CN113837846B - Commodity recommendation method, commodity recommendation device, computer equipment and storage medium - Google Patents
Commodity recommendation method, commodity recommendation device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113837846B CN113837846B CN202111256776.6A CN202111256776A CN113837846B CN 113837846 B CN113837846 B CN 113837846B CN 202111256776 A CN202111256776 A CN 202111256776A CN 113837846 B CN113837846 B CN 113837846B
- Authority
- CN
- China
- Prior art keywords
- commodity
- feature
- words
- complemented
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (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, computer equipment and a storage medium. The method comprises the following steps: acquiring recommendation scores of all commodities, wherein the recommendation scores are used for identifying recommendation values of all the commodities; determining target commodities to be recommended based on the recommendation scores of the commodities; the determining method of the recommendation score of the commodity comprises the following steps: the comment heat information of the commodity is obtained, and the comment information of the commodity is obtained; determining characteristic words of the commodity based on a commodity knowledge graph, comment heat information and comment information of the commodity, wherein the characteristic words are used for identifying characteristic information of the commodity; and determining the recommendation score of the commodity according to the time parameter, the comment heat information of the commodity and the emotion word score associated with each feature word. The method can improve the commodity recommendation precision.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for recommending commodities.
Background
With the development of internet technology, electronic commerce systems are widely used, and commodity information in the electronic commerce systems is continuously amplified, so that the problem of information overload is also brought. To solve this problem, commodity recommendation has been developed which deduces the user's preference and recommends the commodity of interest to the user by analyzing information such as past purchase records of the user or popularity of the commodity.
However, the current recommendation system mainly researches the relationship between users and between commodities, but does not intensively research much information of the users and the commodities themselves, and finally, cannot accurately recommend corresponding commodities to the users.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a commodity recommendation method, apparatus, computer device, and storage medium that can improve commodity recommendation accuracy.
A method of merchandise recommendation, the method comprising:
acquiring recommendation scores of all commodities, wherein the recommendation scores are used for identifying recommendation values of all the commodities;
determining target commodities to be recommended based on the recommendation scores of the commodities;
the determining method of the recommendation score of the commodity comprises the following steps:
acquiring comment information of the commodity, and acquiring heat information of feature words in the comment information;
determining target feature words of the commodity based on the commodity knowledge graph, comment information and heat information of feature words in the comment information, wherein the target feature words are used for identifying the feature information of the commodity;
and determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words and the score of the emotion words associated with each target feature word.
In one embodiment, the determining method of the heat information of the feature words in the comment information includes:
acquiring the times of clicking the commodity by a user, the time of browsing the commodity by the user and the times of occurrence of feature words in the comment information of the user;
and the times of clicking the commodity by the user, the time of browsing the commodity by the user and the times of occurrence of the characteristic words in the comment information of the user are respectively calculated with corresponding constants and used as heat information of the characteristic words in the comment information.
In one embodiment, the determining, based on the commodity knowledge graph, comment information and heat information of feature words in the comment information, a target feature word of the commodity, where the target feature word is used to identify feature information of the commodity includes:
determining an initial feature word set and an initial feature word set to be complemented of the commodity based on the commodity knowledge graph and comment information of the commodity;
determining target feature words to be complemented from the initial feature word set to be complemented according to the heat information of the feature words and the feature word frequency and word reverse collection frequency of the feature words to be complemented in the initial feature word set to be complemented;
and adding the target feature words to be complemented into the initial feature word set, and determining target feature words of the commodity.
In one embodiment, the determining, according to the heat information of the feature words and the initial feature word set to be complemented, the feature word frequency and the word reverse aggregation frequency of the complemented feature words, the target feature word to be complemented from the initial feature word set to be complemented includes:
multiplying the heat information of the feature words with the feature word frequency and word reverse collection frequency of the corresponding feature words to be complemented in the initial feature word set to obtain the total weight of the feature words to be complemented;
and determining the target feature word to be complemented based on the total weight of the feature words to be complemented.
In one embodiment, the determining the target feature word to be complemented based on the feature word total weight of each feature word to be complemented includes:
and selecting the feature words to be complemented with preset proportions from the feature words to be complemented based on the total weight of the feature words to be complemented, and taking the feature words to be complemented with preset proportions as target feature words to be complemented.
In one embodiment, the determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words and the emotion word score associated with each feature word includes:
and multiplying the time parameter, the heat information of the feature words and the emotion word score associated with each feature word to determine the recommendation score of the commodity.
In one embodiment, the method further comprises:
obtaining scores of comment information of the user on the commodity;
and determining similar commodities of the commodity based on the scores of the comment information of the commodity by the user.
A merchandise recommendation apparatus, the apparatus comprising:
the recommendation score acquisition module is used for acquiring recommendation scores of the commodities, wherein the recommendation scores are used for identifying recommendation values of the commodities;
the target commodity determining module is used for determining target commodities to be recommended based on the recommendation scores of the commodities;
the commodity information acquisition module is used for acquiring comment information of the commodity and acquiring heat information of feature words in the comment information;
the commodity feature word determining module is used for determining target feature words of the commodity based on a commodity knowledge graph, comment information and heat information of feature words in the comment information, wherein the target feature words are used for identifying feature information of the commodity;
and the recommendation score determining module is used for determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words and the score of the emotion words associated with each target feature word.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.
According to the commodity recommending method, the commodity recommending device, the computer equipment and the storage medium, the target commodity to be recommended is determined according to the obtained recommending scores of the commodities, and when the recommending scores of the commodities are determined, comment information of the commodities is obtained by obtaining comment heat information of the commodities; determining characteristic words of the commodity based on the commodity knowledge graph, comment heat information and comment information of the commodity, wherein the characteristic words are used for identifying characteristic information of the commodity; and determining the recommendation score of the commodity according to the time parameter, the comment heat information of the commodity and the emotion word score associated with each feature word. The commodity knowledge graph, the comment information of the commodity and the heat information of the feature words in the comment information are combined for analysis, so that the intrinsic relation between the comment of the commodity and the comment can be determined, and the commodity recommendation accuracy can be improved through the method.
Drawings
FIG. 1 is an application environment diagram of a commodity recommendation method in one embodiment;
FIG. 2 is a flow chart of a method for recommending commodities according to an embodiment;
FIG. 3 is a flow chart of a method for recommending commodities according to an embodiment;
FIG. 4 is a block diagram of a commodity recommendation device according to an embodiment;
FIG. 5 is an internal block diagram of a computer device in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The commodity recommendation method provided by the application can be applied to an application environment shown in fig. 1, wherein the application environment can only relate to a terminal 102, can only relate to a server 104, and can also relate to a system of the terminal 102 and the server 104, wherein the terminal 102 communicates with the server 104 through a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers. Specifically, the terminal 102 or the server 104 completes a commodity recommendation method, which includes obtaining recommendation scores of commodities, wherein the recommendation scores are used for identifying recommendation values of the commodities; determining target commodities to be recommended based on the recommendation scores of the commodities; the determining method of the recommendation score of the commodity comprises the following steps: the comment heat information of the commodity is obtained, and the comment information of the commodity is obtained; determining characteristic words of the commodity based on a commodity knowledge graph, comment heat information and comment information of the commodity, wherein the characteristic words are used for identifying characteristic information of the commodity; and determining the recommendation score of the commodity according to the time parameter, the comment heat information of the commodity and the emotion word score associated with each feature word.
In one embodiment, as shown in fig. 2, a commodity recommendation method is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
step S202, obtaining recommendation scores of all commodities, wherein the recommendation scores are used for identifying recommendation values of all the commodities.
In one embodiment, the recommendation score of each commodity refers to the calculated recommendation scores of all commodities, the recommendation scores of the commodities can be used for identifying the favorite degree of the commodity to the user, and the favorite degree can represent the recommendation value of the commodity.
Step S204, determining target commodities to be recommended based on the recommendation scores of the commodities.
In one embodiment, after the recommendation score of each commodity is obtained, the target commodity to be recommended may be determined according to the recommendation score of the commodity, wherein after the recommendation score of the commodity is obtained, the commodity may be ranked from large to small according to the recommendation score of the commodity, the commodity with the high recommendation score may be regarded as the commodity which is more favored by the user group, and specifically, the first k commodities in the recommendation sequence may be given to the user.
In one embodiment, as shown in fig. 3, a process for determining a recommendation score of a commodity is provided, and the process is applied to the terminal 102 or the server 104, for example, and includes the following steps:
step S302, comment information of the commodity is obtained, and heat information of feature words in the comment information is obtained.
In one embodiment, the popularity information of the feature words refers to the popularity of each feature word in the comment information of the commodity, the comment information of the commodity refers to the comment information of a user of any commodity, wherein the popularity information of the feature words in the comment information of the commodity can be determined by the number of times the user clicks the commodity, the time of browsing the commodity by the user, the number of times the feature words appear in the comment information, and the like, the user comment information of a certain commodity can be obtained through an e-commerce platform such as naught, jingdong, and the like, and specifically, after the comment information of the user is obtained, the comment information with the number of words being less than the preset number of words can be removed, the preset number of words can be adjusted according to actual conditions, the preset number of words can be 100 words, the number of words can be 200 words, and the like, so that the accuracy of the subsequent processing of the comment information can be improved.
Step S304, determining target feature words of the commodity based on the commodity knowledge graph, comment information and heat information of feature words in the comment information, wherein the target feature words are used for identifying the feature information of the commodity.
In one embodiment, the knowledge graph of the commodity may refer to a graph formed by triples, where the knowledge graph of the commodity may be pre-established, and a basic form of the triples mainly includes entity 1, relationship, entity 2, attribute value, and the like, and the entity is the most basic element in the knowledge graph, for example, the commodity may be taken as an entity, for example, an electric fan is taken as entity 1, an air conditioner is taken as entity 2, different relationships exist between different entities, and the attribute mainly refers to an attribute, a feature, a characteristic, a feature, and a parameter that an object may have, such as refrigeration capacity, air quantity, and the like; the attribute value mainly refers to a value of an object specified attribute. Each entity may be identified by a globally unique ID (identity), each attribute-attribute value pair may be used to characterize the intrinsic properties of the entity, and a relationship may be used to connect two entities, characterizing the association between them.
Specifically, the entity may be an air conditioner, the corresponding feature words may be price, appearance, etc., the corresponding emotion words may be public way and beautiful, the feature words may be attributes of the entity, and the emotion words may be attribute words.
In one embodiment, based on the commodity knowledge graph, comment information and heat information of feature words in the comment information, target feature words of the commodity can be determined, wherein the target feature words are used for identifying feature information of the commodity.
And step S306, determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words and the score of the emotion words associated with each target feature word.
In one embodiment, the time parameter is a set time period, which is used for determining a recommendation score of the commodity in the time period, the emotion word score associated with each target feature word is a score of an emotion word associated with each target feature word, for example, the target feature word may be a price, the emotion word corresponding to the target feature word may be positive emotion (good, comfortable), neutral emotion (general, fair), and negative emotion (bad, poor, uncomfortable), the score corresponding to the positive emotion may be set to 1, the score corresponding to the neutral emotion is 0, the score corresponding to the negative emotion is-1, and the recommendation score of the commodity may be determined through the time parameter, comment heat information of the commodity, and the emotion word score associated with each feature word. Therefore, the recommendation score of the commodity can be determined from the time angle, the heat of the feature words and the emotion word score associated with the target feature words, and the commodity recommendation precision can be improved by considering a plurality of factors which possibly influence the commodity recommendation score.
In the commodity recommendation method, according to the obtained recommendation scores of the commodities, the target commodities to be recommended are determined according to the recommendation scores of the commodities, wherein when the recommendation scores of the commodities are determined, comment information of the commodities is obtained by obtaining comment heat information of the commodities; determining characteristic words of the commodity based on the commodity knowledge graph, comment heat information and comment information of the commodity, wherein the characteristic words are used for identifying characteristic information of the commodity; and determining the recommendation score of the commodity according to the time parameter, the comment heat information of the commodity and the emotion word score associated with each feature word. The commodity knowledge graph, the comment information of the commodity and the heat information of the feature words in the comment information are combined for analysis, so that the intrinsic relation between the comment of the commodity and the comment can be determined, and the commodity recommendation accuracy can be improved through the method.
In one embodiment, the determining method of the heat information of the feature words in the comment information includes:
acquiring the times of clicking the commodity by a user, the time of browsing the commodity by the user and the times of occurrence of feature words in the comment information of the user;
and respectively carrying out constant operation on the times of clicking the commodity by the user, the time of browsing the commodity by the user and the times of occurrence of the characteristic words in the comment information of the user, and using the times of occurrence of the characteristic words as heat information of the characteristic words in the comment information.
In one embodiment, reference is made to equation 1:
wherein H is i G represents the number of times the user clicks on the commodity i K represents the time of browsing commodity by user i The number of occurrences of each feature word when a user reviews the merchandise is indicated,μ、/>the constant is a weight smaller than 1, and the number of times the user clicks the commodity, the time the user browses the commodity and the number of times the feature word appears in the comment information of the user are respectively calculated with the corresponding constant and used as the heat information of the feature word in the comment information. Clicking on the goods by the userThe number of times of browsing the commodity by the user and the number of times of occurrence of each feature word are calculated to obtain the heat information of the feature word in the comment information, so that the heat information of the feature word in the comment information can be more accurately determined.
In one embodiment, the determining, based on the commodity knowledge graph, the comment heat information and the comment information of the commodity, a target feature word of the commodity, where the target feature word is used to identify feature information of the commodity includes: determining an initial feature word set and an initial feature word set to be complemented of the commodity based on the commodity knowledge graph and comment information of the commodity; determining target feature words to be complemented from the initial feature word set to be complemented according to the evaluation heat information, the feature word frequency and the word reverse collection frequency of the initial feature word set to be complemented, adding the target feature words to be complemented into the initial feature word set, and determining target feature words of the commodity.
In one embodiment, based on the commodity knowledge graph and the comment information of the commodity, an initial feature word set of the commodity is determined, specifically, as shown in formula 2:
F i ＝AF i ∩BF i
the set formed by the attributes of the commodity entity i in the commodity knowledge graph may be defined as a commodity feature set bfi= { bf1, bf2, }, the set formed by the comment information of the commodity may be defined as a comment feature set afi= { af1, af2, }, and an intersection of the comment feature set and the commodity knowledge graph feature set is taken as an initial feature set fi= { f1, f 2.
In one embodiment, based on the commodity knowledge graph and the comment information of the commodity, an initial feature word set to be complemented of the commodity is determined, specifically, as shown in a formula 3:
RF i ＝AF i -BF i
wherein RF i Representing the initial feature word set to be complemented.
In one embodiment, the feature word frequency in the initial feature word set to be complemented refers to the occurrence frequency of the feature words, the word reverse aggregation frequency refers to the number of comments containing the feature words, and the target feature words to be complemented are determined from the feature word set to be complemented according to the comment heat information and the feature word frequency in the feature word set to be complemented and the word reverse aggregation frequency. Therefore, the method can determine the target feature word to be complemented.
In one embodiment, the determining the target feature word to be complemented from the initial feature word set to be complemented according to the evaluation heat information, the feature word frequency in the feature word set to be complemented, and the word reverse aggregation frequency includes: multiplying the evaluation heat information with the feature word frequency and the word reverse aggregation frequency of the corresponding feature words to be complemented in the feature word set to be complemented respectively to obtain the total weight of the feature words of each feature word to be complemented; and determining the target feature word to be complemented based on the total weight of the feature words to be complemented.
In one embodiment, as shown in equation 4:
STF-IDF′＝STF×SIDF×Hot i
wherein STF-IDF' represents the total weight of the feature words, STF represents the word frequency of the feature words, the reverse aggregate frequency of SIDF words and the Hot i And the popularity information of the feature words in the comment information is represented, the popularity information of the feature words in the comment information is multiplied with the feature word frequency and the word reverse aggregation frequency of the corresponding feature words to be complemented respectively in the feature word set to be complemented, and the total weight of the feature words to be complemented is obtained, so that the target feature words to be complemented can be determined through the method.
In one embodiment, the determining the target feature word to be complemented based on the feature word total weight of each feature word to be complemented includes:
and selecting the feature words to be complemented with preset proportions from the feature words to be complemented based on the total weight of the feature words to be complemented, and taking the feature words to be complemented with preset proportions as target feature words to be complemented.
In one embodiment, the words with values within a preset proportion range can be used as target feature words to be complemented according to the STF-IDF value sequence.
In one embodiment, the determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words in the evaluation information and the emotion word score associated with each feature word includes: and multiplying the time parameter, the heat information of the feature words in the evaluation information and the emotion word score associated with each feature word to determine the recommendation score of the commodity.
In one embodiment, as shown in equation 5:
Q＝Hot i 2 ×s×T
q represents the recommendation score of the commodity, and the recommendation score of the commodity is determined by multiplying the time parameter T, the heat information of the feature words in the comment information and the emotion word score S associated with each feature word. When the recommendation score of the commodity is calculated, the heat information of the feature words is fully considered, so that the recommendation accuracy of the recommendation of the commodity can be improved.
In one embodiment, the method further comprises the step of obtaining scores of comment information of the commodity by the user; and determining similar commodities of the commodity based on the scores of the comment information of the commodity by the user.
In one embodiment, in determining similar items of merchandise, the operation may be expanded according to the following formula:
where P represents the average score of the target user u for comment i,representing the score of target user u to comment i, Q u Representing the average score of predicted user u1 for similar good i, i representing the items not scored by predicted user u1, u1 representing the target useru's predicted users, n denotes the predicted user u1 set, sim (u, u 1) denotes the similarity between the target user u and the predicted user u 1.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 4, there is provided a commodity recommendation apparatus including: the system comprises a recommendation score acquisition module, a target commodity determination module, a commodity information acquisition module, a commodity feature word determination module and a recommendation score determination module, wherein:
a recommendation score obtaining module 402, configured to obtain a recommendation score of each commodity, where the recommendation score is used to identify a recommendation value of each commodity.
The target commodity determining module 404 is configured to determine a target commodity to be recommended based on the recommendation score of each commodity.
And the commodity information acquisition module 406 is used for acquiring comment information of the commodity and acquiring heat information of feature words in the comment information.
The commodity feature word determining module 408 is configured to determine a target feature word of the commodity based on a commodity knowledge graph, comment information, and heat information of feature words in the comment information, where the target feature word is used to identify feature information of the commodity.
The recommendation score determining module 410 determines a recommendation score of the commodity according to the time parameter, the heat information of the feature words and the score of the emotion word associated with each target feature word.
In one embodiment, the commodity information acquisition module is used for acquiring the number of times that the user clicks the commodity, the time that the user browses the commodity and the number of times that the feature word appears in the user comment information; and the times of clicking the commodity by the user, the time of browsing the commodity by the user and the times of occurrence of the characteristic words in the comment information of the user are respectively calculated with corresponding constants and used as heat information of the characteristic words in the comment information.
In one embodiment, the commodity feature word determining module is configured to determine an initial feature word set and an initial feature word set to be complemented of the commodity based on the commodity knowledge graph and comment information of the commodity; determining target feature words to be complemented from the initial feature word set according to the evaluation heat information, the feature word frequency in the initial feature word set to be complemented and the word reverse aggregation frequency in the feature word set to be complemented, adding the target feature words to be complemented into the initial feature word set, and determining target feature words of the commodity.
In one embodiment, the commodity feature word determining module is configured to multiply the evaluation heat information with the feature word frequency and the word reverse aggregation frequency of the corresponding feature word to be complemented in the initial feature word set to obtain a feature word total weight of each feature word to be complemented; and determining the target feature word to be complemented based on the total weight of the feature words to be complemented.
In one embodiment, the commodity feature word determining module is configured to select, based on a feature word total weight of each initial feature word to be complemented, a feature word to be complemented with a preset proportion from each initial feature word to be complemented as a target feature word to be complemented.
In one embodiment, the recommendation score determining module is configured to multiply the time parameter, comment heat information of the commodity, and emotion word scores associated with the feature words, so as to determine a recommendation score of the commodity.
In one embodiment, the commodity recommendation device further includes:
the similar commodity determining module is used for obtaining scores of comment information of the commodity by a user; and determining similar commodities of the commodity based on the scores of the comment information of the commodity by the user.
For specific limitations of the commodity recommendation device, reference may be made to the above limitation of the commodity recommendation method, and the description thereof will not be repeated here. The respective modules in the commodity recommendation apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing merchandise related data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a commodity recommendation method.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a commodity recommendation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the structures shown in fig. 5 and 6 are merely block diagrams of partial structures associated with the inventive arrangements and do not constitute a limitation of the computer device to which the inventive arrangements may be applied, and that a particular computer device may include more or less components than those shown, or may be combined with certain components, or may have a different arrangement of components.
In one embodiment, a computer device is provided that includes a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of the article recommendation method described above.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, implements the steps of the merchandise recommendation method described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method of recommending goods, the method comprising:
acquiring recommendation scores of all commodities, wherein the recommendation scores are used for identifying recommendation values of all the commodities;
determining target commodities to be recommended based on the recommendation scores of the commodities;
the determining method of the recommendation score of the commodity comprises the following steps:
acquiring the times of clicking the commodity by a user, the time of browsing the commodity by the user and the times of occurrence of feature words in comment information of the commodity; the times of clicking the commodity by the user, the time of browsing the commodity by the user and the times of occurrence of the characteristic words in the comment information of the commodity are respectively calculated with corresponding constants and used as heat information of the characteristic words in the comment information;
determining an initial characteristic word set and an initial characteristic word set to be complemented of the commodity based on the commodity knowledge graph and comment information of the commodity; multiplying the heat information of the feature words with the feature word frequency and word reverse collection frequency of the corresponding initial feature words to be complemented in the initial feature word set to obtain the total weight of the feature words of the initial feature words to be complemented; determining target feature words to be complemented based on the total weight of the feature words of the initial feature words to be complemented; adding the target feature words to be complemented into the initial feature word set, and determining target feature words of the commodity; the target feature words are used for identifying feature information of the commodity;
determining a recommendation score of the commodity according to a time parameter, the heat information of the feature words and the score of the emotion words associated with each target feature word, wherein the time parameter is a preset time period and is used for representing the time period for determining the recommendation score of the commodity; the score of the emotion words is the score of the emotion words associated with the preset target feature words.
2. The method of claim 1, wherein the determining the target feature word to be complemented based on the feature word total weight of each of the feature words to be complemented comprises:
and selecting the feature words to be complemented with preset proportions from the feature words to be complemented based on the total weight of the feature words to be complemented, and taking the feature words to be complemented with preset proportions as target feature words to be complemented.
3. The method of claim 1, wherein determining the recommendation score for the good based on the time parameter, the popularity information for the feature words, and the score for the emotion words associated with each of the feature words comprises:
and multiplying the time parameter, the heat information of the feature words and the score of the emotion words associated with the feature words to determine the recommendation score of the commodity.
4. The method as recited in claim 1, further comprising:
obtaining scores of comment information of the user on the commodity;
and determining similar commodities of the commodity based on the scores of the comment information of the commodity by the user.
5. A merchandise recommendation apparatus, the apparatus comprising:
the recommendation score acquisition module is used for acquiring recommendation scores of the commodities, wherein the recommendation scores are used for identifying recommendation values of the commodities;
the target commodity determining module is used for determining target commodities to be recommended based on the recommendation scores of the commodities;
the commodity information acquisition module is used for acquiring the times of clicking the commodity by a user, the time of browsing the commodity by the user and the times of occurrence of feature words in comment information of the commodity; the times of clicking the commodity by the user, the time of browsing the commodity by the user and the times of occurrence of the characteristic words in the comment information of the commodity are respectively calculated with corresponding constants and used as heat information of the characteristic words in the comment information;
the commodity feature word determining module is used for determining an initial feature word set and an initial feature word set to be complemented of the commodity based on a commodity knowledge graph and comment information of the commodity; multiplying the heat information of the feature words with the feature word frequency and word reverse aggregation frequency of the corresponding feature words to be complemented in the feature word set to be complemented to obtain the total weight of the feature words of each feature word to be complemented; determining target feature words to be complemented based on the total weight of the feature words to be complemented; adding the target feature words to be complemented into the initial feature word set, and determining target feature words of the commodity; the target feature words are used for identifying feature information of the commodity;
and the recommendation score determining module is used for determining the recommendation score of the commodity according to the time parameter, the heat information of the feature words and the score of the emotion words associated with each target feature word.
6. The merchandise recommendation apparatus according to claim 5, wherein the merchandise feature word determining module is configured to select a feature word to be complemented of a preset proportion from the initial feature words to be complemented as a target feature word to be complemented based on a feature word total weight of the initial feature words to be complemented.
7. The article recommendation device according to claim 5, wherein the recommendation score determining module is configured to multiply the time parameter, comment heat information of the article, and emotion word score associated with each of the feature words, to determine a recommendation score of the article.
8. The article recommendation device according to claim 5, further comprising: a similar commodity determination module;
the similar commodity determining module is used for obtaining scores of comment information of the commodity by a user; and determining similar commodities of the commodity based on the scores of the comment information of the commodity by the user.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111256776.6A CN113837846B (en) | 2021-10-27 | 2021-10-27 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111256776.6A CN113837846B (en) | 2021-10-27 | 2021-10-27 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113837846A CN113837846A (en) | 2021-12-24 |
| CN113837846B true CN113837846B (en) | 2023-09-22 |
Family
ID=78966392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111256776.6A Active CN113837846B (en) | 2021-10-27 | 2021-10-27 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837846B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017041372A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN109360058A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Method for pushing, device, computer equipment and storage medium based on trust network |
| CN111177559A (en) * | 2019-12-30 | 2020-05-19 | 中国联合网络通信集团有限公司 | Text travel service recommendation method and device, electronic equipment and storage medium |
| CN111260437A (en) * | 2020-01-14 | 2020-06-09 | 北京邮电大学 | Product recommendation method based on commodity aspect level emotion mining and fuzzy decision |
| CN112001773A (en) * | 2020-08-07 | 2020-11-27 | 北京三快在线科技有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN112989208A (en) * | 2021-04-30 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN113190752A (en) * | 2021-05-10 | 2021-07-30 | 上海传英信息技术有限公司 | Information recommendation method, mobile terminal and storage medium |
-
2021
- 2021-10-27 CN CN202111256776.6A patent/CN113837846B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017041372A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN109360058A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Method for pushing, device, computer equipment and storage medium based on trust network |
| CN111177559A (en) * | 2019-12-30 | 2020-05-19 | 中国联合网络通信集团有限公司 | Text travel service recommendation method and device, electronic equipment and storage medium |
| CN111260437A (en) * | 2020-01-14 | 2020-06-09 | 北京邮电大学 | Product recommendation method based on commodity aspect level emotion mining and fuzzy decision |
| CN112001773A (en) * | 2020-08-07 | 2020-11-27 | 北京三快在线科技有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN112989208A (en) * | 2021-04-30 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN113190752A (en) * | 2021-05-10 | 2021-07-30 | 上海传英信息技术有限公司 | Information recommendation method, mobile terminal and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| "基于知识图谱的个性化推荐系统研究与应用";吕刚;《中国优秀硕士学位论文全文数据库信息科技辑》;第1-42页 * |
| "融合知识图谱与用户评论的商品推荐算法";汤伟韬等;《计算机工程》;第1-10页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113837846A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866181B (en) | Resource recommendation method, device and storage medium | |
| US11823218B2 (en) | Customer clustering using integer programming | |
| CN108230058B (en) | Product recommendation method and system | |
| US10606883B2 (en) | Selection of initial document collection for visual interactive search | |
| CN111798273A (en) | Training method of purchase probability prediction model of product and purchase probability prediction method | |
| WO2019085327A1 (en) | Electronic device, product recommendation method and system, and computer readable storage medium | |
| WO2020238502A1 (en) | Article recommendation method and apparatus, electronic device and storage medium | |
| US11176586B2 (en) | Data analysis method and system thereof | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN111310046B (en) | Object recommendation method and device | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| CN113077317A (en) | Item recommendation method, device and equipment based on user data and storage medium | |
| US10937070B2 (en) | Collaborative filtering to generate recommendations | |
| WO2020221022A1 (en) | Service object recommendation method | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| CN111310038A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN112149003B (en) | Commodity community recommendation method and device and computer equipment | |
| CN113032668A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN115239421A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and commodity recommendation medium | |
| CN110827101A (en) | Shop recommendation method and device | |
| CN109325796B (en) | Potential user screening method, device, computer equipment and storage medium | |
| CN117435130A (en) | Financial data storage method, apparatus, computer device and storage medium | |
| CN113837846B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| CN111339434B (en) | Information recommendation method and device, electronic equipment and computer storage medium | |
| CN113076339A (en) | Data caching method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |