instruction in a preset time length;
and if the repetition coefficient is greater than the preset times, determining that the use requirement of the user is not met.
8. An article recommendation device, comprising:
the acquisition module is used for acquiring behavior data of a user;
when the user needs to recommend the commodity, determining the attribute of the commodity to be recommended according to the user behavior data;
determining a target commodity associated with the commodity attribute from a pre-constructed knowledge graph;
and recommending the target commodity for the user.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory for storing a computer program;
the processor is configured to execute the program stored in the memory to implement the product recommendation method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the item recommendation method of any one of claims 1-7.
CN202111601212.1A 2021-12-24 2021-12-24 Commodity recommendation method and device, electronic equipment and storage medium Pending CN114202390A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111601212.1A CN114202390A (en) 2021-12-24 2021-12-24 Commodity recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111601212.1A CN114202390A (en) 2021-12-24 2021-12-24 Commodity recommendation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114202390A true CN114202390A (en) 2022-03-18

Family

ID=80656498

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111601212.1A Pending CN114202390A (en) 2021-12-24 2021-12-24 Commodity recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114202390A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111563791A (en) * 2020-03-31 2020-08-21 北京奇艺世纪科技有限公司 Commodity dividing and recommending method and device, electronic equipment and storage medium
CN116051247A (en) * 2023-03-23 2023-05-02 新立讯科技股份有限公司 Multi-mode knowledge graph-based agriculture, forestry and animal husbandry product recommendation method and system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111563791A (en) * 2020-03-31 2020-08-21 北京奇艺世纪科技有限公司 Commodity dividing and recommending method and device, electronic equipment and storage medium
CN111563791B (en) * 2020-03-31 2023-12-26 北京奇艺世纪科技有限公司 Commodity dividing and recommending method and device, electronic equipment and storage medium
CN116051247A (en) * 2023-03-23 2023-05-02 新立讯科技股份有限公司 Multi-mode knowledge graph-based agriculture, forestry and animal husbandry product recommendation method and system

Similar Documents

Publication Publication Date Title
CN110825957B (en) Deep learning-based information recommendation method, device, equipment and storage medium
KR102345945B1 (en) Methods and systems for providing customized on-site information exchange
WO2020006835A1 (en) Customer service method, apparatus, and device for engaging in multiple rounds of question and answer, and storage medium
CN114202390A (en) Commodity recommendation method and device, electronic equipment and storage medium
JP6061729B2 (en) Product information providing system and product information providing program
CN105869015A (en) Information processing method and system
CN103534697B (en) For providing the method and system of statistics dialog manager training
US20200334730A1 (en) Internet of Things (IoT) Configurator
CN103377262A (en) Method and device for grouping users
WO2020228030A1 (en) Device recommendation method and apparatus, electronic device, and storage medium
CN109146707A (en) Power consumer analysis method, device and electronic equipment based on big data analysis
KR20190086126A (en) Manual retrieval service providing server and method using chatbot
WO2023124211A1 (en) Processing method and apparatus for set of customized household appliances, electronic device, and storage medium
JP5237337B2 (en) Object customization and management system
CN114581175A (en) Commodity pushing method and device, storage medium and electronic equipment
US10453103B2 (en) Price estimation system
CN110489531B (en) Method and device for determining high-frequency problem
KR102438679B1 (en) Operating method of server for providing media marketing service
JP6684970B1 (en) Analysis program, analysis method, and analysis device
KR102499688B1 (en) E-commerce product sales store management system based on bigdata and mehotd for providing integrated product evaluation information service thereof
CN110727853A (en) Presenting controlled heterogeneous digital content to a user
CN112163083B (en) Intelligent question-answering method, device, electronic equipment and storage medium
CN113724044A (en) User portrait based commodity recommendation, apparatus, computer device and storage medium
CN113011953A (en) Household appliance recommendation method and device, storage medium and electronic equipment
CN110889279B (en) Method and device for displaying display information in document

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