CN110110267A - Extract characteristics of objects, the method and apparatus of object search - Google Patents
Extract characteristics of objects, the method and apparatus of object search Download PDFInfo
- Publication number
- CN110110267A CN110110267A CN201810073340.5A CN201810073340A CN110110267A CN 110110267 A CN110110267 A CN 110110267A CN 201810073340 A CN201810073340 A CN 201810073340A CN 110110267 A CN110110267 A CN 110110267A
- Authority
- CN
- China
- Prior art keywords
- value
- word
- feature
- scheduled
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000000284 extract Substances 0.000 title claims description 17
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012913 prioritisation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 15
- 230000008859 change Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 7
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 241000406668 Loxodonta cyclotis Species 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Abstract
The invention discloses a kind of extraction characteristics of objects, the method and apparatus of object search, are related to field of computer technology.One specific embodiment of this method includes: the characteristic information for obtaining object in predetermined amount of time;Wherein, characteristic information includes at least fisrt feature information and second feature information;Word segmentation processing is carried out to fisrt feature information, the Feature Words of object are determined according to the quantity of word each after participle and scheduled fisrt feature word extracting rule;Rule is determined according to second feature information and scheduled object value, determines object in the object value of current time;It is at least based on Feature Words and object value, is generated and the associated mark sheet of object.This embodiment offers a kind of thinkings for extracting characteristics of objects, carry out object search according to characteristics of objects convenient for subsequent, so that search is more targeted, and then improve the search efficiency for the object.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of extraction characteristics of objects, the method for object search and dresses
It sets.
Background technique
With the improvement of people ' s living standards and the development of mobile Internet, people whenever and wherever possible can be in shopping websites
On do shopping, online shopping has become a kind of instantly the most popular shopping way.It at present include extensive stock in shopping platform
The system of sequence usually passes through the integrity degree of merchandise news, search field text similarity, commodity hits, volumes of searches, order
The factors such as number, positive rating, user behavior preference calculate weight order, and gained sequence plays commodity water conservancy diversion, raising Sales Volume of Commodity
To vital effect.
In realizing process of the present invention, inventor has found the prior art, and at least there are the following problems:
(1) existing ranking factor is typically based on historical data generation, but since the commodity of new restocking are no or lack this
The basic data of a little factors, causes sequence to be difficult to obtain flow rearward, is mentioned to cause seller by improper means such as brush lists
High goods weight, and then adverse effect is generated to electric business platform and social credibility.
(2) existing sort method needs the process of a data accumulation, but for timeliness, seasonal apparent quotient
Product, it is understood that there may be being added to weight the phenomenon that no longer effective property, be unfavorable for the sale of the commodity.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of extraction characteristics of objects, the method and apparatus of object search, at least can
Enough solve the phenomenon that existing sequencing means are not suitable for newly created object and timeliness apparent object.
To achieve the above object, according to an aspect of an embodiment of the present invention, a kind of side for extracting characteristics of objects is provided
Method characterized by comprising obtain the characteristic information of object in predetermined amount of time;Wherein, the characteristic information includes at least the
One characteristic information and second feature information;Word segmentation processing is carried out to the fisrt feature information, according to word each after participle
Quantity and scheduled fisrt feature word extracting rule, determine the Feature Words of the object;According to the second feature information
And scheduled object value determines rule, determines the object in the object value of current time;At least based on the Feature Words with
And the object value, it generates and the associated mark sheet of the object.
Optionally, the quantity according to word each after participle and scheduled fisrt feature word extracting rule determine
The Feature Words of the object include: to determine the first pad value of each word after participle according to scheduled first decay formula, mention
Taking word of first pad value beyond predetermined drop threshold is the Feature Words of the object.
Optionally, the second feature information includes at least the creation time and history log information of the object;Institute
It states and rule is determined according to the second feature information and scheduled object value, determine the object in the object value of current time
Include: the creation time and scheduled second decay formula according to the object, determines the temperature of the object when current
Between the second pad value;According to the history log information of the object and scheduled value of feedback method of determination, it is described right to determine
As the value of feedback in current time;According to second pad value and the value of feedback, determine the object in current time
The object value.
To achieve the above object, other side according to an embodiment of the present invention provides a kind of method of object search,
It is characterised by comprising: being generated and the associated spy of the object using the method described in any of the above embodiments for extracting characteristics of objects
Levy table;And searching request is received, according to scheduled second feature word extracting rule, determine that first in described search request is special
Levy word;When the fisrt feature word is in the mark sheet, the first object for meeting described search request is obtained;It obtains each
The object value of first object is extracted object value and is sent beyond the first object concurrency of predetermined object value threshold value.
Optionally, further includes: the creation time for obtaining each first object determines that the difference of creation time and current time exists
The first object priority arrangement within the scope of preset space length.
Optionally, the second feature word extracting rule includes at least the fisrt feature word extracting rule and normalization
Rule.
To achieve the above object, according to another aspect of an embodiment of the present invention, a kind of dress for extracting characteristics of objects is provided
It sets characterized by comprising object acquisition module, for obtaining the characteristic information of object in predetermined amount of time;Wherein, described
Characteristic information includes at least fisrt feature information and second feature information;Feature Words extraction module, for special to described first
Reference breath carries out word segmentation processing, according to the quantity of word each after participle and scheduled fisrt feature word extracting rule, determines
The Feature Words of the object;Object value determining module, for being determined according to the second feature information and scheduled object value
Rule determines the object in the object value of current time;Mark sheet generation module, at least based on the Feature Words and
The object value generates and the associated mark sheet of the object.
Optionally, the Feature Words extraction module, is used for: according to scheduled first decay formula, determining each after segmenting
First pad value of word extracts the Feature Words that word of first pad value beyond predetermined drop threshold is the object.
Optionally, the second feature information includes at least the creation time and history log information of the object;Institute
State object value determining module, be used for: according to the creation time of the object and scheduled second decay formula, it is described right to determine
Second pad value of the temperature of elephant in current time;It is determined according to the history log information of the object and scheduled value of feedback
Mode determines the object in the value of feedback of current time;According to second pad value and the value of feedback, determine described in
The object value of the object in current time.
To achieve the above object, according to another aspect of an embodiment of the present invention, a kind of device of object search is provided,
It is characterized in that, comprising: using the device described in any of the above embodiments for extracting characteristics of objects, generate and the associated feature of the object
Table;And request receiving module, according to scheduled second feature word extracting rule, is searched for receiving searching request described in determination
Fisrt feature word in rope request;Object search module, for obtaining symbol when the fisrt feature word is in the mark sheet
Close the first object of described search request;Object screening module extracts object value for obtaining the object value of each first object
The first object concurrency beyond predetermined object value threshold value is sent.
Optionally, further include object arrangement module, be used for: obtaining the creation time of each first object, when determining creation
Between and first object priority of the difference within the scope of preset space length of current time arrange.
Optionally, the second feature word extracting rule includes at least the fisrt feature word extracting rule and normalization
Rule.
To achieve the above object, according to an embodiment of the present invention in another aspect, providing a kind of extraction characteristics of objects, search
The electronic equipment of object.
The electronic equipment of the embodiment of the present invention includes: one or more processors;Storage device, for storing one or more
A program, when one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes any of the above-described extraction characteristics of objects, the method for object search.
To achieve the above object, according to an embodiment of the present invention in another aspect, provide a kind of computer-readable medium,
On be stored with computer program, any of the above-described extraction characteristics of objects, search are realized when described program is executed by processor
The method of object.
The scheme of the offer according to the present invention, one embodiment in foregoing invention have the following advantages that or beneficial to effects
Fruit: a kind of special new approaches for extracting feature and special search for object are provided, the search for object is improved
Accuracy meets the search need of user, while the user experience is improved.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is a kind of main flow schematic diagram of method for extracting characteristics of objects according to an embodiment of the present invention;
Fig. 2 is a kind of flow diagram of optional method for extracting characteristics of objects according to an embodiment of the present invention;
Fig. 3 is the flow diagram of another optional method for extracting characteristics of objects according to an embodiment of the present invention;
Fig. 4 is a kind of flow diagram of the method for object search according to an embodiment of the present invention;
Fig. 5 is a kind of flow diagram of the method for optional object search according to an embodiment of the present invention;
Fig. 6 is a kind of main modular schematic diagram of device for extracting characteristics of objects according to an embodiment of the present invention;
Fig. 7 is a kind of main modular schematic diagram of the device of object search according to an embodiment of the present invention;
Fig. 8 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein;
Fig. 9 is adapted for the structural representation for realizing the mobile device of the embodiment of the present invention or the computer system of server
Figure.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
It should be noted that the embodiment of the present invention is suitable for online service mild-natured, such as shopping, tourism, food and drink, video
Water conservancy diversion etc..Provided object include but is not limited to be video, food and drink, commodity etc., for example, (for example, 30 in predetermined amount of time
It) restocking for the first time sale (abbreviation restocking later) new commodity (abbreviation new product later).For the object repeated, for example, it is heavy
The commodity of multiple restocking, to reduce the influence to online service order, the present invention is not considered herein.
Referring to Fig. 1, thus it is shown that a kind of broad flow diagram for the method for extracting characteristics of objects provided in an embodiment of the present invention,
Include the following steps:
S101: the characteristic information of object in predetermined amount of time is obtained;Wherein, characteristic information includes at least fisrt feature information
And second feature information.
S102: carrying out word segmentation processing to fisrt feature information, according to the quantity of word each after participle and scheduled the
One Feature Words extracting rule, determines the Feature Words of object.
S103: rule is determined according to second feature information and scheduled object value, determines object in pair of current time
As value.
S104: being at least based on Feature Words and object value, generates and the associated mark sheet of object.
In above embodiment, for step S101, each object has its creation time, it is possible thereby to extract predetermined
The object of (for example, 30 days) in period, such as extract the quotient of restocking for the first time and shelf life within certain time limit in commodity library
Product, to prevent the commodity of restocking for a long time from still occurring in new product the selection result.
In addition, the characteristic information of object includes but is not limited to be creation time, identification information, description information etc..It is obtaining
It while characteristic information, needs to judge whether object meets judgement demand, i.e., whether is specified desired object.It is with new product
Example, judge that commodity for the mode of new product, can be judged according to merchandise news, the merchandise news include but is not limited to be commodity
Description information, commodity ID, commodity shelf life.Its specific judgement can be just like under type:
(1) stabbed and judged according to the creation time of object: each object has respective creation time to stab, such as
2018.01.02 restocking commodity A, hereafter object changes (for example, restocking after commodity elder generation undercarriage) anyway, this timestamp is
Constant;
(2) according to the identification information judgment of object: each object has respective identification information, which can deposit
It is stored in object information library, can't change.Match if being inquired in object information library less than with object id information
Information when, it may be determined that the object creates for the first time, for example, the new product of restocking for the first time;For modifying the object uploaded again after deleting
(for example, the commodity for repeating restocking), identification information is constant, and presence can be inquired in object information library;
(3) judged according to the description information of object: object on line has relevant description information, which can be with
It is picture, title, introduction etc., and these description informations and the object composition generate a data, are stored in object information library.
For newly created object (for example, the commodity for repeating restocking) identical with original object, if its description information and object information
The similarity of Reassessment information in library exceeds certain similarity threshold, for example, similarity is greater than 90%, can be confirmed and has deposited
In history object similar with the object, which is not considered.
Wherein, judged according to the similarity of object factory information, it can be just like under type:
1) text description comparison: segmenting text description information, judges between word (participle minimum unit) set
Multiplicity, such as after participle " winter money one-piece dress " and " one-piece dress winter money " there is it is highly similar;
2) image comparison: what is generallyd use at present is to extract finger image first to be compared again.For example, by picture normalizing
Change to same size (for example, 1250 pixels), extracts pixel value from specific pixel, the picture with other image same positions
Element carry out pixel value comparison, the identical quantity of statistical pixel, when quantity exceed predetermined quantity threshold value (for example, 10), can be true
The two fixed objects are similar.
For step S102, for acquired object, before determining Feature Words, can to its fisrt feature information into
Row participle operation, word segmentation processing can be just like under type:
(1) object created in predetermined amount of time is chosen, determines corresponding fisrt feature information, such as its description letter
Breath, generic etc.;
(2) according to the search fields such as title, description, category, brand name, store name, type, for the fisrt feature of object
Information carries out word segmentation processing, multiple words after being segmented;
(3) according to the weight size of different search fields, such as title > description > type, the word after participle is arranged
Sequence generates word set.
By taking predetermined amount of time is 30 as an example, for identified object, a word set is generated daily with creation time;It
Afterwards, the word set for counting all objects in the time limit, multiple word will occurs and is counted and normalized, to reduce background service
Operating pressure, it is final to merge one total word set of generation, statistical distribution is improved compared with single word set, reduces the heat of single object
Degree ratio.
It should be noted that within the time limit of being in certain due to the different and determining object of the creation time of each object, because
This, will not change for the single word set of predetermined amount of time, but for total word set, can occur therewith with the change of time
Variation.
For the word set of object, the Feature Words that can wherein embody characteristics of objects can be extracted, which includes but unlimited
Then such as under type:
(1) determine that the high frequency words in characteristic information, i.e. frequency of occurrence are characterized word, example beyond the word of pre-determined number threshold value
Such as, " ankle boots ";
(2) for the object just created, temperature (concerned degree) is gradually smaller with the growth of shelf life, when
When reaching intended duration, it may be determined that it is no longer new object.Therefore, each word can be calculated according to certain damped expoential
Decay fraction determine word of the gross score beyond predetermined score threshold value for spy with this cumulative gross score for obtaining each word
Levy word.
It,, can also be according to the second spy of object in addition to extracting Feature Words for identified object for step S103
Reference breath carries out scoring operations to it, for example, creation time, history log information etc., convenient for according to score value to the object into
Row sequence.It specifically can be just like under type:
1) from after Object Creation, user gives a mark to its positive rating;
2) it is given a mark according to the clicking rate of object, buying rate;
3) it is given a mark according to the temperature of object (that is, concerned degree);
4) it is given a mark according to the temperature of object generic;
5) it is given a mark according to the download of platform where object, clicking rate.
Temperature due to object etc. can be gradually decreased with the growth of its shelf life, and its click volume, buying rate etc.
It can be gradually increased with the growth of its shelf life, therefore, for aforesaid way, can be used in combination, can also individually make
Herein with no restrictions with, the present invention.
In addition, a field of the object value as object record, can show with object being incremented by for time and be changed, when right
When reaching intended duration as display, it is no longer new product that its object value, which is returned behind 0, such as New Arrivals 30 days,.
It is right that object-Feature Words-can be generated after the Feature Words and object value for determining object for step S104
As the mark sheet of value, which can change therewith with the variation of time, therefore, can cover update for mark sheet.In addition,
Can also frequency of occurrence, the size of object value etc. according to Feature Words, according to sequence from big to small, for pair in mark sheet
As being ranked up.
Further, object-Feature Words-object value label can also be generated, and adds the label into characteristics of objects.By
Change in Feature Words and object value with object shelf life, therefore the label can cache, and can also change over time
Substitution updates, and the present invention is herein with no restrictions.
Method provided by above-described embodiment, provide it is a kind of extract characteristics of objects thinking, by characteristic information into
Row Feature Words extract and object value determines, generate mark sheet associated with object and are mentioned with the multidimensional characteristic of this conservation object
The accuracy that high characteristics of objects is extracted.In addition, since Feature Words and object value can be gradually changed with being incremented by for time, because
This, gained mark sheet can more fully demonstrate Properties of Objects and the concerned degree from after creating, and more meet the change of its temperature
Law.
Referring to fig. 2, a kind of optional method flow signal for extracting characteristics of objects according to an embodiment of the present invention is shown
Figure, includes the following steps,
S201: the characteristic information of object in predetermined amount of time is obtained;Wherein, characteristic information includes at least fisrt feature information
And second feature information.
S202: carrying out word segmentation processing to fisrt feature information, according to scheduled first decay formula, determines each after segmenting
First pad value of word extracts the Feature Words that word of first pad value beyond predetermined drop threshold is object.
S203: rule is determined according to second feature information and scheduled object value, determines object in pair of current time
As value.
S204: being at least based on Feature Words and object value, generates and the associated mark sheet of object.
In above embodiment, step S201, S203, S204 can distinguish step S101, S103, S104 shown in Figure 1
Description, details are not described herein.
In above embodiment, for step S202, shopping platform increases the temperature of object with shelf life on line
Situation of change, usually rapid decay early period, later period decay at a slow speed.The situation is similar to the decaying that internet hot spots F.F. goes out fastly
Trend, therefore the phase mode that declines can be used, each word of its object is extracted, which includes but is not limited to be
Linear attenuation, half-life period decaying.The present invention mainly uses half-life period damped manner;Wherein, half-life period is characterized the reduction of word score
For the time needed for original half, length of time can reflect the rate of decay of object.
Specifically, the first decay formula can be following formula:
M=M* (1/2) ^ (t/T)
According to the frequency of occurrence of each word in word set, the first pad value of each word is calculated, such as each word daily
The first pad value m, with Feature Words dimension then was carried out cumulative summarize to 30 days scores;Wherein, M is that initial time object is special
Levy the first foundation value of word, such as 100;T is the reaction time, corresponding to the time of object restocking in intended duration, such as 1
~30 days;T is half-life period, such as 7 days.
Citing is specifically described below:
For example, the same day newly creates 3 objects, respective characteristic information is obtained, and fisrt feature information is divided respectively
Word operation, obtains:
Object 1:ABCD
Object 2:CDEF
Object 3:ADE
The number that each word occurs is counted, is obtained:
A:2 times;B:1 times;C:2 times;D:3 times;E:2 times;F:1 times
Above-mentioned word input half-life period formula is calculated, score K1 of each word on the day of is obtained;
If the statistics of yesterday are as follows:
A:3 times;B:2 times;C:1 times;G:1 times;
Due to the growth of shelf life, the word of yesterday need to be inputted in half-life period formula and carry out decay calculation, obtained
Score K2 (K1* decaying number);
Successively analogy can be intended to 0 for the pad value that the same day is calculated, if but the word in daily newly created object
In occur again, then the word is no longer intended to 0, therefore 30 days pad values are merged, and daily pad value is according to restocking
Time is calculated.
Further, for online shopping platform, the object created for the first time counted on daily may be ten hundreds of, because
This obtained Feature Words quantity is more, to mitigate background service operating pressure, is inputting its frequency of occurrence to half-life period formula
Before, it can be normalized first, for example, compression number is between 1~100.
The corresponding relationship of " word-pad value " is calculated through the above steps, and according to the size order of pad value, rejecting declines
Depreciation is lower than the word of predetermined attenuation value threshold value, exports Feature Words;It can also be to obtained Feature Words, according to the big of pad value
It is small to be ranked up.
Method provided by above-described embodiment provides a kind of specific mode for extracting characteristics of objects word, according to half-life period
Formula, calculates the pad value of each word frequency of occurrence within a predetermined period of time, and the temperature that aforesaid way more meets object declines
Subtract trend, so that the Feature Words extracted more meet the decay characteristics of object.
Referring to Fig. 3, shows another optional method flow for extracting characteristics of objects according to an embodiment of the present invention and show
It is intended to, includes the following steps:
S301: the characteristic information of object in predetermined amount of time is obtained;Wherein, characteristic information includes at least fisrt feature information
And second feature information, and second feature information includes at least the creation time and history log information of object.
S302: carrying out word segmentation processing to fisrt feature information, according to the quantity of word each after participle and scheduled the
One Feature Words extracting rule, determines the Feature Words of object.
S303: according to the creation time of object and scheduled second decay formula, determine the temperature of object when current
Between the second pad value;
S304: according to the history log information of object and scheduled value of feedback method of determination, determine object when current
Between value of feedback;
S305: according to the second pad value and value of feedback, determine object in the object value of current time.
S306: being at least based on Feature Words and object value, generates and the associated mark sheet of object.
In above embodiment, step S301, S306 can distinguish the description of step S101, S104 shown in Figure 1, step
S302 can be found in the description of step S202 shown in step S102 shown in Fig. 1 and Fig. 2, and details are not described herein.
In above embodiment, for step S303~S305, trap queuing can be carried out for object, which can be with
It is carried out according to object value, wherein object value mainly includes 2 parts:
(1) second pad value: representing the decaying of object temperature, which works as the day before yesterday by the time gap of object restocking
The difference of phase determines that the second basic value at this time can also use first foundation value shown in Fig. 2, it is possible to distinguish in first foundation
Value, for example, value 50.Used second decay formula, can be identical as the first decay formula, referring specifically to according to Fig. 2 institute
Show description, be also possible to other formula known to those skilled in the art, the present invention is herein with no restrictions;
(2) value of feedback: for object, creating second day at it there is corresponding history log information, the history log
Information corresponds to first day user of creation for the browsing click volume of the object.Object appears in equipment (for example, mobile phone, computer)
Last time will report the object single exposure from the background, indicate that user sees the object;If user browses and clicks and checks
The object, backstage can also report the object one click;Later according to light exposure and click volume, the anti-of the object is calculated
Feedback value, i.e. exposure click conversion ratio;Wherein, which clicks conversion ratio=total touching quantity/total exposure quantity.
It is specifically described below with embodiment:
Object Creation restocking first day, total object value was 100 points, and the second pad value is 50 points, and initial feedback value is 50
Point.With the growth of object shelf life, the second pad value and value of feedback change therewith, specifically:
Second pad value: 50 points of restocking first day, second day 45 points, third day 41 divides ... the 7th day 25 points ... third
Ten days 2 points;
Value of feedback: assuming that first day conversion ratio 5% of restocking, second day conversion ratio 10% ...
Further, before determining value of feedback, operation can also be normalized to the value of feedback being calculated, that is, unites
The average conversion for counting each object normalizes to preset range as value of feedback, such as 0~50, is improved with reducing businessman
Value of feedback and the case where practise fraud.Normalized concrete mode include but is not limited to be 50*log (n), wherein n be average conversion.
Method provided by above-described embodiment provides a kind of thinking of determining object value, the main creation according to object
Time and exposure rate meet the variation tendency of the concerned degree of object, while being convenient for ranked object, improve the management of object
Efficiency.
Referring to fig. 4, thus it is shown that a kind of broad flow diagram of the method for object search provided in an embodiment of the present invention, including
Following steps:
S401: the characteristic information of object in predetermined amount of time is obtained;Wherein, characteristic information includes at least fisrt feature information
And second feature information.
S402: carrying out word segmentation processing to fisrt feature information, according to the quantity of word each after participle and scheduled the
One Feature Words extracting rule, determines the Feature Words of object.
S403: rule is determined according to second feature information and scheduled object value, determines object in pair of current time
As value.
S404: being at least based on Feature Words and object value, generates and the associated mark sheet of object.
S405: receiving searching request, according to scheduled second feature word extracting rule, determines that first in searching request is special
Levy word.
S406: when fisrt feature word is in mark sheet, the first object for meeting searching request is obtained.
S407: obtaining the object value of each first object, extracts the first object that object value exceeds predetermined object value threshold value
And it sends.
In above embodiment, step S401, S404 can distinguish the description of step S101, S104 shown in Figure 1, step
S402 can be found in the description of step S202 shown in step S102 shown in Fig. 1 and Fig. 2, and step S403 can be found in step shown in Fig. 1
The description of step S303~S305 shown in S103 and Fig. 3, details are not described herein.
Which by determining the Feature Words of object, for searching for front end, can determine in the searching request for receiving word
When, there is object screening item, such as new product screens item, and do not occur then for which word.Equally, for the object of object
Value, for the sale, click, browsing convenient for high-quality object, can only extract partial objects and be shown.
In above embodiment, for step S405, when receiving user after searching for the searching request of front end input, after
Platform can parse the searching request, obtain and analyze search information therein.When the Feature Words in search information are in spy generated
When levying in table, corresponding object can be exported and browsed to search interface for user.For light exposure, the pageview for improving partial objects
And sales volume, it can only display portion sort forward object, or new object is preferentially arranged in list object
Column display.
In addition, can be Fig. 1 and Feature Words shown in Fig. 2 for the fisrt feature word acquisition modes in searching request
Extracting rule is also possible to the search query word (search query) in original search request or by normalizing (for example, big
Write turn small letter, traditional font turns simplified, filter extra space etc.) search query word, specific embodiment, the present invention is herein not
It is limited.
For step S406, when the Feature Words searched in information are in mark sheet, " the spy in search information can be exported
Levy word+object " portmanteau word in the search option of search interface, for user select, such as in drop-down option " autumn clothing is new
Product " from the background can filter the commodity comprising the specific word but not new product if user selects the option, be beaten with only showing
Mark the commodity of new product.
The option of " object " can also be set in search interface Filter Options, for example, new product option, wherein is
Choice box.When receiving user and choosing the request of new product, new product can be exported to search interface;If user inputs search letter simultaneously
When breath, matching inquiry can be carried out in new product in conjunction with the search information, meet the new product of searching request to searching for boundary to export
Face.
In addition, needing all inquire presence, such as " autumn in feature vocabulary for the Feature Words in searching request
Dress " " one-piece dress ", if one of word " autumn clothing " " even skirt " when query result is no in feature vocabulary, is no longer directed at this time
Object is exported.
In addition, above embodiment is equally applicable to the object search under certain object type, to guide user to browse, increase
Add the pageview and sales volume of special object, wherein object type include but is not limited to be electric appliance, clothes, shoes packet, accessories.
Mark sheet at this time corresponds to the certain object type, so that determining that the feature of object under the type has specific aim, for example, special
Determine the new product under commodity category.
The click conversion ratio of high mass object is improved to accelerate user for the acquisition efficiency of object for step S407,
Object value threshold value (for example, 0,0.4) can be preset, the object that object value exceeds the predetermined object value threshold value is only exported;Its
In, which can also carry out input setting by user by system sets itself, for example, in the screening item of search interface
Middle addition object value range selects option.
In addition, object value is only used as a weighted term, can be used for when output meets the list object of searching request to right
The screening of elephant.For the integrated ordered of object, it is also necessary to the other information in relation to object or businessman is considered, for example, businessman's prestige
Degree, integrity degree of object information etc..
Method provided by above-described embodiment provides a kind of thinking searched for and screen object, meets user for right
The concern demand of elephant conducive to the exposure clicking rate of object, while improving the sequencing display of timeliness object, is that the browsing of object is sold
It provides convenience, reduces the case where businessman improves object ranking by improper means.In addition, by pair under specific type
As carrying out special water conservancy diversion, so that water conservancy diversion has specific aim, embodies the personalization features of certain object type.
Referring to Fig. 5, a kind of method flow schematic diagram of optional object search according to an embodiment of the present invention is shown, is wrapped
Include following steps:
S501: the characteristic information of object in predetermined amount of time is obtained;Wherein, characteristic information includes at least fisrt feature information
And second feature information.
S502: carrying out word segmentation processing to fisrt feature information, according to the quantity of word each after participle and scheduled the
One Feature Words extracting rule, determines the Feature Words of object.
S503: rule is determined according to second feature information and scheduled object value, determines object in pair of current time
As value.
S504: being at least based on Feature Words and object value, generates and the associated mark sheet of object.
S505: receiving searching request, according to scheduled second feature word extracting rule, determines that first in searching request is special
Levy word.
S506: when fisrt feature word is in mark sheet, the first object for meeting searching request is obtained.
S507: obtaining the object value of each first object, extracts the first object that object value exceeds predetermined object value threshold value.
S508: obtaining the creation time of each first object, determines the difference of creation time and current time in preset space length
The first object priority arrangement in range.
In above embodiment, step S501, S504 can distinguish the description of step S101, S104 shown in Figure 1, step
S502 can be found in the description of step S202 shown in step S102 shown in Fig. 1 and Fig. 2, and step S503 can be found in step shown in Fig. 1
The description of step S303~S305 shown in S103 and Fig. 3, step S505~S507 can be found in step S405~S407 shown in Fig. 4
Description, details are not described herein.
In above embodiment, for step S508, for object in the sequence of search interface, including but is not limited to is figure
Mode shown in 4 can also be arranged according to the creation time of object according to the distance interval length of creation time and current time
Column, for example, current time be 2018.01.03, commodity A for the first time shelf life be 2018.01.02, commodity B restocking for the first time when
Between be 2018.01.01, then in search interface, prioritization commodity A.
Method provided by above-described embodiment provides a kind of sequence thinking for object, to improve the exposure of object
Light quantity converts convenient for the click of object, improves the efficient sequence of timeliness object.In addition, by object carry out scoring operations, when
Between sort judgement, improve user and look for the efficiency of high-quality object, new creation object, and then improve the user experience.
Referring to Fig. 6, the main modular for showing a kind of device 600 for extracting characteristics of objects provided in an embodiment of the present invention is shown
It is intended to, comprising:
Object acquisition module 601, for obtaining the characteristic information of object in predetermined amount of time;Wherein, the characteristic information
Including at least fisrt feature information and second feature information;
Feature Words extraction module 602, for carrying out word segmentation processing to the fisrt feature information, according to word each after participle
The quantity of language and scheduled fisrt feature word extracting rule, determine the Feature Words of the object;
Object value determining module 603, for determining rule according to the second feature information and scheduled object value, really
Object value of the fixed object in current time;
Mark sheet generation module 604 generates and the object for being at least based on the Feature Words and the object value
Associated mark sheet.
In implementing device of the present invention, the Feature Words extraction module 602 is used for:
According to scheduled first decay formula, the first pad value of each word after participle is determined, extract the first pad value
Word beyond predetermined drop threshold is the Feature Words of the object.
In implementing device of the present invention, the second feature information includes at least creation time and the history day of the object
Will information;
The object value determining module 603, is used for:
According to the creation time of the object and scheduled second decay formula, determine the temperature of the object current
The second pad value of time;
According to the history log information of the object and scheduled value of feedback method of determination, determine the object current
The value of feedback of time;
According to second pad value and the value of feedback, determine the object in the object value of current time.
Referring to Fig. 7, a kind of main modular signal of the device 700 of object search provided in an embodiment of the present invention is shown
Figure, comprising:
Using the device described in any of the above embodiments for extracting characteristics of objects, generate and the associated mark sheet of the object;With
And
Request receiving module 701, according to scheduled second feature word extracting rule, determines institute for receiving searching request
State the fisrt feature word in searching request;
Object search module 702, for when the fisrt feature word is in the mark sheet, acquisition to meet described search
First object of request;
Object screening module 703 extracts object value and exceeds predetermined object value for obtaining the object value of each first object
First object concurrency of threshold value is sent.
Implementing device of the present invention further includes object arrangement module 704, is used for:
The creation time for obtaining each first object determines the difference of creation time and current time within the scope of preset space length
The first object priority arrangement.
In implementing device of the present invention, the second feature word extracting rule includes at least the fisrt feature word extracting rule
And normalization rule.
Device provided by above-described embodiment provides a kind of sequence thinking for object, to improve the exposure of object
Light quantity converts convenient for the click of object, improves the efficient sequence of timeliness object.In addition, by object carry out scoring operations, when
Between sort judgement, improve user and look for the efficiency of high-quality object, new creation object, and then improve the user experience.
In addition, the specific implementation content of the device of extraction characteristics of objects, object search described in embodiments of the present invention,
It has been described in detail in the method for object search described above, therefore has no longer illustrated in this duplicate contents.
The extraction characteristics of objects, object search method or apparatus that can apply the embodiment of the present invention are shown referring to Fig. 8
Exemplary system architecture 800.
As shown in figure 8, system architecture 800 may include terminal device 801,802,803, network 804 and server 805.
Network 804 between terminal device 801,802,803 and server 805 to provide the medium of communication link.Network 804 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 801,802,803 and be interacted by network 804 with server 805, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 801,802,803
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social intercourse system softwares.
Terminal device 801,802,803 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 805 can be to provide the server of various services, such as utilize terminal device 801,802,803 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to reception
To the data such as information query request analyze etc. processing, and by processing result (such as target push information, product letter
Breath -- merely illustrative) feed back to terminal device.
It should be noted that object method is arranged provided by the embodiment of the present invention in lists generally by server 805
It executes, correspondingly, arranges object apparatus in lists and be generally positioned in server 805.
It should be understood that the number of terminal device, network and server in Fig. 8 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Referring to Fig. 9, it illustrates the knots of the computer system 900 for the terminal device for being suitable for being used to realize the embodiment of the present invention
Structure schematic diagram.Terminal device shown in Fig. 9 is only an example, should not function and use scope band to the embodiment of the present invention
Carry out any restrictions.
As shown in figure 9, computer system 900 includes central processing unit (CPU) 901, it can be read-only according to being stored in
Program in memory (ROM) 902 or be loaded into the program in random access storage device (RAM) 903 from storage section 908 and
Execute various movements appropriate and processing.In RAM 903, also it is stored with system 900 and operates required various programs and data.
CPU 901, ROM 902 and RAM 903 are connected with each other by bus 904.Typing/output (I/O) interface 905 is also connected to always
Line 904.
I/O interface 905 is connected to lower component: the typing part 906 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 907 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage section 908 including hard disk etc.;
And the communications portion 909 of the network interface card including LAN card, modem etc..Communications portion 909 via such as because
The network of spy's net executes communication process.Driver 910 is also connected to I/O interface 905 as needed.Detachable media 911, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 910, in order to read from thereon
Computer program be mounted into storage section 908 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 909, and/or from can
Medium 911 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 901, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
Include object acquisition module, Feature Words extraction module, object value determining module and mark sheet generation module.Wherein, these modules
Title do not constitute the restriction to the module itself under certain conditions, for example, object acquisition module is also described as
" characteristic information of object obtains module ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment;It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
Obtaining the equipment includes:
Obtain the characteristic information of object in predetermined amount of time;Wherein, the characteristic information includes at least fisrt feature information
And second feature information;
Word segmentation processing is carried out to the fisrt feature information, according to the quantity of word each after participle and scheduled first
Feature Words extracting rule determines the Feature Words of the object;
Rule is determined according to the second feature information and scheduled object value, determines the object in current time
Object value;
It is at least based on the Feature Words and the object value, is generated and the associated mark sheet of the object.
And
Searching request is received, according to scheduled second feature word extracting rule, determines that first in described search request is special
Levy word;
When the fisrt feature word is in the mark sheet, the first object for meeting described search request is obtained;
The object value of each first object is obtained, the first object concurrency that object value exceeds predetermined object value threshold value is extracted
It send.
Technical solution according to an embodiment of the present invention provides a kind of sequence thinking for object, to improve object
Light exposure, convenient for object click convert, improve timeliness object efficient sequence.In addition, by carrying out marking behaviour to object
Make, time-sequencing judgement, improves user and look for the efficiency of high-quality object, new creation object, and then improve the user experience.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (14)
1. a kind of method for extracting characteristics of objects characterized by comprising
Obtain the characteristic information of object in predetermined amount of time;Wherein, the characteristic information include at least fisrt feature information and
Second feature information;
Word segmentation processing is carried out to the fisrt feature information, according to the quantity and scheduled fisrt feature of word each after participle
Word extracting rule determines the Feature Words of the object;
Rule is determined according to the second feature information and scheduled object value, determines the object in the object of current time
Value;
It is at least based on the Feature Words and the object value, is generated and the associated mark sheet of the object.
2. the method according to claim 1, wherein the quantity according to word each after participle and predetermined
Fisrt feature word extracting rule, determine that the Feature Words of the object include:
According to scheduled first decay formula, the first pad value of each word after participle is determined, extract the first pad value and exceed
The word of predetermined drop threshold is the Feature Words of the object.
3. the method according to claim 1, wherein the second feature information includes at least the wound of the object
Build time and history log information;
It is described that rule is determined according to the second feature information and scheduled object value, determine the object in current time
Object value includes:
According to the creation time of the object and scheduled second decay formula, determine the temperature of the object in current time
The second pad value;
According to the history log information of the object and scheduled value of feedback method of determination, determine the object in current time
Value of feedback;
According to second pad value and the value of feedback, determine the object in the object value of current time.
4. a kind of method of object search characterized by comprising
Using the method for the extraction characteristics of objects of any of claims 1-3, generate and the associated feature of the object
Table;And
Searching request is received, according to scheduled second feature word extracting rule, determines the fisrt feature word in described search request;
When the fisrt feature word is in the mark sheet, the first object for meeting described search request is obtained;
The object value of each first object is obtained, object value is extracted and is sent beyond the first object concurrency of predetermined object value threshold value.
5. according to the method described in claim 4, it is characterized by further comprising:
The creation time for obtaining each first object determines of the difference of creation time and current time within the scope of preset space length
An object prioritization.
6. according to the method described in claim 4, it is characterized in that, the second feature word extracting rule includes at least described the
One Feature Words extracting rule and normalization rule.
7. a kind of device for extracting characteristics of objects characterized by comprising
Object acquisition module, for obtaining the characteristic information of object in predetermined amount of time;Wherein, the characteristic information includes at least
Fisrt feature information and second feature information;
Feature Words extraction module, for carrying out word segmentation processing to the fisrt feature information, according to the number of word each after participle
Amount and scheduled fisrt feature word extracting rule, determine the Feature Words of the object;
Object value determining module, described in determining according to the second feature information and the determining rule of scheduled object value
Object value of the object in current time;
Mark sheet generation module generates associated with the object for being at least based on the Feature Words and the object value
Mark sheet.
8. device according to claim 7, which is characterized in that the Feature Words extraction module is used for:
According to scheduled first decay formula, the first pad value of each word after participle is determined, extract the first pad value and exceed
The word of predetermined drop threshold is the Feature Words of the object.
9. device according to claim 7, which is characterized in that the second feature information includes at least the wound of the object
Build time and history log information;
The object value determining module, is used for:
According to the creation time of the object and scheduled second decay formula, determine the temperature of the object in current time
The second pad value;
According to the history log information of the object and scheduled value of feedback method of determination, determine the object in current time
Value of feedback;
According to second pad value and the value of feedback, determine the object in the object value of current time.
10. a kind of device of object search characterized by comprising
Using the device of extraction characteristics of objects described in any one of claim 7-9, generate and the associated feature of the object
Table;And
Request receiving module, according to scheduled second feature word extracting rule, determines that described search is asked for receiving searching request
Fisrt feature word in asking;
Object search module meets described search request for obtaining when the fisrt feature word is in the mark sheet
First object;
Object screening module extracts object value beyond predetermined object value threshold value for obtaining the object value of each first object
First object concurrency is sent.
11. device according to claim 10, which is characterized in that further include object arrangement module, be used for:
The creation time for obtaining each first object determines of the difference of creation time and current time within the scope of preset space length
An object prioritization.
12. device according to claim 10, which is characterized in that the second feature word extracting rule includes at least described
Fisrt feature word extracting rule and normalization rule.
13. a kind of electronic equipment characterized by comprising
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 6.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
Such as method as claimed in any one of claims 1 to 6 is realized when row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810073340.5A CN110110267A (en) | 2018-01-25 | 2018-01-25 | Extract characteristics of objects, the method and apparatus of object search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810073340.5A CN110110267A (en) | 2018-01-25 | 2018-01-25 | Extract characteristics of objects, the method and apparatus of object search |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110267A true CN110110267A (en) | 2019-08-09 |
Family
ID=67483601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810073340.5A Pending CN110110267A (en) | 2018-01-25 | 2018-01-25 | Extract characteristics of objects, the method and apparatus of object search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110267A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487277A (en) * | 2019-09-11 | 2021-03-12 | 拉扎斯网络科技(上海)有限公司 | Data distribution method and device, readable storage medium and electronic equipment |
CN115526173A (en) * | 2022-10-12 | 2022-12-27 | 湖北大学 | Feature word extraction method and system based on computer information technology |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440242A (en) * | 2013-06-26 | 2013-12-11 | 北京亿赞普网络技术有限公司 | User search behavior-based personalized recommendation method and system |
CN104252456A (en) * | 2013-06-25 | 2014-12-31 | 阿里巴巴集团控股有限公司 | Method, device and system for weight estimation |
US20150161139A1 (en) * | 2013-12-10 | 2015-06-11 | Alibaba Group Holding Limited | Data search processing |
CN106997350A (en) * | 2016-01-22 | 2017-08-01 | 阿里巴巴集团控股有限公司 | A kind of method and device of data processing |
CN107256244A (en) * | 2017-06-01 | 2017-10-17 | 北京京东尚科信息技术有限公司 | Data processing method and system |
CN107526800A (en) * | 2017-08-20 | 2017-12-29 | 平安科技(深圳)有限公司 | Device, method and the computer-readable recording medium of information recommendation |
-
2018
- 2018-01-25 CN CN201810073340.5A patent/CN110110267A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104252456A (en) * | 2013-06-25 | 2014-12-31 | 阿里巴巴集团控股有限公司 | Method, device and system for weight estimation |
CN103440242A (en) * | 2013-06-26 | 2013-12-11 | 北京亿赞普网络技术有限公司 | User search behavior-based personalized recommendation method and system |
US20150161139A1 (en) * | 2013-12-10 | 2015-06-11 | Alibaba Group Holding Limited | Data search processing |
CN106997350A (en) * | 2016-01-22 | 2017-08-01 | 阿里巴巴集团控股有限公司 | A kind of method and device of data processing |
CN107256244A (en) * | 2017-06-01 | 2017-10-17 | 北京京东尚科信息技术有限公司 | Data processing method and system |
CN107526800A (en) * | 2017-08-20 | 2017-12-29 | 平安科技(深圳)有限公司 | Device, method and the computer-readable recording medium of information recommendation |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487277A (en) * | 2019-09-11 | 2021-03-12 | 拉扎斯网络科技(上海)有限公司 | Data distribution method and device, readable storage medium and electronic equipment |
CN112487277B (en) * | 2019-09-11 | 2023-04-07 | 拉扎斯网络科技(上海)有限公司 | Data distribution method and device, readable storage medium and electronic equipment |
CN115526173A (en) * | 2022-10-12 | 2022-12-27 | 湖北大学 | Feature word extraction method and system based on computer information technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102567511B (en) | Method and device for automatically recommending application | |
CN108228906B (en) | Method and apparatus for generating information | |
CN102360364A (en) | Automatic application recommendation method and device | |
CN106415644A (en) | Dynamic content item creation | |
CN110363604A (en) | Page generation method and device | |
CN110020143A (en) | A kind of landing page generation method and device | |
CN110276065A (en) | A kind of method and apparatus handling goods review | |
CN110020162A (en) | User identification method and device | |
CN108898496A (en) | Products Show method, apparatus, medium and electronic equipment | |
CN112528153A (en) | Content recommendation method, device, equipment, storage medium and program product | |
CN110348921A (en) | The method and apparatus that shops's article is chosen | |
CN109903105A (en) | A kind of method and apparatus for improving end article attribute | |
CN109190027A (en) | Multi-source recommended method, terminal, server, computer equipment, readable medium | |
CN110473043A (en) | A kind of item recommendation method and device based on user behavior | |
CN110110267A (en) | Extract characteristics of objects, the method and apparatus of object search | |
CN111767459A (en) | Item recommendation method and device | |
CN110232581A (en) | It is a kind of to provide the method and apparatus of discount coupon for user | |
JP5256273B2 (en) | Intention extraction apparatus, method and program | |
CN109426998A (en) | Information-pushing method and device | |
CN104881447A (en) | Searching method and device | |
CN108959294A (en) | A kind of method and apparatus accessing search engine | |
KR101990502B1 (en) | a device and a method for extracting generalized information | |
CN110827044A (en) | Method and device for extracting user interest mode | |
CN110020131A (en) | A kind of method and apparatus arranging commodity | |
CN110490682A (en) | The method and apparatus for analyzing item property |
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 |