CN108984688A - Mother and baby's knowledge topic recommended method and device - Google Patents
Mother and baby's knowledge topic recommended method and device Download PDFInfo
- Publication number
- CN108984688A CN108984688A CN201810719230.1A CN201810719230A CN108984688A CN 108984688 A CN108984688 A CN 108984688A CN 201810719230 A CN201810719230 A CN 201810719230A CN 108984688 A CN108984688 A CN 108984688A
- Authority
- CN
- China
- Prior art keywords
- baby
- mother
- topic
- knowledge
- document
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The embodiment of the present application provides a kind of mother and baby's knowledge topic recommended method and device.This method comprises: being directed to each mother and baby's commodity, the descriptive labelling information of mother and baby's commodity and mother and baby's knowledge topic library with mother and baby's commodity association are obtained；The Topic Similarity in the descriptive labelling information and mother and baby's knowledge topic library between each mother and baby's knowledge topic document is calculated, Topic Similarity set is obtained；Recommendation document of the mother and baby's knowledge topic document for meeting preset rules as mother and baby's commodity is picked out according to the Topic Similarity set.It is that mother and baby user recommends mother and baby's knowledge topic relevant with mother and baby's commodity of browsing when thereby, it is possible to browse mother and baby's commodity for mother and baby user, so that mother and baby user be helped to become more apparent upon commodity and mother and baby's knowledge, so that mother and baby user is actively engaged in discussion, generates content of good.
Description
Technical field
This application involves text semantic analysis fields, in particular to a kind of mother and baby's knowledge topic recommended method and dress
It sets.
Background technique
The details page of mother and baby's commodity is the most important part of mother and baby's electric business website, usually mainly by descriptive labelling and commodity figure
Piece is constituted.General merchandise description is filled in by businessman or website operation, more formal and specification.Selecting for mother and baby's commodity is more special
Very, in addition to should also be understood that corresponding breed of commodity is known when most of it is to be understood that price etc. describes substantially the characteristics of commodity
Know, and further meets the discussion etc. for breeding topic about commodity of mother and baby user group's needs.It how to be female
Baby user recommend it is relevant with commodity breed knowledge and it is relevant with commodity breed topic, to help mother and baby user more
Commodity and mother and baby's knowledge are solved, is those skilled in the art's technical problem urgently to be resolved.
Summary of the invention
In order to overcome above-mentioned deficiency in the prior art, the application's is designed to provide a kind of mother and baby's knowledge topic recommendation
It is that mother and baby user recommends mother relevant with mother and baby's commodity of browsing that method and device, which can be when mother and baby user browses mother and baby's commodity,
Baby's knowledge topic, so that mother and baby user is actively engaged in discussion, produces so that mother and baby user be helped to become more apparent upon commodity and mother and baby's knowledge
Raw content of good.
To achieve the goals above, the embodiment of the present application the technical solution adopted is as follows:
In a first aspect, the embodiment of the present application provides a kind of mother and baby's knowledge topic recommended method, it is applied to server, the side
Method includes:
For each mother and baby's commodity, the descriptive labelling information of mother and baby's commodity and the mother with mother and baby's commodity association are obtained
Baby's knowledge topic library；
It calculates in the descriptive labelling information and mother and baby's knowledge topic library between each mother and baby's knowledge topic document
Topic Similarity obtains Topic Similarity set；
The mother and baby's knowledge topic document for meeting preset rules is picked out according to the Topic Similarity set as the mother and baby
The recommendation document of commodity.
Optionally, the descriptive labelling information for obtaining mother and baby's commodity and mother and baby's knowledge with mother and baby's commodity association
The step of topic library, comprising:
Obtain product features information of the mother and baby's commodity in the current presentation page, and using the product features information as
The descriptive labelling information, the product features information include at least product name, commodity classification, commodity title；
Go out mother and baby's knowledge topic library with mother and baby's commodity association based on the product features information retrieval.
Optionally, described to calculate each mother and baby's knowledge topic in the descriptive labelling information and mother and baby's knowledge topic library
Topic Similarity between document, the step of obtaining Topic Similarity set, comprising:
Each mother and baby's knowledge topic document in mother and baby's knowledge topic library is segmented, each mother and baby's knowledge is obtained
Multiple words in topic document；
LDA model training is input to using multiple words after participle as LDA mode input vector obtains the mother and baby know
Know the topic model expression in topic library, wherein the topic model expression includes each mother and baby in mother and baby's knowledge topic library
The theme of knowledge topic document indicates the theme indicates to include theme weight of each theme in mother and baby's knowledge topic document
Want degree；
The embedded expression that each theme is calculated and each word are expressed in conjunction with TWE model and the topic model
Embedded expression；
It is calculated based on topic model expression, the embedded expression of each theme and the embedded expression of each word
The probability of descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library, and will be described general
Rate is as the Topic Similarity between each mother and baby's knowledge topic document and the descriptive labelling information.
Optionally, described based on the embedding of topic model expression, the embedded expression of each theme and each word
Enter formula expression and calculates the general of descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library
The calculation formula of rate are as follows:
Wherein, Topic Similarity of the Sim (s, d) between the descriptive labelling information s and mother and baby's knowledge topic document d, P
(w|zk) it is embedded expression at each word w and each theme zkEmbedded expression between Topic Similarity, P (zk|
It d) is each theme zkEmbedded expression and each mother and baby's knowledge topic document d theme expression between Topic Similarity.
Optionally, described that the mother and baby's knowledge topic document for meeting preset rules is picked out according to the Topic Similarity set
The step of recommendation document as mother and baby's commodity, comprising:
By mother and baby's knowledge topic corresponding less than the Topic Similarity of the first preset threshold in the Topic Similarity set
Document is filtered；
Mother and baby's knowledge topic document remaining after filtering is ranked up according to Topic Similarity size, generates sequence knot
Fruit；
The mother and baby's knowledge topic document for meeting preset rules is picked out according to the ranking results as mother and baby's commodity
Recommend document.
Optionally, the mother and baby's knowledge topic document for meeting preset rules of being picked out according to the ranking results is as this
The step of recommendation document of mother and baby's commodity, comprising:
It chooses Topic Similarity size in the ranking results and is located at mother and baby's knowledge topic document of top n as the mother and baby
The recommendation document of commodity；Or
Choose all mother and baby's knowledge topics text that Topic Similarity size in the ranking results is greater than the second preset threshold
Recommendation document of the shelves as mother and baby's commodity.
Optionally, described that the mother and baby's knowledge topic document for meeting preset rules is picked out according to the Topic Similarity set
After the step of recommendation document as mother and baby's commodity, which comprises
When the merchandise display page for detecting mother and baby's commodity is opened, by the recommendation document display of mother and baby's commodity in the mother
In the merchandise display page of baby's commodity.
Second aspect, the embodiment of the present application also provide a kind of mother and baby's knowledge topic recommendation apparatus, are applied to server, described
Device includes:
Obtain module, for be directed to each mother and baby's commodity, obtain mother and baby's commodity descriptive labelling information and with the mother
Mother and baby's knowledge topic library of baby's commodity association；
Computing module is talked about for calculating each mother and baby's knowledge in the descriptive labelling information and mother and baby's knowledge topic library
The Topic Similarity between document is inscribed, Topic Similarity set is obtained；
Choosing module, for picking out the mother and baby's knowledge topic text for meeting preset rules according to the Topic Similarity set
Recommendation document of the shelves as mother and baby's commodity.
The third aspect, the embodiment of the present application also provide a kind of readable storage medium storing program for executing, are stored in the readable storage medium storing program for executing
Computer program, the computer program, which is performed, realizes above-mentioned mother and baby's knowledge topic recommended method.
In terms of existing technologies, the application has the advantages that
Mother and baby's knowledge topic recommended method provided by the embodiments of the present application and device are obtained first against each mother and baby's commodity
Take the descriptive labelling information of mother and baby's commodity and mother and baby's knowledge topic library with mother and baby's commodity association.Then, described in calculating
Topic Similarity in descriptive labelling information and mother and baby's knowledge topic library between each mother and baby's knowledge topic document, is led
Inscribe similarity set.Finally, picking out the mother and baby's knowledge topic document for meeting preset rules according to the Topic Similarity set
Recommendation document as mother and baby's commodity.It can be that mother and baby user is when browsing mother and baby's commodity by using above-mentioned technical proposal
Mother and baby user recommends the relevant mother and baby's knowledge topic of mother and baby's commodity with browsing, thus help mother and baby user become more apparent upon commodity and
Mother and baby's knowledge generates content of good so that mother and baby user is actively engaged in discussion.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the application scenarios schematic diagram of mother and baby's knowledge topic recommended method provided by the embodiments of the present application；
Fig. 2 is a kind of flow diagram of mother and baby's knowledge topic recommended method provided by the embodiments of the present application；
Fig. 3 is another flow diagram of mother and baby's knowledge topic recommended method provided by the embodiments of the present application；
Fig. 4 is the structure of the server provided by the embodiments of the present application for realizing above-mentioned mother and baby's knowledge topic recommended method
Block diagram；
Fig. 5 is the functional block diagram of mother and baby's knowledge topic recommendation apparatus shown in Fig. 4.
Icon: 100- server；110- bus；120- processor；130- storage medium；140- bus interface；150- net
Network adapter；160- user interface；200- mother and baby's knowledge topic recommendation apparatus；210- obtains module；220- computing module；230-
Choosing module；300- user terminal.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Usually herein
The component of the embodiment of the present application described and illustrated in place's attached drawing can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiments herein provided in the accompanying drawings is not intended to limit below claimed
Scope of the present application, but be merely representative of the selected embodiment of the application.Based on the embodiment in the application, this field is common
Technical staff's all other embodiment obtained without creative efforts belongs to the model of the application protection
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile the application's
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Referring to Fig. 1, a kind of application scenarios for mother and baby's knowledge topic recommended method provided by the embodiments of the present application are illustrated
Figure.In the present embodiment, the application scenarios include at least one user terminal 300 and at least one described user terminal
The server 100 of 300 communication connections.
In the present embodiment, the user terminal 300 can be PC, smart phone, tablet computer, wearable device
Etc., the present embodiment does not limit this in detail.
According to some embodiments of the present application, the user terminal 300 may include: comprising using processing unit and radio frequency/
The processing unit of digital signals processor；Display screen；It may include secondary or physical bond, the membrane keyboard being covered on display screen or their group
The keypad of conjunction；SIM card；It may include the storage of ROM, RAM, flash memory or their any combination
Device device；Wi-Fi and/or blue tooth interface；NFC chip connects for radio energy receiving coil, the radio telephone of wireless charging
Mouthful；Electric power management circuit with relevant battery；USB interface and connector；With relevant microphone, loudspeaker and earphone jack
Message management system；And the selectable appurtenances of various cameras, global positioning system, accelerator etc..This
Outside, various user terminal applications can be installed on user terminal 300, user terminal application can be used for allowing using user terminal
300 come transmit be suitable for other equipment operate order.This kind of application can be downloaded and installed to user from server 100
It, can also be installed on user terminal 300 in advance in the memory of terminal 300.In the embodiment of the present application, user terminal
It is mountable on 300 to there is the application of mother and baby's commodity (to can be APP application, wechat small routine, Alipay small routine, WEB light application etc.
Deng).Wherein, mother and baby's commodity application can give directions user to realize user's registration, user's login, articles storage, mother and baby's commodity
The functions such as browsing, mother and baby's commodity purchasing, mother and baby's knowledge topic browsing, user's invitation.
In the present embodiment, the server 100 should be understood the service point of offer processing, data bank, communications service.It lifts
For example, server 100 can refer to the single physical processor with related communication and data storage and document library facility, or
It can refer to the aggregate of networking or the processor gathered, related network and storing unit, and to software and one or more
The application software serviced provided by document library system and support server 100 is operated.Server 100 can configuration or
It is widely different in performance, but server 100 generally may include one or more central processing unit and storage unit.Service
Device 100 can also include one or more large-scale storage area equipment, one or more power supplys, one or more wired or wireless nets
Network component, one or more input output assemblies or one or more operating systems, such as, Windows Server, Mac
OS X, Unix, Linux, FreeBSD etc..
Further, referring to Fig. 2, being a kind of process of mother and baby's knowledge topic recommended method provided by the embodiments of the present application
Schematic diagram, the method server 100 as shown in Fig. 1 execute.It should be noted that mother and baby provided by the embodiments of the present application
Knowledge topic recommended method is not limitation with Fig. 2 and specific order as described below, which can be with
It is achieved by the steps of:
Step S210, for each mother and baby's commodity, obtain mother and baby's commodity descriptive labelling information and with the mother and baby quotient
The associated mother and baby's knowledge topic library of product.
In the present embodiment, mother and baby's commodity library S and the total library D of mother and baby's knowledge topic are prestored in the server 100.
It in detail, include all mother and baby of 100 place mother and baby's electric business restocking of current server in mother and baby's commodity library S
Commodity s, the also as specialty products that provide of these two types of special associated groups of pregnant and perinatal period women and 0-3 years old baby, such as pregnant woman
Articles, postpartum articles, baby's bedding products, early education articles, washing product, feeding bottle and assistant product etc..
It include various to breed knowledge mother and baby's knowledge topic relevant with topic is bred in the total library D of mother and baby's knowledge topic
Document d, these mother and baby's knowledge topic documents upload onto the server 100 after being shared by each user, can also be from other phases
It closes and uploads onto the server 100 after obtaining in mother and baby website, the present embodiment is not made to have to the source of mother and baby's knowledge topic document
Body limitation.
In the present embodiment, product features information of the available mother and baby's commodity in the current presentation page, and will be described
Product features information includes at least product name, commodity classification, quotient as the descriptive labelling information, the product features information
Product title.
Meanwhile inventor has found under study for action, for general mother and baby's electric business, the magnitude of mother and baby's commodity library S is tens
The magnitude of ten thousand, mother and baby's knowledge topic library D are ten tens of thousands of, if each mother and baby's commodity and every mother and baby's knowledge topic document will be counted
Semantic topic similarity is calculated, then D*S will be for a very big calculating magnitude.In order to reduce calculation amount, and reduce unnecessary
Risk, current embodiment require that choosing the lesser mother and baby's knowledge topic library for having certain degree of association for each mother and baby's commodity s.
Thus, it is possible to go out mother and baby's knowledge topic library with mother and baby's commodity association based on the product features information retrieval.
In detail, the corpus of text in mother and baby's knowledge topic library D can be put into open source search engine solr and establishes index, for mother
Each of baby's commodity library S mother and baby commodity s goes in open source search engine solr to retrieve and commodity using product features information
Relevant mother and baby's knowledge topic collection of document D ', D ' that is to say mother and baby's knowledge topic library with mother and baby's commodity association.As a result, can
It enough ensures that mother and baby's commodity and its alternative documents set have the preliminary degree of correlation, while reducing subsequent calculation amount, reduce server
100 performance pressures.
Step S220 calculates each mother and baby's knowledge topic text in the descriptive labelling information and mother and baby's knowledge topic library
Topic Similarity between shelves, obtains Topic Similarity set.
As an implementation, this step S220 can be realized by following sub-step:
Firstly, segmenting to each mother and baby's knowledge topic document in mother and baby's knowledge topic library, each mother is obtained
Multiple words in baby's knowledge topic document.For example, including 100 mother and baby's knowledge topic texts in mother and baby's knowledge topic library D
Shelves d, then segment the content in this 100 mother and baby's knowledge topic document d.
Then, multiple words after participle are input to LDA model training as LDA mode input vector and obtain the mother
The topic model in baby's knowledge topic library is expressed, wherein the topic model expression includes each in mother and baby's knowledge topic library
The theme of mother and baby's knowledge topic document indicates the theme indicates to include master of each theme in mother and baby's knowledge topic document
Inscribe significance level.For example, indicate can be with for the theme of each mother and baby's knowledge topic document are as follows:
T (d)=(t1, t2..., tn)
In above formula, n is the theme number of setting, tiIllustrate each theme in mother and baby's knowledge topic document d
Theme significance level.
Wherein, LDA (Latent Dirichlet Allocation) is that a kind of document subject matter generates model, also referred to as one
A three layers of bayesian probability model includes word, theme and document three-decker.So-called generation model, that is, it is believed that one
Each word of piece mother and baby's knowledge topic document is by " with some theme of certain probability selection, and from this theme
With some word of certain probability selection " such a process obtains.Mother and baby's knowledge topic document obeys multinomial distribution to theme,
Theme obeys multinomial distribution to word.That is, one that some themes of each mother and baby's knowledge topic documents representative are constituted
Probability distribution, and each theme represents the probability distribution that many words are constituted.
Then, in conjunction with TWE (Topical Word Embeddings, descriptor insertion) model and the topic model table
Up to the embedded expression for the embedded expression and each word that each theme is calculated.
Then, the embedded table based on topic model expression, the embedded expression of each theme and each word
Up to the probability for calculating descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library, and will
The probability is as the Topic Similarity between each mother and baby's knowledge topic document and the descriptive labelling information.
Optionally, the calculation formula of above-mentioned steps can be such that
Wherein, Topic Similarity of the Sim (s, d) between the descriptive labelling information s and mother and baby's knowledge topic document d, P
(w|zk) it is embedded expression at each word w and each theme zkEmbedded expression between Topic Similarity, P (zk|
It d) is each theme zkEmbedded expression and each mother and baby's knowledge topic document d theme expression between Topic Similarity.
As a result, when needing to calculate the semantic relevancy of mother and baby's commodity s and mother and baby's knowledge topic document d, by
It is usually shorter short text in the descriptive labelling information of mother and baby's commodity s, and mother and baby's knowledge topic document d is longer long article
This, therefore when calculating Topic Similarity, the present embodiment, which has been evaded, directly carries out theme mapping to short text, but according to
The theme distribution of mother and baby's knowledge topic document d calculates each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library
The probability of the descriptive labelling information, as the master between each mother and baby's knowledge topic document and the descriptive labelling information
Inscribe similarity.
Step S230 picks out the mother and baby's knowledge topic document work for meeting preset rules according to the Topic Similarity set
For the recommendation document of mother and baby's commodity.
As an implementation, this step S230 can be realized by following sub-step:
Firstly, by mother and baby's knowledge corresponding less than the Topic Similarity of the first preset threshold in the Topic Similarity set
Topic document is filtered, and mother and baby's knowledge topic document to guarantee subsequent recommendation is related enough.
Then, mother and baby's knowledge topic document remaining after filtering is ranked up according to Topic Similarity size, the row of generation
Sequence is as a result, pick out the mother and baby's knowledge topic document for meeting preset rules further according to the ranking results as mother and baby's commodity
Recommend document.It is alternatively possible to choose mother and baby's knowledge topic text that Topic Similarity size in the ranking results is located at top n
Recommendation document of the shelves as mother and baby's commodity；Alternatively, can also choose in the ranking results Topic Similarity size is greater than the
Recommendation document of all mother and baby's knowledge topic documents of two preset thresholds as mother and baby's commodity.
So far, it is based on the above method, can be mother and baby user's recommendation and browsing when mother and baby user browses mother and baby's commodity
The relevant mother and baby's knowledge topic of mother and baby's commodity, to help mother and baby user to become more apparent upon commodity and mother and baby's knowledge, so that mother and baby uses
Householder is dynamic to participate in discussion, and generates content of good.
Optionally, please further refering to Fig. 3, after step S230, mother and baby's knowledge topic recommended method may be used also
To include the following steps:
Step S240, when the merchandise display page for detecting mother and baby's commodity is opened, by the recommendation document of mother and baby's commodity
It shows in the merchandise display page of mother and baby's commodity.
In the present embodiment, user when browsing the merchandise display page of mother and baby's commodity on the display interface of user terminal 300,
Server 100 ought be then by the recommendation document display of mother and baby's commodity in the merchandise display page of mother and baby's commodity.User exists as a result,
It also can choose when browsing the merchandise news of mother and baby's commodity and browse matching mother and baby's knowledge and mother and baby's topic, and participate in begging for
By selecting more suitable mother and baby's commodity to further appreciate that commodity.
Referring to Fig. 4, being the service provided by the embodiments of the present application for realizing above-mentioned mother and baby's knowledge topic recommended method
The structural schematic block diagram of device 100.As shown in figure 4, the server 100 can be made general bus architecture knot by bus 110
Structure is realized.According to the concrete application of server 100 and overall design constraints condition, bus 110 may include any number of
Interconnection bus and bridge joint.Together by various circuit connections, these circuits include processor 120, storage medium 130 to bus 110
With bus interface 140.Optionally, bus interface 140 can be used, and network adapter 150 is equal via bus 110 in server 100
Connection.Network adapter 150 can be used for realizing the signal processing function of physical layer in cordless communication network, and be realized by antenna
Radiofrequency signal sends and receives.User interface 160 can connect external equipment, such as: keyboard, display, mouse or behaviour
Vertical pole etc..Bus 110 can also connect various other circuits, such as timing source, peripheral equipment, voltage regulator or power management
Circuit etc., these circuits are known in the art, therefore are no longer described in detail.
It can replace, server 100 may also be configured to generic processing system, such as be commonly referred to as chip, the general procedure
System includes: to provide the one or more microprocessors of processing function, and provide at least part of outer of storage medium 130
Portion's memory, it is all these all to be linked together by external bus architecture and other support circuits.
Alternatively, following realize can be used in server 100: having processor 120, bus interface 140, Yong Hujie
The ASIC (specific integrated circuit) of mouth 160；And it is integrated at least part of the storage medium 130 in one single chip, alternatively,
Following realize: one or more FPGA (field programmable gate array), PLD (programmable logic device can be used in server 100
Part), controller, state machine, gate logic, discrete hardware components, any other suitable circuit or to be able to carry out the application logical
Any combination of the circuit of various functions described in.
Wherein, processor 120 is responsible for management bus 110 and general processing (is stored on storage medium 130 including executing
Software).One or more general processors and/or application specific processor can be used to realize in processor 120.Processor 120
Example includes microprocessor, microcontroller, dsp processor and the other circuits for being able to carry out software.It should be by software broadly
It is construed to indicate instruction, data or any combination thereof, regardless of being called it as software, firmware, middleware, microcode, hard
Part description language or other.
Storage medium 130 is illustrated as separating with processor 120 in Fig. 4, however, those skilled in the art be easy to it is bright
White, storage medium 130 or its arbitrary portion can be located at except server 100.For example, storage medium 130 may include passing
Defeated line, the carrier waveform modulated with data, and/or the computer product that separates with radio node, these media can be by
Processor 120 is accessed by bus interface 140.Alternatively, storage medium 130 or its arbitrary portion are desirably integrated into processing
In device 120, for example, it may be cache and/or general register.
Above-described embodiment can be performed in the processor 120, specifically, can store in the storage medium 130 described
Mother and baby's knowledge topic recommendation apparatus 200, the processor 120 can be used for executing mother and baby's knowledge topic recommendation apparatus 200.
Further, correspond to mother and baby's knowledge topic recommended method shown in Fig. 2, referring to Fig. 3, mother and baby's knowledge
Topic recommendation apparatus 200 can include:
Obtain module 210, for be directed to each mother and baby's commodity, obtain mother and baby's commodity descriptive labelling information and with this
Mother and baby's knowledge topic library of mother and baby's commodity association.
Computing module 220 is known for calculating the descriptive labelling information with each mother and baby in mother and baby's knowledge topic library
Know the Topic Similarity between topic document, obtains Topic Similarity set.
Choosing module 230, for picking out the mother and baby's knowledge words for meeting preset rules according to the Topic Similarity set
Inscribe recommendation document of the document as mother and baby's commodity.
Optionally, the acquisition module 210 is also used to obtain the product features of mother and baby's commodity in the current presentation page
Information, and using the product features information as the descriptive labelling information, then based on the product features information retrieval go out with
Mother and baby's knowledge topic library of mother and baby's commodity association；The product features information includes at least product name, commodity classification, commodity
Title.
Optionally, the computing module 220 is also used to each mother and baby's knowledge topic in mother and baby's knowledge topic library
Document is segmented, and multiple words in each mother and baby's knowledge topic document are obtained；
LDA model training is input to using multiple words after participle as LDA mode input vector obtains the mother and baby know
Know the topic model expression in topic library, wherein the topic model expression includes each mother and baby in mother and baby's knowledge topic library
The theme of knowledge topic document indicates the theme indicates to include theme weight of each theme in mother and baby's knowledge topic document
Want degree；
The embedded expression that each theme is calculated and each word are expressed in conjunction with TWE model and the topic model
Embedded expression；
It is calculated based on topic model expression, the embedded expression of each theme and the embedded expression of each word
The probability of descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library, and will be described general
Rate is as the Topic Similarity between each mother and baby's knowledge topic document and the descriptive labelling information.
It is understood that the concrete operation method of each functional module in the present embodiment can refer to above method embodiment
The detailed description of middle corresponding steps, it is no longer repeated herein.
Further, the embodiment of the present application also provides a kind of readable storage medium storing program for executing, is stored in the readable storage medium storing program for executing
Computer program, the computer program, which is performed, realizes above-mentioned mother and baby's knowledge topic recommended method.
In conclusion mother and baby's knowledge topic recommended method provided by the embodiments of the present application and device, first against each mother
Baby's commodity obtain the descriptive labelling information of mother and baby's commodity and mother and baby's knowledge topic library with mother and baby's commodity association.Then,
The theme calculated between the descriptive labelling information and each mother and baby's knowledge topic document in mother and baby's knowledge topic library is similar
Degree, obtains Topic Similarity set.Finally, picking out the mother and baby's knowledge for meeting preset rules according to the Topic Similarity set
Recommendation document of the topic document as mother and baby's commodity.By using above-mentioned technical proposal, mother and baby can be browsed for mother and baby user
Recommend mother and baby's knowledge topic relevant with mother and baby's commodity of browsing when commodity for mother and baby user, to help mother and baby user more
Commodity and mother and baby's knowledge are solved, so that mother and baby user is actively engaged in discussion, generates content of good.
In embodiment provided herein, it should be understood that disclosed device and method, it can also be by other
Mode realize.Device and method embodiment described above is only schematical, for example, flow chart and frame in attached drawing
Figure shows the system frame in the cards of the system of multiple embodiments according to the application, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be with not in some implementations as replacement
It is same as the sequence marked in attached drawing generation.For example, two continuous boxes can actually be basically executed in parallel, they have
When can also execute in the opposite order, this depends on the function involved.It is also noted that in block diagram and or flow chart
Each box and the box in block diagram and or flow chart combination, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the application can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It can replace, can be realized wholly or partly by software, hardware, firmware or any combination thereof.When
When using software realization, can entirely or partly it realize in the form of a computer program product.The computer program product
Including one or more computer instructions.It is all or part of when loading on computers and executing the computer program instructions
Ground is generated according to process or function described in the embodiment of the present application.The computer can be general purpose computer, special purpose computer,
Computer network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or
Person is transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction
Wired (such as coaxial cable, optical fiber, digital subscriber can be passed through from a web-site, computer, server or data center
Line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or data
It is transmitted at center.The computer readable storage medium can be any usable medium that computer can access and either wrap
The data storage devices such as server, the data center integrated containing one or more usable mediums.The usable medium can be magnetic
Property medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc.
It should be noted that, in this document, term " including ", " including " or its any other variant are intended to non-row
Its property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and
And further include the other elements being not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including one ... ", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case where without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and scope of the present application is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the application.Any reference signs in the claims should not be construed as limiting the involved claims.
Claims (10)
1. a kind of mother and baby's knowledge topic recommended method, which is characterized in that be applied to server, which comprises
For each mother and baby's commodity, obtains the descriptive labelling information of mother and baby's commodity and know with the mother and baby of mother and baby's commodity association
Know topic library；
Calculate the theme in the descriptive labelling information and mother and baby's knowledge topic library between each mother and baby's knowledge topic document
Similarity obtains Topic Similarity set；
The mother and baby's knowledge topic document for meeting preset rules is picked out according to the Topic Similarity set as mother and baby's commodity
Recommendation document.
2. mother and baby's knowledge topic recommended method according to claim 1, which is characterized in that acquisition mother and baby's commodity
The step of descriptive labelling information and mother and baby knowledge topic library with mother and baby's commodity association, comprising:
Product features information of the mother and baby's commodity in the current presentation page is obtained, and using the product features information as described in
Descriptive labelling information, the product features information include at least product name, commodity classification, commodity title；
Go out mother and baby's knowledge topic library with mother and baby's commodity association based on the product features information retrieval.
3. mother and baby's knowledge topic recommended method according to claim 1, which is characterized in that described to calculate the descriptive labelling
Topic Similarity in information and mother and baby's knowledge topic library between each mother and baby's knowledge topic document, obtains Topic Similarity
The step of set, comprising:
Each mother and baby's knowledge topic document in mother and baby's knowledge topic library is segmented, each mother and baby's knowledge topic is obtained
Multiple words in document；
Multiple words after participle are input to LDA model training as LDA mode input vector and obtain mother and baby's knowledge words
The topic model of exam pool is expressed, wherein the topic model expression includes each mother and baby's knowledge in mother and baby's knowledge topic library
The theme of topic document indicates the theme indicates to include theme important journey of each theme in mother and baby's knowledge topic document
Degree；
The embedding of the embedded expression and each word that each theme is calculated is expressed in conjunction with TWE model and the topic model
Enter formula expression；
Based on described in topic model expression, the embedded expression of each theme and the embedded expression of each word calculating
The probability of descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library, and the probability is made
For the Topic Similarity between each mother and baby's knowledge topic document and the descriptive labelling information.
4. mother and baby's knowledge topic recommended method according to claim 3, which is characterized in that described to be based on the topic model
Expression, the embedded expression of each theme and the embedded expression of each word calculate each in mother and baby's knowledge topic library
The calculation formula of the probability of descriptive labelling information described in mother and baby's knowledge topic document structure tree are as follows:
Wherein, Topic Similarity of the Sim (s, d) between the descriptive labelling information s and mother and baby's knowledge topic document d, P (w |
zk) it is embedded expression at each word w and each theme zkEmbedded expression between Topic Similarity, P (zk| d) it is
Each theme zkEmbedded expression and each mother and baby's knowledge topic document d theme expression between Topic Similarity.
5. mother and baby's knowledge topic recommended method according to claim 1, which is characterized in that described similar according to the theme
Degree set picks out the step of recommendation document of the mother and baby's knowledge topic document for meeting preset rules as mother and baby's commodity, packet
It includes:
By mother and baby's knowledge topic document corresponding less than the Topic Similarity of the first preset threshold in the Topic Similarity set
It is filtered；
Mother and baby's knowledge topic document remaining after filtering is ranked up according to Topic Similarity size, generates ranking results；
Recommendation of the mother and baby's knowledge topic document for meeting preset rules as mother and baby's commodity is picked out according to the ranking results
Document.
6. mother and baby's knowledge topic recommended method according to claim 5, which is characterized in that described according to the ranking results
The step of picking out recommendation document of the mother and baby's knowledge topic document for meeting preset rules as mother and baby's commodity, comprising:
It chooses Topic Similarity size in the ranking results and is located at mother and baby's knowledge topic document of top n as mother and baby's commodity
Recommendation document；Or
Choose all mother and baby's knowledge topic documents work that Topic Similarity size in the ranking results is greater than the second preset threshold
For the recommendation document of mother and baby's commodity.
7. mother and baby's knowledge topic recommended method according to claim 1, which is characterized in that described similar according to the theme
After degree set picks out the step of recommendation document of the mother and baby's knowledge topic document for meeting preset rules as mother and baby's commodity,
The described method includes:
When the merchandise display page for detecting mother and baby's commodity is opened, by the recommendation document display of mother and baby's commodity in the mother and baby quotient
In the merchandise display page of product.
8. a kind of mother and baby's knowledge topic recommendation apparatus, which is characterized in that be applied to server, described device includes:
Obtain module, for be directed to each mother and baby's commodity, obtain mother and baby's commodity descriptive labelling information and with the mother and baby quotient
The associated mother and baby's knowledge topic library of product；
Computing module, for calculating each mother and baby's knowledge topic text in the descriptive labelling information and mother and baby's knowledge topic library
Topic Similarity between shelves, obtains Topic Similarity set；
Choosing module, for picking out the mother and baby's knowledge topic document work for meeting preset rules according to the Topic Similarity set
For the recommendation document of mother and baby's commodity.
9. mother and baby's knowledge topic recommendation apparatus according to claim 8, it is characterised in that:
The acquisition module is also used to obtain product features information of the mother and baby's commodity in the current presentation page, and will be described
Product features information is gone out and mother and baby's commodity association as the descriptive labelling information, then based on the product features information retrieval
Mother and baby's knowledge topic library；The product features information includes at least product name, commodity classification, commodity title.
10. mother and baby's knowledge topic recommendation apparatus according to claim 8, it is characterised in that:
The computing module is also used to segment each mother and baby's knowledge topic document in mother and baby's knowledge topic library,
Obtain multiple words in each mother and baby's knowledge topic document；
Multiple words after participle are input to LDA model training as LDA mode input vector and obtain mother and baby's knowledge words
The topic model of exam pool is expressed, wherein the topic model expression includes each mother and baby's knowledge in mother and baby's knowledge topic library
The theme of topic document indicates the theme indicates to include theme important journey of each theme in mother and baby's knowledge topic document
Degree；
The embedding of the embedded expression and each word that each theme is calculated is expressed in conjunction with TWE model and the topic model
Enter formula expression；
Based on described in topic model expression, the embedded expression of each theme and the embedded expression of each word calculating
The probability of descriptive labelling information described in each mother and baby's knowledge topic document structure tree in mother and baby's knowledge topic library, and the probability is made
For the Topic Similarity between each mother and baby's knowledge topic document and the descriptive labelling information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810719230.1A CN108984688B (en) | 2018-07-03 | 2018-07-03 | Mother and infant knowledge topic recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810719230.1A CN108984688B (en) | 2018-07-03 | 2018-07-03 | Mother and infant knowledge topic recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108984688A true CN108984688A (en) | 2018-12-11 |
| CN108984688B CN108984688B (en) | 2021-03-02 |
Family
ID=64536780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810719230.1A Active CN108984688B (en) | 2018-07-03 | 2018-07-03 | Mother and infant knowledge topic recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108984688B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727102A (en) * | 2019-01-31 | 2019-05-07 | 珠海优特智厨科技有限公司 | A kind of correlation recommendation method and device of menu and kitchen tool apparatus |
| CN113254836A (en) * | 2021-06-16 | 2021-08-13 | 长沙豆芽文化科技有限公司 | Intelligent child-care knowledge point information pushing method and system and cloud platform |
| CN113763123A (en) * | 2021-08-12 | 2021-12-07 | 阿里巴巴（中国）有限公司 | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020851A (en) * | 2013-01-10 | 2013-04-03 | 山东地纬计算机软件有限公司 | Measurement calculation method supporting commodity comment data multidimensional analysis |
| CN103544282A (en) * | 2013-10-24 | 2014-01-29 | 北京京东尚科信息技术有限公司 | Information push method and device |
| JP2015200962A (en) * | 2014-04-04 | 2015-11-12 | 日本放送協会 | Inter-document relation extraction device and program |
| CN105117956A (en) * | 2015-08-28 | 2015-12-02 | 彭小林 | Method for collecting and issuing commodity picture and text information based on network platform |
| CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业（深圳）有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
-
2018
- 2018-07-03 CN CN201810719230.1A patent/CN108984688B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020851A (en) * | 2013-01-10 | 2013-04-03 | 山东地纬计算机软件有限公司 | Measurement calculation method supporting commodity comment data multidimensional analysis |
| CN103544282A (en) * | 2013-10-24 | 2014-01-29 | 北京京东尚科信息技术有限公司 | Information push method and device |
| JP2015200962A (en) * | 2014-04-04 | 2015-11-12 | 日本放送協会 | Inter-document relation extraction device and program |
| CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业（深圳）有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
| CN105117956A (en) * | 2015-08-28 | 2015-12-02 | 彭小林 | Method for collecting and issuing commodity picture and text information based on network platform |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727102A (en) * | 2019-01-31 | 2019-05-07 | 珠海优特智厨科技有限公司 | A kind of correlation recommendation method and device of menu and kitchen tool apparatus |
| CN113254836A (en) * | 2021-06-16 | 2021-08-13 | 长沙豆芽文化科技有限公司 | Intelligent child-care knowledge point information pushing method and system and cloud platform |
| CN113254836B (en) * | 2021-06-16 | 2021-09-14 | 长沙豆芽文化科技有限公司 | Intelligent child-care knowledge point information pushing method and system and cloud platform |
| CN113763123A (en) * | 2021-08-12 | 2021-12-07 | 阿里巴巴（中国）有限公司 | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108984688B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10977311B2 (en) | Dynamically modifying elements of user interface based on knowledge graph | |
| US11172040B2 (en) | Method and apparatus for pushing information | |
| CN108228906B (en) | Method and apparatus for generating information | |
| CN106257452B (en) | Modifying search results based on contextual characteristics | |
| WO2014206151A1 (en) | System and method for tagging and searching documents | |
| CN105389325A (en) | Content search method and electronic device implementing same | |
| CN108984688A (en) | Mother and baby's knowledge topic recommended method and device | |
| WO2015200500A1 (en) | Attribute fill using text extraction | |
| CN107894994A (en) | A kind of method and apparatus for detecting much-talked-about topic classification | |
| CN113836131B (en) | Big data cleaning method and device, computer equipment and storage medium | |
| CN113204691B (en) | Information display method, device, equipment and medium | |
| CN112052297B (en) | Information generation method, apparatus, electronic device and computer readable medium | |
| CN107911448A (en) | Content pushing method and device | |
| CN104317920A (en) | Information pushing method and information pushing system based on intelligent user demand matching | |
| CN110362815A (en) | Text vector generation method and device | |
| CN109271425A (en) | It constructs the method for rumour database, analyze the method and electronic equipment of rumour data | |
| CN109190050A (en) | The method, apparatus and electronic equipment for recommending word are provided based on article figure | |
| CN109862100A (en) | Method and apparatus for pushed information | |
| CN109284367A (en) | Method and apparatus for handling text | |
| CN109785072A (en) | Method and apparatus for generating information | |
| CN103123651A (en) | Method of rapidly searching multiple same-kind paper, device and mobile equipment | |
| CN109840120A (en) | Decouple micro services dissemination method, electronic device and computer readable storage medium | |
| CN107562881A (en) | Interference method, medium, system and the computing device of commending system | |
| CN110363206A (en) | Cluster, data processing and the data identification method of data object | |
| US10289740B2 (en) | Computer systems to outline search content and related methods therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220929 Address after: 311100 rooms 809 and 810, building 8, Xixi bafangcheng, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Mitu network technology (Group) Co.,Ltd. Address before: Room 701, 702, 7 / F, 101, 3-14 / F, building 1, yard 17, Guangqu Road, Chaoyang District, Beijing Patentee before: MIYA BAOBEI (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |