CN103020128A - Method and device for data interaction with terminal device - Google Patents
Method and device for data interaction with terminal device Download PDFInfo
- Publication number
- CN103020128A CN103020128A CN2012104691279A CN201210469127A CN103020128A CN 103020128 A CN103020128 A CN 103020128A CN 2012104691279 A CN2012104691279 A CN 2012104691279A CN 201210469127 A CN201210469127 A CN 201210469127A CN 103020128 A CN103020128 A CN 103020128A
- Authority
- CN
- China
- Prior art keywords
- shopping
- shopping information
- word
- terminal device
- information
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for data interaction with a terminal device. The method comprises the following steps: obtaining a preset shopping recommendation word related to the shopping behavior of the terminal device; obtaining commodity information related to at least one commodity corresponding to the preset shopping recommendation word in a matched manner according to the preset shopping recommendation word; and sending the commodity information related to the at least one commodity obtained in a matched manner to the terminal device. Since the shopping recommendation word is not needed to be extracted from detailed and sufficient commodity information, the commodity recommendation effect of the embodiment of the invention is convenient to control; and the individualized shopping recommendation based on the shopping recommendation word simplifies complexity of a shopping recommendation system and improves real-time recommendation response.
Description
Technical field
The invention belongs to communication technical field, relate in particular to a kind of and method and device the terminal device interaction data.
Background technology
Along with the arrival of information age, shopping online has also become one of main shopping way of people.The user only need network and can not operate the commodity that the door can obtain comparatively to be satisfied with.
The angle of building and moving from existing shopping commending system, the shopping commending system needs the dependent merchandise information of the commodity that analysis user in real time browsed or bought, in order to recommend accurately commodity to the targeted customer, the shopping commending system need to rely on huge information of goods information data storehouse, the shopping commending system utilizes above-mentioned analysis result and information of goods information data storehouse to carry out in real time the commercial product recommending computing, obtains close commercial product recommending to the user.Because huge information of goods information data storehouse, the required computational resource of recommendation process that causes doing shopping is larger, causes the increase in the processing time of shopping commending system, affects recommendation response speed.
Summary of the invention
In view of the above problems, the present invention has been proposed in order to a kind of overcome the problems referred to above or that address the above problem at least in part and method and device the terminal device interaction data are provided.
According to one aspect of the present invention, the method that provides a kind of merchandise news to process, the method comprises: obtain the default shopping relevant with the shopping behavior of terminal device and recommend word; Recommend word according to default shopping, coupling obtains recommending with default shopping the dependent merchandise information of at least one commodity corresponding to word; The dependent merchandise information of at least one commodity that coupling is obtained sends to described terminal device.
According to another aspect of the present invention, provide a kind of and the device terminal device interaction data, device comprises: memory module is used for the default shopping of storage and recommends word; Acquisition module is used for obtaining the default shopping relevant with the shopping behavior of terminal device and recommends word; Matching module, for recommending word according to default shopping, coupling obtains the dependent merchandise information with at least one commodity corresponding to recommendation word of doing shopping; Sending module sends to terminal device for the dependent merchandise information that coupling is obtained at least one commodity.
According to the method for a kind of and terminal device interaction data provided by the invention and with the device of terminal device interaction data, identify by the shopping behavior to terminal device, obtain the default shopping relevant with this shopping behavior and recommend word, then utilize shopping to recommend word as recommending intermediary, to recommend commercial product recommending corresponding to word to terminal device with this shopping, the feature owing to need to not do shopping by the merchandise news structure user of detailed abundance, but the shopping behavior of terminal device is mapped to corresponding shopping recommendation word, identify by the concrete shopping behavior to terminal device, can obtain the shopping corresponding with the shopping behavior and recommend word, therefore the convenient control of the commercial product recommending effect in the embodiment of the invention, effectively simplify the complexity of shopping commending system, improve real-time recommendation response speed.
Above-mentioned explanation only is the general introduction of technical solution of the present invention, for can clearer understanding technological means of the present invention, and can be implemented according to the content of instructions, and for above and other objects of the present invention, feature and advantage can be become apparent, below especially exemplified by the specific embodiment of the present invention.
Description of drawings
By reading hereinafter detailed description of the preferred embodiment, various other advantage and benefits will become cheer and bright for those of ordinary skills.Accompanying drawing only is used for the purpose of preferred implementation is shown, and does not think limitation of the present invention.And in whole accompanying drawing, represent identical parts with identical reference symbol.In the accompanying drawings:
Fig. 1 shows according to an embodiment of the invention the process flow diagram with the method for terminal device interaction data;
Fig. 2 shows the process flow diagram among the step S10 among Fig. 1;
Fig. 3 shows the process flow diagram among the step S104 among Fig. 2; And
Fig. 4 shows in accordance with another embodiment of the present invention the structured flowchart with the device 400 of terminal device interaction data.
Embodiment
Exemplary embodiment of the present disclosure is described below with reference to accompanying drawings in more detail.Although shown exemplary embodiment of the present disclosure in the accompanying drawing, yet should be appreciated that and to realize the disclosure and the embodiment that should do not set forth limits here with various forms.On the contrary, it is in order to understand the disclosure more thoroughly that these embodiment are provided, and can with the scope of the present disclosure complete convey to those skilled in the art.
Fig. 1 shows according to an embodiment of the invention the process flow diagram with the method for terminal device interaction data, need to prove, although in Fig. 1, described the operation of this recognition methods with particular order, but, this is not that requirement or hint must be carried out these operations according to this particular order, or the operation shown in must carrying out all could realize the result of expectation.On the contrary, the step of describing in the process flow diagram can change execution sequence.Additionally or alternatively, can omit some step, a plurality of steps be merged into a step carry out, and/or a step is decomposed into a plurality of steps carries out.
As shown in Figure 1, the method starts from step S10, wherein obtains the default shopping relevant with the shopping behavior of terminal device and recommends word.
Particularly, referring to Fig. 2, in step S 10, can may further comprise the steps, in step S102, obtain the shopping information relevant with the shopping behavior of terminal device, this shopping information comprises: the keyword of terminal device search commercial articles, terminal device are browsed the merchandise news of commodity or the merchandise news of terminal device purchased item; Subsequently, in step S 104, obtain at least one default shopping corresponding with shopping information according to the shopping information coupling and recommend word.Namely, recommend word according to the shopping that the keyword coupling of the search commercial articles of terminal device input obtains presetting, perhaps browse the shopping that the merchandise news coupling of commodity obtains presetting according to terminal device and recommend word, word is recommended in the shopping that perhaps obtains presetting according to the dependent merchandise information matches of terminal device purchased item.
According to one embodiment of present invention, default shopping recommendation word can be the word according to the dependent merchandise information structuring of much-sought-after item, for example searches for the word of the dependent merchandise information structuring of maximum commodity according to terminal device.Each shopping recommends to comprise a plurality of shopping information elements in the word that wherein the shopping information element refers to: the type of merchandise, trade name or proprietary concentrate.Below understanding, enumerate several shopping recommendation words, such as: the woollen overcoat of men's clothing hair, smart mobile phone, HDTV, man's cold-proof underwear etc.What certainly can understand is not limit in an embodiment of the present invention the expression-form that word is recommended in shopping.
Alternatively, default shopping recommends word to obtain and to store from the shopping conversation daily record of electrical type business web site, also can from the commercial articles searching ranking list of search website, obtain and store, recommend word can be kept in the database shopping of obtaining, and also preserve the corresponding relation that word and dependent merchandise are recommended in shopping in database, for example shopping recommends word " smart mobile phone " to set up with apple iphone5, Samsung GALAXY Note II N7100, the happy PhoneK860 of association and HTC One X S720e corresponding relation.Therefore, after obtaining shopping recommendation word, can obtain to recommend with this shopping the dependent merchandise information of commodity corresponding to word.Owing to can by shopping being recommended the maintenance of word, to satisfy the shopping recommended requirements of terminal device, therefore not need in an embodiment of the present invention huge information of goods information data storehouse.
According to one embodiment of present invention, can identify the shopping information relevant with this shopping behavior from the shopping behavior of terminal device in step S102, this shopping behavior includes but not limited to: the behavior that the behavior of terminal device input keyword, the behavior that terminal device is browsed commodity or terminal device are bought commodity.
When terminal device is done shopping; usually can be by the keyword search commodity; the commodity of then being correlated with in the navigate search results; for example terminal device is logined ecommerce class website (Taobao; store, Jingdone district etc.); the search engine that uses ecommerce class website to provide; in search engine, utilize the keyword search dependent merchandise; then relevant commodity in the navigate search results; owing to can input the behavior of keyword by the record terminal device in the shopping conversation daily record of e-commerce website, so can identify the keyword of search commercial articles by the behavior to terminal device input keyword.
When terminal device is browsed Search Results, can navigate search results in one or more in the trade name, the type of merchandise, goods marks, marque.Owing to can record the behavior of browsing commodity of terminal device in the shopping conversation daily record of e-commerce website, therefore, identify by the behavior of browsing commodity to terminal device, can identify terminal device and browse the merchandise news of commodity, this merchandise news comprises: one or more in trade name, the type of merchandise, goods marks, the marque.
Terminal device can record the behavior that terminal device is bought commodity in the shopping conversation daily record of ecommerce class website after the electrical type business web site is bought commodity.Owing to can record the behavior of the purchase commodity of terminal device in the shopping conversation daily record of e-commerce website, therefore identify by the behavior of this terminal device being bought commodity, can identify the dependent merchandise information that obtains commodity that terminal device is bought, this merchandise news comprises: one or more in trade name, the type of merchandise, goods marks, marque, the commodity price.
Therefore, analyze by the shopping behavior to terminal device, can obtain the keyword of the terminal device search commercial articles relevant with this shopping behavior, merchandise news that terminal device is browsed commodity or the merchandise news of terminal device purchased item.And identify by the shopping behavior to terminal device, can remove in the shopping behavior of terminal device the information irrelevant with merchandise news, the accuracy of the Recommendations information that finally provides can be provided thus.
According to one embodiment of present invention, recommend the accuracy of word coupling in order to improve shopping, can carry out clustering processing to shopping information, obtain to reflect the shopping information class with at least part of identical shopping information element, and then obtain shopping recommendation word according to shopping information class coupling.
Referring to Fig. 3, step S104 may further comprise the steps, in step S1042, shopping information is divided into a plurality of shopping information elements, subsequently, in step S1044, according to the shopping information element, a plurality of shopping informations are carried out clustering processing, obtain the shopping information class, wherein each shopping information class comprises at least one shopping information, then, in step S1046, each shopping information class is mated at least one shopping recommend word.
Alternatively, in step S1042, can shopping information T be divided into a plurality of shopping information element t according to the mode of participle, after participle was divided, this shopping information can be expressed as T={t
1, t
2..., t
n, wherein n is natural number.According to the importance of shopping information element t, the weighted value of each shopping information element t is set.For example, the shopping information T that obtains in step S102 " the woollen overcoat man of the warming hair of cultivating one's moral character of Fubai autumn and winter trendy men's clothing wind coat stand-up collar " in step S1042, is divided into { Fubai with above-mentioned shopping information T participle, autumn and winter are trendy, men's clothing, wind coat, stand-up collar, warming, cultivate one's moral character, hair is woollen, overcoat }.According to shopping information T={Fubai, autumn and winter are trendy, men's clothing, wind coat, stand-up collar, warming, cultivate one's moral character, hair is woollen, overcoat } in the importance of each shopping information element t, the weighted value of each shopping information element t is set, for example the frequency of this shopping information element appearance is higher, can think that then this shopping information element t is more important, weighted value is larger, and the importance of shopping information element t can be arranged as from high to low among the above-mentioned shopping information T: men's clothing, hair woollen cloth, overcoat, wind coat, stand-up collar, warming, cultivate one's moral character, the autumn and winter are trendy, Fubai.
Alternatively, in step S1044, according to the weighted value sum of all shopping information element t among the shopping information T, a plurality of shopping information T are carried out clustering processing, obtain corresponding shopping information class G.For example, calculate the weighted value sum of all shopping information element t among the shopping information T, and then calculate the average weight value of shopping information element t among the shopping information T, the average weight value is aggregated to the shopping information class G of same class commodity more than or equal to the shopping information of threshold limit a.
According to one embodiment of present invention, can adopt TF-IDF(Term Frequency-InverseDocument Frequency, a kind of weighting technique commonly used of prospecting for information retrieval and information) algorithm arranges the weighted value of shopping information element t, what certainly can understand is that embodiments of the invention do not limit the mode of the weighted value that shopping information element t is set.A plurality of shopping information T are carried out clustering processing, and to obtain the concrete mode of shopping information class G as follows:
(1) if shopping information class G does not comprise any shopping information, shopping information T belongs to shopping information class G so;
(2) if shopping information class G comprises some shopping informations, certain shopping information T belongs to shopping information class G need be satisfied:
Wherein, ∑
Term ∈ G ∩ TScore represents: be present among the shopping information class G weighted value sum of each shopping information element t among the shopping information T;
Count represents: the number of the shopping information T that comprises among the shopping information class G;
α represents threshold limit, and this threshold limit can be adjusted as the case may be;
(3) if certain shopping information T does not belong to any one shopping information class G, this shopping information T itself belongs to a newly-built shopping information class G so;
Alternatively, in step S 1046, recommend an optional shopping recommendation word the word Q from a plurality of default shopping, then calculate the weighted value sum of the shopping information element t that jointly comprises among this shopping information class G and the shopping recommendation word Q, and then calculate the weighted value sum of the shopping information element t jointly comprise, and the ratio between the number of the shopping information element t that comprises among the shopping recommendation word Q, and cycle calculations, recommending word Q until traveled through all shopping, is that word Q is recommended in the corresponding shopping of ratio of a maximum of shopping information class G coupling at last.
According to one embodiment of present invention, the concrete mode among the step S1046 is as follows:
If a shopping information class G comprises many shopping informations T, each shopping information T comprises a plurality of shopping information element t, and shopping information class G is comprised of m shopping information element t, shopping information class G can be denoted as G={t_1 thus, t_2 ..., t_m};
Each shopping recommends word Q to be comprised of n shopping information element t, is denoted as Q={t_1, t_2 ..., t_n};
According to following formula, calculate shopping and recommend word Q with respect to the ratio of shopping information class G;
Wherein, ∑
Term ∈ G ∩ QScoreT represents: the weighted value sum of the shopping information element t that shopping recommendation word Q and shopping information class G comprise jointly;
CountQ represents: the number of the shopping information element t that shopping recommendation word Q comprises.
Ratio Score (Q|G) according to formula (2) calculates is the corresponding shopping recommendation of ratio Score (Q|G) the word Q of a maximum of shopping information class G coupling.
By above step, can realize obtaining shopping recommendation word according to user's shopping behavior coupling.These shopping recommend the dependent merchandise information of commodity corresponding to word just to can be used as the recommendation results of terminal device shopping.
Subsequently, in step S12, the recommendation word mates the dependent merchandise information that obtains and do shopping at least one commodity corresponding to recommendation word according to doing shopping.
For example: the behavior of in step S10, obtaining terminal device historical viewings commodity, acquire the trade name " the warming woollen overcoat of hair of cultivating one's moral character of Fubai autumn and winter trendy men's clothing wind coat stand-up collar " of browsing before the terminal device, then obtain shopping according to above-mentioned trade name coupling and recommend word " the woollen overcoat of men's clothing hair ", in step S12, recommend word " the woollen overcoat of men's clothing hair " coupling to obtain the dependent merchandise information of at least one commodity corresponding with " the woollen overcoat of men's clothing hair " according to shopping.
Subsequently, in step S14, the dependent merchandise information of these commodity that coupling is obtained sends to terminal device.
For example: the dependent merchandise information pushing of at least one commodity that will be corresponding with " the woollen overcoat of men's clothing hair " is to terminal device.According to one embodiment of present invention, this merchandise news comprises: any one in the manufacturer of trade name, commodity picture, commodity price, goods marks, marque and commodity or much information.
Method according to a kind of and terminal device interaction data provided by the invention, identify by the shopping behavior to terminal device, obtain the default shopping relevant with this shopping behavior and recommend word, then utilize shopping to recommend word as recommending intermediary, to recommend commercial product recommending corresponding to word to terminal device with this shopping, recommend word owing to need to not excavate shopping by the merchandise news of detailed abundance, but the shopping behavior of terminal device is mapped to corresponding shopping recommendation word, then the concrete shopping behavior of terminal device is identified, obtain the shopping corresponding with the shopping behavior and recommend word, therefore the convenient control of the commercial product recommending effect in the embodiment of the invention, effectively simplify the complexity of shopping commending system, improve real-time recommendation response speed.
Fig. 4 shows in accordance with another embodiment of the present invention the structured flowchart with the device 400 of terminal device interaction data.
This device 400 comprises as shown in Figure 4: memory module 401, acquisition module 402, matching module 404 and sending module 406, wherein,
Word is recommended in the default shopping of memory module 401 storages, according to one embodiment of present invention, default shopping recommendation word can be the word according to the dependent merchandise information structuring of much-sought-after item, for example searches for the word of the dependent merchandise information structuring of maximum commodity according to terminal device.Each shopping recommends to comprise a plurality of shopping information elements in the word that wherein the shopping information element refers to: the type of merchandise, trade name or proprietary concentrate.Below understanding, enumerate several shopping recommendation words, such as: the woollen overcoat of men's clothing hair, smart mobile phone, HDTV, man's cold-proof underwear etc.What certainly can understand is not limit in an embodiment of the present invention the expression-form that word is recommended in shopping.
Alternatively, default shopping recommends word can be kept in the database, and also preserve the corresponding relation that word and dependent merchandise are recommended in shopping in database, for example shopping recommends word " smart mobile phone " to set up with apple iphone5, Samsung GALAXY Note II N7100, the happy PhoneK860 of association and HTC One X S720e corresponding relation.Therefore, after word is recommended in the shopping that obtains presetting, can obtain to recommend with this shopping the dependent merchandise information of commodity corresponding to word.Owing to can by shopping being recommended the maintenance of word, to satisfy the shopping recommended requirements of terminal device, therefore not need in an embodiment of the present invention huge information of goods information data storehouse.
Sending module 406 be used for will with the relevant of at least one commodity and terminal device interaction data to terminal device.
According to one embodiment of present invention, acquiring unit 4022 is further used for identifying shopping information from the shopping behavior of terminal device, and this shopping behavior includes but not limited to: the behavior that the behavior of terminal device input keyword, the behavior that terminal device is browsed commodity or terminal device are bought commodity.
When terminal device is done shopping; usually can be by the keyword search commodity; the commodity of then being correlated with in the navigate search results; for example terminal device is logined ecommerce class website (Taobao; store, Jingdone district etc.); the search engine that uses ecommerce class website to provide; in search engine, utilize the keyword search dependent merchandise; then relevant commodity in the navigate search results; owing to can input the behavior of keyword by the record terminal device in the shopping conversation daily record of e-commerce website, so can identify the keyword of search commercial articles by the behavior to terminal device input keyword.
When terminal device is browsed Search Results, can navigate search results in one or more in the trade name, the type of merchandise, goods marks, marque.Owing to can record the behavior of browsing commodity of terminal device in the shopping conversation daily record of e-commerce website, therefore, identify by the behavior of browsing commodity to terminal device, can identify terminal device and browse the merchandise news of commodity, this merchandise news comprises: one or more in trade name, the type of merchandise, goods marks, the marque.
Terminal device can record the behavior that terminal device is bought commodity in the shopping conversation daily record of ecommerce class website after the electrical type business web site is bought commodity.Owing to can record the behavior of the purchase commodity of terminal device in the shopping conversation daily record of e-commerce website, therefore identify by the behavior of this terminal device being bought commodity, can identify the dependent merchandise information that obtains commodity that terminal device is bought, this merchandise news comprises: one or more in trade name, the type of merchandise, goods marks, marque, the commodity price.
Therefore, analyze by the shopping behavior to terminal device, can obtain the keyword of the terminal device search commercial articles relevant with this shopping behavior, merchandise news that terminal device is browsed commodity or the merchandise news of terminal device purchased item.And identify by the shopping behavior to terminal device, can remove in the shopping behavior of terminal device the information irrelevant with merchandise news, the accuracy of the Recommendations information that finally provides can be provided thus.
According to one embodiment of present invention, the first matching unit 4024 comprises: cluster subelement and coupling subelement, wherein the cluster subelement is used for shopping information is carried out clustering processing, obtains a plurality of shopping information classes, and wherein each shopping information class comprises at least one shopping information; The coupling subelement mates at least one shopping to each shopping information class recommends word.
In another embodiment of the present invention, the first matching unit 4024 also comprises: divide subelement and subelement is set, wherein divide subelement and be used for shopping information is divided into a plurality of shopping information elements; Particularly, divide subelement and can shopping information be divided into a plurality of shopping information elements according to the mode of participle.And subelement is set is used for each shopping information element of a plurality of shopping information elements is arranged weighted value, weighted value is used for the significance level of expression shopping information element.
Correspondingly, the cluster subelement is further used for the weighted value according to the shopping information element, and a plurality of shopping informations are carried out clustering processing, obtains corresponding shopping information class.
According to one embodiment of present invention, the cluster subelement is further used for calculating the weighted value sum of all shopping information elements in the shopping information; Calculate the average weight value of shopping information element in the shopping information; Then the shopping information of average weight value more than or equal to threshold limit is aggregated in the shopping information class of same class commodity.
Particularly, the cluster subelement can carry out clustering processing to shopping information according to following formula:
Recommend word if shopping information class G comprises some shopping, certain shopping information T belongs to shopping information class G need be satisfied:
Wherein, ∑
Term ∈ G ∩ TScore represents: be present among the shopping information class G weighted value sum of shopping information element t among the shopping information T;
Count represents: the number of the shopping information T that comprises among the shopping information class G;
α represents threshold limit, and this threshold limit can be adjusted as the case may be.
According to one embodiment of present invention, described coupling subelement is further used for recommending to choose wantonly the word shopping from a plurality of default shopping and recommends word, then calculates the weighted value sum of the shopping information element that jointly comprises in this shopping information class and the shopping recommendation word; Calculate the weighted value sum of the shopping information element that jointly comprises, and the ratio between the number of the shopping information element that comprises in the shopping recommendation word; Cycle calculations is recommended word until traveled through all shopping, recommends word for the corresponding shopping of ratio of a maximum of shopping information class coupling at last.
Particularly, the coupling subelement is further used for according to following formula, calculates shopping and recommends word Q with respect to the ratio of shopping information class G;
Wherein, ∑
Term ∈ G ∩ QScoreT represents: shopping recommends word Q and shopping information class G jointly to comprise the weighted value sum of shopping information element t;
CountQ represents: the number of the shopping information element t that shopping recommendation word Q comprises;
According to the ratio Score (Q|G) that calculates, shopping information class G selects a corresponding shopping of the highest ratio Score (Q|G) to recommend word Q.
In an embodiment of the present invention, identify by the shopping behavior to terminal device, obtain the default shopping relevant with this shopping behavior and recommend word, then utilize shopping to recommend word as recommending intermediary, to recommend commercial product recommending corresponding to word to terminal device with this shopping, recommend word owing to need to not excavate shopping by the merchandise news of detailed abundance, but the shopping behavior of terminal device is mapped to corresponding shopping recommendation word, then the concrete shopping behavior of terminal device is identified, obtain the shopping corresponding with the shopping behavior and recommend word, therefore the convenient control of the commercial product recommending effect in the embodiment of the invention, effectively simplify the complexity of shopping commending system, improve real-time recommendation response speed.
Intrinsic not relevant with any certain computer, virtual system or miscellaneous equipment with demonstration at this algorithm that provides.Various general-purpose systems also can be with using based on the teaching at this.According to top description, it is apparent constructing the desired structure of this type systematic.In addition, the present invention is not also for any certain programmed language.Should be understood that and to utilize various programming languages to realize content of the present invention described here, and the top description that language-specific is done is in order to disclose preferred forms of the present invention.
In the instructions that provides herein, a large amount of details have been described.Yet, can understand, embodiments of the invention can be put into practice in the situation of these details not having.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Similarly, be to be understood that, in order to simplify the disclosure and to help to understand one or more in each inventive aspect, in the description to exemplary embodiment of the present invention, each feature of the present invention is grouped together in single embodiment, figure or the description to it sometimes in the above.Yet the method for the disclosure should be construed to the following intention of reflection: namely the present invention for required protection requires the more feature of feature clearly put down in writing than institute in each claim.Or rather, as following claims reflected, inventive aspect was to be less than all features of the disclosed single embodiment in front.Therefore, follow claims of embodiment and incorporate clearly thus this embodiment into, wherein each claim itself is as independent embodiment of the present invention.
Those skilled in the art are appreciated that and can adaptively change and they are arranged in one or more equipment different from this embodiment the module in the equipment among the embodiment.Can be combined into a module or unit or assembly to the module among the embodiment or unit or assembly, and can be divided into a plurality of submodules or subelement or sub-component to them in addition.In such feature and/or process or unit at least some are mutually repelling, and can adopt any combination to disclosed all features in this instructions (comprising claim, summary and the accompanying drawing followed) and so all processes or the unit of disclosed any method or equipment make up.Unless in addition clearly statement, disclosed each feature can be by providing identical, being equal to or the alternative features of similar purpose replaces in this instructions (comprising claim, summary and the accompanying drawing followed).
In addition, those skilled in the art can understand, although embodiment more described herein comprise some feature rather than further feature included among other embodiment, the combination of the feature of different embodiment means and is within the scope of the present invention and forms different embodiment.For example, in the following claims, the one of any of embodiment required for protection can be used with array mode arbitrarily.
All parts embodiment of the present invention can realize with hardware, perhaps realizes with the software module of moving at one or more processor, and perhaps the combination with them realizes.It will be understood by those of skill in the art that and to use in practice microprocessor or digital signal processor (DSP) to realize according to some or all some or repertoire of parts in the process recognition device of the embodiment of the invention.The present invention can also be embodied as be used to part or all equipment or the device program (for example, computer program and computer program) of carrying out method as described herein.Such realization program of the present invention can be stored on the computer-readable medium, perhaps can have the form of one or more signal.Such signal can be downloaded from internet website and obtain, and perhaps provides at carrier signal, perhaps provides with any other form.
It should be noted above-described embodiment the present invention will be described rather than limit the invention, and those skilled in the art can design alternative embodiment in the situation of the scope that does not break away from claims.In the claims, any reference symbol between bracket should be configured to limitations on claims.Word " comprises " not to be got rid of existence and is not listed in element or step in the claim.Being positioned at word " " before the element or " one " does not get rid of and has a plurality of such elements.The present invention can realize by means of the hardware that includes some different elements and by means of the computing machine of suitably programming.In having enumerated the unit claim of some devices, several in these devices can be to come imbody by same hardware branch.The use of word first, second and C grade does not represent any order.Can be title with these word explanations.
Claims (16)
1. method with the terminal device interaction data is characterized in that described method comprises:
Obtain the default shopping relevant with the shopping behavior of terminal device and recommend word;
Recommend word according to described default shopping, coupling obtains the dependent merchandise information of recommending at least one commodity corresponding to word with described default shopping;
The dependent merchandise information of described at least one commodity that coupling is obtained sends to described terminal device.
2. method according to claim 1, it is characterized in that, described default shopping recommends word to obtain and store from the shopping conversation daily record of electrical type business web site in advance, and perhaps described default shopping recommends word to obtain and store from the commercial articles searching ranking list of search website in advance.
3. method according to claim 1 is characterized in that, the described step of obtaining the default shopping recommendation word relevant with the shopping behavior of terminal device comprises:
Obtain the shopping information relevant with the shopping behavior of terminal device, described shopping information comprises: the keyword of terminal device search commercial articles, terminal device are browsed one or more in the merchandise news of merchandise news, terminal device purchased item of commodity;
According to the described shopping information that obtains, coupling obtains at least one default shopping corresponding with described shopping information and recommends word.
4. method according to claim 3 is characterized in that, the described step of obtaining the shopping information relevant with the shopping behavior of terminal device is:
Identify described shopping information from the shopping behavior of described terminal device, described shopping behavior comprises: one or more in the behavior of commodity are bought in the behavior that the behavior of terminal device inputted search key word, terminal device are browsed commodity, terminal device.
5. method according to claim 3 is characterized in that, described coupling obtains at least one default shopping corresponding with described shopping information and recommends the step of word to comprise:
A plurality of shopping informations are carried out clustering processing, obtain the shopping information class, wherein each shopping information class comprises at least one shopping information;
Each described shopping information class is mated at least one default shopping recommend word.
6. method according to claim 5 is characterized in that, described a plurality of shopping informations is carried out clustering processing, obtains also comprising before the step of shopping information class:
Described shopping information is divided into a plurality of shopping information elements;
Each shopping information element in described a plurality of shopping information elements is arranged weighted value, and described weighted value is used for representing the significance level of described shopping information element;
Described a plurality of shopping informations are carried out clustering processing, the step that obtains the shopping information class is:
According to the weighted value of described shopping information element, described shopping information is carried out clustering processing, obtain a plurality of shopping information classes.
7. method according to claim 6 is characterized in that, described weighted value according to described shopping information element carries out clustering processing to described shopping information, and the step that obtains a plurality of shopping information classes comprises:
Calculate the weighted value sum of all shopping information elements in the described shopping information;
Calculate the average weight value of shopping information element in the shopping information;
The shopping information of average weight value more than or equal to threshold limit is aggregated in the shopping information class of same class commodity.
8. method according to claim 5 is characterized in that, describedly each described shopping information class is mated at least one shopping recommends the step of word to comprise:
Recommend to choose wantonly the word shopping from a plurality of default shopping and recommend word, then calculate the weighted value sum of the shopping information element that jointly comprises in this shopping information class and the shopping recommendation word;
Calculate the weighted value sum of the shopping information element that jointly comprises, and the ratio between the number of the shopping information element that comprises in the shopping recommendation word;
Cycle calculations is recommended word until traveled through all shopping, recommends word for the corresponding shopping of ratio of a maximum of shopping information class coupling at last.
9. method according to claim 5 is characterized in that, the described step that described shopping information is divided into a plurality of shopping information elements is:
Mode according to participle is divided into a plurality of shopping information elements with described shopping information.
10. device with the terminal device interaction data is characterized in that described device comprises:
Memory module is used for the default shopping of storage and recommends word;
Acquisition module is used for obtaining the default shopping relevant with the shopping behavior of terminal device and recommends word;
Matching module is used for recommending word according to described default shopping, and coupling obtains recommending with described shopping the dependent merchandise information of at least one commodity corresponding to word;
Sending module sends to described terminal device for the dependent merchandise information that coupling is obtained described at least one commodity.
11. device according to claim 10 is characterized in that, described acquisition module comprises:
Acquiring unit is used for obtaining the shopping information relevant with the shopping behavior of described terminal device, and described shopping information comprises: the merchandise news of the keyword of terminal device search commercial articles and/or terminal device purchased item;
The first matching unit is used for according to the described shopping information that obtains, and coupling obtains at least one shopping corresponding with described shopping information and recommends word.
12. device according to claim 11, it is characterized in that, described acquiring unit is further used for identifying described shopping information from the shopping behavior of described terminal device, and described shopping behavior comprises: one or more in the behavior of commodity are bought in the behavior that the behavior of terminal device inputted search key word, terminal device are browsed commodity, terminal device.
13. device according to claim 11 is characterized in that, described the first matching unit comprises:
The cluster subelement is used for described shopping information is carried out clustering processing, obtains a plurality of shopping information classes, and wherein each shopping information class comprises at least one shopping information;
The coupling subelement is used for that each described shopping information class is mated at least one shopping and recommends word.
14. device according to claim 13 is characterized in that, described the first matching unit also comprises:
Divide subelement, be used for described shopping information is divided into a plurality of shopping information elements;
Subelement is set, is used for each shopping information element of described a plurality of shopping information elements is arranged weighted value, described weighted value is used for representing the significance level of described shopping information element;
The cluster subelement is further used for the weighted value according to described shopping information element, and a plurality of described shopping informations are carried out clustering processing, obtains the shopping information class.
15. device according to claim 14 is characterized in that, described cluster subelement is further used for calculating the weighted value sum of all shopping information elements in the described shopping information; Calculate the average weight value of shopping information element in the shopping information; Then the shopping information of average weight value more than or equal to threshold limit is aggregated in the shopping information class of same class commodity.
16. device according to claim 14, it is characterized in that, described coupling subelement is further used for recommending to choose wantonly the word shopping from a plurality of default shopping and recommends word, then calculates the weighted value sum of the shopping information element that jointly comprises in this shopping information class and the shopping recommendation word; Calculate the weighted value sum of the shopping information element that jointly comprises, and the ratio between the number of the shopping information element that comprises in the shopping recommendation word; Cycle calculations is recommended word until traveled through all shopping, recommends word for the corresponding shopping of ratio of a maximum of shopping information class coupling at last.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210469127.9A CN103020128B (en) | 2012-11-19 | 2012-11-19 | With the method and apparatus of data interaction with terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210469127.9A CN103020128B (en) | 2012-11-19 | 2012-11-19 | With the method and apparatus of data interaction with terminal device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103020128A true CN103020128A (en) | 2013-04-03 |
| CN103020128B CN103020128B (en) | 2015-12-09 |
Family
ID=47968732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210469127.9A Expired - Fee Related CN103020128B (en) | 2012-11-19 | 2012-11-19 | With the method and apparatus of data interaction with terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103020128B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034680A (en) * | 2012-11-19 | 2013-04-10 | 北京奇虎科技有限公司 | Data interaction method and device for terminal device |
| CN103559639A (en) * | 2013-10-31 | 2014-02-05 | 宇龙计算机通信科技(深圳)有限公司 | Commodity information processing method and device |
| CN104462438A (en) * | 2014-12-15 | 2015-03-25 | 北京搜狗科技发展有限公司 | Information processing method and device |
| CN104750760A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团上海有限公司 | Application software recommending method and device |
| CN106407232A (en) * | 2015-08-03 | 2017-02-15 | 天脉聚源（北京）科技有限公司 | A method and a system for statistical analysis for television shopping |
| CN107203518A (en) * | 2016-03-16 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Method, system and device, the electronic equipment of on-line system personalized recommendation |
| CN108388464A (en) * | 2018-03-07 | 2018-08-10 | 山东超越数控电子股份有限公司 | A kind of superior classification search method based on Local hydrodynamic unit |
| CN111401974A (en) * | 2020-06-03 | 2020-07-10 | 北京每日优鲜电子商务有限公司 | Information sending method, information sending device, electronic equipment and computer readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419779A (en) * | 2012-01-13 | 2012-04-18 | 青岛理工大学 | Commodity personalized search method and device based on attribute sorting |
| CN102479366A (en) * | 2010-11-25 | 2012-05-30 | 阿里巴巴集团控股有限公司 | Commodity recommending method and system |
| CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
| CN103034680A (en) * | 2012-11-19 | 2013-04-10 | 北京奇虎科技有限公司 | Data interaction method and device for terminal device |
-
2012
- 2012-11-19 CN CN201210469127.9A patent/CN103020128B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479366A (en) * | 2010-11-25 | 2012-05-30 | 阿里巴巴集团控股有限公司 | Commodity recommending method and system |
| CN102419779A (en) * | 2012-01-13 | 2012-04-18 | 青岛理工大学 | Commodity personalized search method and device based on attribute sorting |
| CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
| CN103034680A (en) * | 2012-11-19 | 2013-04-10 | 北京奇虎科技有限公司 | Data interaction method and device for terminal device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034680A (en) * | 2012-11-19 | 2013-04-10 | 北京奇虎科技有限公司 | Data interaction method and device for terminal device |
| CN103034680B (en) * | 2012-11-19 | 2015-11-25 | 北京奇虎科技有限公司 | For data interactive method and the device of terminal device |
| CN103559639A (en) * | 2013-10-31 | 2014-02-05 | 宇龙计算机通信科技(深圳)有限公司 | Commodity information processing method and device |
| CN104750760A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团上海有限公司 | Application software recommending method and device |
| CN104750760B (en) * | 2013-12-31 | 2018-11-23 | 中国移动通信集团上海有限公司 | A kind of implementation method and device for recommending application software |
| CN104462438A (en) * | 2014-12-15 | 2015-03-25 | 北京搜狗科技发展有限公司 | Information processing method and device |
| CN106407232A (en) * | 2015-08-03 | 2017-02-15 | 天脉聚源（北京）科技有限公司 | A method and a system for statistical analysis for television shopping |
| CN107203518A (en) * | 2016-03-16 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Method, system and device, the electronic equipment of on-line system personalized recommendation |
| CN108388464A (en) * | 2018-03-07 | 2018-08-10 | 山东超越数控电子股份有限公司 | A kind of superior classification search method based on Local hydrodynamic unit |
| CN108388464B (en) * | 2018-03-07 | 2021-05-18 | 山东超越数控电子股份有限公司 | Advanced classification retrieval method based on local refreshing |
| CN111401974A (en) * | 2020-06-03 | 2020-07-10 | 北京每日优鲜电子商务有限公司 | Information sending method, information sending device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103020128B (en) | 2015-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103034680B (en) | For data interactive method and the device of terminal device | |
| US11669579B2 (en) | Method and apparatus for providing search results | |
| US11314823B2 (en) | Method and apparatus for expanding query | |
| CN103020128B (en) | With the method and apparatus of data interaction with terminal device | |
| CN102253936B (en) | Method for recording access of user to merchandise information, search method and server | |
| CN102053983B (en) | Method, system and device for querying vertical search | |
| CN104077286A (en) | Commodity information search method and system | |
| CN109241403B (en) | Project recommendation method and device, machine equipment and computer-readable storage medium | |
| CN104850546B (en) | Display method and system of mobile media information | |
| CN109145280A (en) | The method and apparatus of information push | |
| CN102375885A (en) | Method and device for providing search suggestions corresponding to query sequence | |
| CN110827112B (en) | Deep learning commodity recommendation method and device, computer equipment and storage medium | |
| CN105677780A (en) | Scalable user intent mining method and system thereof | |
| CN103488785A (en) | Method, system and server for providing search service | |
| CN103618774A (en) | Resource recommending method, device and system based on network behaviors | |
| CN105512180A (en) | Search recommendation method and device | |
| CN110111167A (en) | A kind of method and apparatus of determining recommended | |
| CN107911448A (en) | Content pushing method and device | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN109190027A (en) | Multi-source recommended method, terminal, server, computer equipment, readable medium | |
| US11328005B2 (en) | Machine learning (ML) based expansion of a data set | |
| Zhu et al. | The case study for price extracting of mobile phone sell online | |
| US12056201B2 (en) | Systems and methods for automatic and adaptive browser bookmarks | |
| EP3062240A1 (en) | Search system, search criteria setting device, control method for search criteria setting device, program, and information storage medium | |
| CN104765747A (en) | Webpage processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151209 Termination date: 20211119 |