CN106446531A - Family tree construction method based on prior decision model - Google Patents
Family tree construction method based on prior decision model Download PDFInfo
- Publication number
- CN106446531A CN106446531A CN201610810480.7A CN201610810480A CN106446531A CN 106446531 A CN106446531 A CN 106446531A CN 201610810480 A CN201610810480 A CN 201610810480A CN 106446531 A CN106446531 A CN 106446531A
- Authority
- CN
- China
- Prior art keywords
- attribute
- species
- initial
- tree
- decision point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B10/00—ICT specially adapted for evolutionary bioinformatics, e.g. phylogenetic tree construction or analysis
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a family tree construction method based on a prior decision model. The method comprises the following steps of: S1: adopting maximum parsimony to establish an initial family tree; S2: according to the initial family tree, establishing a prior decision model; S3: through the prior decision model, judging the affiliation of a new species; and S4: according to the affiliation of the new species, updating the initial family tree. Compared with the maximum parsimony, the family tree construction method is characterized in that the position accuracy of the species with a high deletion proportion in the family tree is greatly improved. By use of the family tree construction method, the species can be grafted into an initial tree, and an influence on relationships among other species is avoided.
Description
Technical field
The invention belongs to bioinformatics technique field, it is related to a kind of method building biological genealogical tree.
Background technology
At present when building genealogical tree using biological morphology data, it is most commonly used that maximum parsimony method, but biomorph
Learn data especially paleobiomorphology data and inevitably there is substantial amounts of missing data in collection, in missing data
When ratio constantly rises, maximum parsimony method occurs problems with：
1. the appearance of the missing data in species can lead to its accuracy rate of position in genealogical tree to substantially reduce.
2., due to there is missing data, the credibility of the genealogical tree constructed by maximum parsimony method also can decrease, that is, often
It is unstable that the secondary genealogical tree obtaining becomes extremely.
3. the missing values in missing data species can produce impact to the interspecies relation of species other in genealogical tree.
Content of the invention
For the problems referred to above, the invention discloses a kind of pedigree tree constructing method based on priori decision model.
A kind of pedigree tree constructing method based on priori decision model, comprises the following steps：
Step 1, sets up initial genealogical tree using maximum parsimony method；
Step 2, according to initial genealogical tree, sets up priori decision model using attribute reduction method；
Step 3, by priori decision model, judges the ownership of new species；
Step 4, according to the ownership of new species, updates initial genealogical tree.
Further, setting up initial genealogical tree using maximum parsimony method and refer to described in step 1, will be without missing data
Or the species containing a small amount of missing data are merged into a data set, maximum parsimony method is used to build initialization this data set
Genealogical tree.
Further, described in step 2 according to initial genealogical tree, priori decision model is set up using attribute reduction method
Refer to：
Step 21, the node of an optional initial genealogical tree is present node, obtains the genus of the subordinate species of this present node
Property set and tag along sort；
Step 22, by community set and the tag along sort of the subordinate species of this present node described, obtains deserving prosthomere
The subordinate species decision table of point；
Step 23, obtains conditional attribute collection from without missing data or the species containing a small amount of missing data, builds
This present node appurtenant kind attribute reduction set, obtains decision point corresponding with this present node；
Step 24, repeat step 21-23, until obtain the one-to-one decision point with all nodes of initial genealogical tree；
Step 25, the decision point according to step 24 builds priori decision model.
Further, this present node appurtenant kind attribute reduction set of the structure described in step 23 refers to：
Step 231, calculates the positive region for subordinate species attribute for the present node subordinate species categorical attribute；
Step 232, by present node subordinate species categorical attribute for the positive region of subordinate species attribute, calculates each
The importance degree of present node subordinate species attribute；
Step 233, the importance degree order from small to large according to each present node subordinate species attribute chooses each section
Point subordinate species attribute as current attribute, one of optional conditions property set conditional attribute as conditions present attribute,
If after rejecting current attribute, the classification being divided according to conditions present attribute is constant, then reject this current attribute, obtain this current
The attribute reduction set of conditional attribute collection；
Concentrate from conditional attribute and reject this conditions present attribute；
Step 234, repeat step 233, till conditional attribute integrates as empty set；
Further, described in step 3 by priori decision model, judge that the ownership of new species refers to：
Step 41, the root decision point choosing priori decision model is as current decision point；
In step 42, optionally this current decision point, a set of properties is as current attribute group, if new species and this current attribute
The attribute of group is identical, then new species belong to this current set of properties；
Otherwise, repeat step 42, till all of set of properties is all different from new species attribute in this current decision point；
Step 43, if all of set of properties is all different from new species attribute in this current decision point, chooses priori decision-making
Next layer of decision point of model root decision point, repeat step 42, till judging new species attribute.
Further, the ownership according to new species described in step 4, updates initial genealogical tree and refers to：According to new species
Attribute, obtains the decision point that this new species is belonged to, by new species grafting in its decision point corresponding to initial pedigree tree node
In, obtain the initial genealogical tree updating.
Compared with prior art, the present invention has following technique effect：
1. the present invention compares maximum parsimony method, and the higher species of disappearance ratio accuracy rate of position in genealogical tree carries significantly
High；
2. the present invention is grafted onto in initial tree using by species, it is to avoid impact to other species interspecies relations.
Brief description
Fig. 1 is the foundation figure of initial genealogical tree branch node；
Fig. 2 is that initial genealogical tree individual node sets up schematic diagram；
Fig. 3 is decision point illustraton of model；
Fig. 4 is initial genealogical tree priori decision model figure；
Fig. 5 is that initial pedigree tree node sets up branch's (grafting) schematic diagram；
Fig. 6 is to process, without disappearance, the family tree diagram obtaining；
Fig. 7 is the family tree diagram constructed by this paper；
Fig. 8 is the family tree diagram that maximum parsimony method builds；
Fig. 9 is that Palaearctic parasite species of Testudinidae missing data ratio is put down with species
All accuracy rate experimental result pictures.
Specific embodiment
Below in conjunction with drawings and Examples, the present invention is further illustrated.
A kind of pedigree tree constructing method based on priori decision model, comprises the following steps：
Step 1, sets up initial genealogical tree using maximum parsimony method；
To put forward to be merged into a data set without missing data or the species containing a small amount of missing data, with
Big parsimony principle builds the higher genealogical tree of credibility, or builds genealogical tree according to the existing priori of researcher oneself, and with
This is as initial tree.Node is set up to the place branch in initial tree, as shown in Figure 1.The end of genealogical tree is to participate in structure
Build the species of genealogical tree, at each node, suffer from being subordinated to the species set of present node, the living species at each node
Naturally it is divided into different classifications, and have obvious tag along sort.
In FIG, circle represents node, box indicating species.Set up branch node according to 4 branches of in figure respectively, mark
Number it is followed successively by N1、N2、N3、N4, each branch node suffers from being subordinated to the species of this node.In N1At node, subordinate species are
A, B, C, D, E, can be divided into two classes subordinate species by the branch of node, and A is a class, and B, C, D, E are a class.And N2Under node
Subordinate species be B, C, D, E, then subordinate species are divided into B, C and D, E two class.In N3And N4Subordinate species difference at node
For B, C and D, E.Two nodes are also divided into two classes, N3Node is B mono- class and C mono- class, N4Node is D mono- class and E mono- class.
Step 2, according to initial genealogical tree, sets up priori decision model；
Wherein, described according to initial genealogical tree, set up priori decision model and refer to：
Step 21, the node of an optional initial genealogical tree is present node, obtains the genus of the subordinate species of this present node
Property set and tag along sort；
Step 22, by community set and the tag along sort of the subordinate species of this present node described, obtains deserving prosthomere
The subordinate species decision table of point；
Step 23, obtains conditional attribute collection from without missing data or the species containing a small amount of missing data, builds
This present node appurtenant kind attribute reduction set, obtains decision point corresponding with this present node；
Step 24, repeat step 21-23, until obtain the one-to-one decision point with all nodes of initial genealogical tree；
Step 25, the decision point according to step 24 builds priori decision model.
Wherein, this present node appurtenant kind attribute reduction set of the structure described in step 23 refers to：
Step 231, calculates the positive region for subordinate species attribute for the present node subordinate species categorical attribute；
Step 232, by present node subordinate species categorical attribute for the positive region of subordinate species attribute, calculates each
The importance degree of present node subordinate species attribute；
Step 233, the importance degree order from small to large according to each present node subordinate species attribute chooses each section
Point subordinate species attribute as current attribute, one of optional conditions property set conditional attribute as conditions present attribute,
If after rejecting current attribute, the classification being divided according to conditions present attribute is constant, then reject this current attribute, obtain this current
The attribute reduction set of conditional attribute collection；
Concentrate from conditional attribute and reject this conditions present attribute；
Step 234, repeat step 233, until conditional attribute integrates as empty set；
Using the charge-coupled set of properties replaced corresponding to this present node of Attribute Reduction Set obtained above, that is, before being deserved
The corresponding decision point of node.
, what decision point to be described sets up process to the present embodiment taking one of initial genealogical tree node as a example.As Fig. 2 institute
Show, N is the node in initial genealogical tree, the subordinate species of N node are respectively present in A tree and B-tree.Can be set up currently with this
The decision point of node.
Node subordinate species attribute set and tag along sort are regarded as decision table, the knowledge representation system of decision point subordinate species
System may be defined as S=(U, R, V, f), wherein U be domain, R be decision point subordinate species attribute collection, R=C ∪ D and C ∩ D=Φ,
C is referred to as decision point subordinate species morphological properties collection, and D is referred to as decision point subordinate species tag attributes collection, f:U × R → V is one
Individual information function, it specifies the property value of each of U object X.
Define 1:In information system S, for attribute setIndiscernible relation is defined as:
Obviously IND (P) is also equivalence relation, and U/R represents the institute of R
There is equivalence class.
Define 2:(U, R, V, f), for each subset for given information system decision-making table S=And Indiscernible relation
The lower aprons collection of P, X and upper approximate set can be respectively defined as:
The present embodiment carries out yojan to whole conditional attribute collection C, and this is progressively gathered by the heuristic information using positive region
In unnecessary attribute divide out, but still meet current decision point classification it is ensured that the community set Reduct that obtains be one about
Letter, i.e. attribute decision-making group Reduct1, reject and participate in original community set setting up the attribute of set of properties, remaining condition is belonged to
Property collection proceeds attribute reduction and obtains corresponding Reducti, till conditional attribute collection can not build community set again.
Specific implementation process for the present embodiment as follows：
Input:Decision point subordinate species information system decision table
(U, R, V, f), R=C ∪ D is decision point subordinate species attribute set to S=, C={ ai, i=1,2 ..., m } claim
For conditional attribute collection, decision point subordinate species decision kind set is D={ di, i=1,2 ..., n }；
Step 1, calculates the positive region POS for subordinate species attribute C for decision point subordinate species categorical attribute Dc(D)；
Step 2, to each present node subordinate species attribute aiCalculate
Step 3, makes Reduct=C；By attribute aiBy pos order arrangement from small to large, behaviour is executed to each attribute
Make；IfThen attribute aiAnswer yojan, Reduct=Reduct- { ai}；Otherwise ai
Can not be by yojan, Reduct is constant；
Step 4, obtains attribute reduction group Reducti, the attribute participating in setting up set of properties is rejected, i.e. residue
=C-Reducti；
Step 5, gives C, i.e. C=residue residue condition property set residue；
Step 6, executes Step 1, sets up many set of properties reduct of decision pointi(i=1,2 ... n) belongs to until C condition
Till property collection cannot build set of properties；
Output:Decision point set of properties set reducti(i=1,2 ... n)；
By the structure to Fig. 2 interior joint subordinate species attribute reduction set, obtain decision-making corresponding with node
Point, finally constructs decision-making point model, as shown in figure 3, reduct1To reductnFor the set of properties set in decision point.
Corresponding decision point is set up to each node in initial genealogical tree, and then obtains the decision-making priori mould of initial genealogical tree
Type, the tree topology of model is consistent with the structure of initial tree, as shown in figure 4, the circle of in figure represents decision point, box indicating
Species.
In Fig. 1, initial genealogical tree has 4 nodes, and the decision point of correspondence establishment is the P in Fig. 41、P2、P3、P4.Decision model
The end of type structure is species, corresponding with species in Fig. 2, is A, B, C, D, E.
Step 3, by priori decision model, judges the ownership of new species；
Wherein, concretely comprise the following steps：
Step 31, the root decision point choosing priori decision model is as current decision point；
In step 32, optionally this current decision point, a set of properties is as current attribute group, if new species and this current attribute
The attribute of group is identical, then new species belong to this current set of properties；
Otherwise, repeat step 32, till all of set of properties is all different from new species attribute in this current decision point；
Step 33, if all of set of properties is all different from new species attribute in this current decision point, chooses priori decision-making
Next layer of decision point of model root decision point, repeat step 32, till judging new species attribute.
The present embodiment sets and belongs to the set of properties number of A tree as m, and the set of properties number belonging to B-tree is n.By determining to new species
The attribute of each set of properties in plan point compares, and same alike result group such as, then judge the attribute in current decision point for the new species
Group ownership, that is, belong to A tree or belong to B-tree, and ownership set of properties number is added up.If being both not belonging to A tree and being not belonging to B
Set, or the attribute belonging to missing data in new species is the attribute currently judging in set of properties in decision point, then cannot judge
The ownership of new species, is not counted in the set of properties number of any subtree ownership, i.e. m, n are not added up.Complete returning of each set of properties
Belong to after judging, finally draw the set of properties number m, n of new species subtree ownership.Then new species decision point ownership determination strategy is：
According to above-mentioned decision point determination strategy, new species start to judge ownership from the root decision point of priori decision model, recognize
Surely, after belonging to A subtree or B subtree, the root decision point for ownership subtree proceeds ownership judgement.Repeatedly execute this behaviour
Make until stopping judging.
Step 4, according to the ownership of new species, updates initial genealogical tree.
After new species stop judging, according to new species attribute, obtain the decision point that this new species is belonged to, new species are transferred
It is connected in the initial pedigree tree node corresponding to its decision point, obtain the initial genealogical tree updating.New species grafting subtree process
As shown in figure 5, stop judging ownership course in P decision point, and node N in the corresponding initial genealogical tree of P decision point for the grafting
On, become the new branch of initial genealogical tree.
In order to verify the effectiveness of this method, experiment is with without missing data or having containing a small amount of missing data
The biological morphology data set specifying pedigree, as experimental data set, carries out missing at random data processing to species therein, fortune
The method being proposed with this paper and maximum parsimony method carry out Experimental comparison.
Tested with Palaearctic parasite species of Testudinidae data set, to species
T.marocana carries out missing at random process and obtains with without the data that disappearance is processed respectively with maximum parsimony method and this method
To genealogical tree result compare.As Fig. 6, shown in 7,8.
Each species in data set are carried out missing at random process, using the method proposing in literary composition and maximum parsimony method structure
The genealogical tree built carries out accuracy rate and compares.In fig .9, abscissa represents the missing data ratio of species, from 0% to 70%.Vertical
The Average Accuracy of coordinate representation species.
Claims (6)
1. a kind of pedigree tree constructing method based on priori decision model, comprises the following steps：
Step 1, sets up initial genealogical tree using maximum parsimony method；
It is characterized in that, further comprising the steps of：
Step 2, according to initial genealogical tree, sets up priori decision model using attribute reduction method；
Step 3, by priori decision model, judges the ownership of new species；
Step 4, according to the ownership of new species, updates initial genealogical tree.
2. pedigree tree constructing method as claimed in claim 1 is it is characterised in that the employing maximum parsimony method described in step 1
Set up initial genealogical tree to refer to, a data set will be merged into without missing data or the species containing a small amount of missing data,
This data set is used maximum parsimony method build initialization genealogical tree.
3. pedigree tree constructing method as claimed in claim 1 it is characterised in that described in step 2 according to initial genealogical tree,
Set up priori decision model using attribute reduction method to refer to：
Step 21, the node of an optional initial genealogical tree is present node, obtains the property set of the subordinate species of this present node
Close and tag along sort；
Step 22, by community set and the tag along sort of the subordinate species of this present node described, obtains this present node
Subordinate species decision table；
Step 23, obtains conditional attribute collection from without missing data or the species containing a small amount of missing data, builds and deserve
Front nodal point subordinate species attribute reduction set, obtains decision point corresponding with this present node；
Step 24, repeat step 21-23, until obtain the one-to-one decision point with all nodes of initial genealogical tree；
Step 25, the decision point according to step 24 builds priori decision model.
4. pedigree tree constructing method as claimed in claim 3 is it is characterised in that this present node of the structure described in step 23
Subordinate species attribute reduction set refers to：
Step 231, calculates the positive region for subordinate species attribute for the present node subordinate species categorical attribute；
Step 232, by present node subordinate species categorical attribute for the positive region of subordinate species attribute, calculates each current
The importance degree of node subordinate species attribute；
Step 233, the importance degree order from small to large according to each present node subordinate species attribute choose each node from
The attribute of species as current attribute, one of optional conditions property set conditional attribute as conditions present attribute, if picking
After current attribute, the classification being divided according to conditions present attribute is constant, then reject this current attribute, obtain this conditions present
The attribute reduction set of property set；
Concentrate from conditional attribute and reject this conditions present attribute；
Step 234, repeat step 233, till conditional attribute integrates as empty set.
5. pedigree tree constructing method as claimed in claim 3 it is characterised in that described in step 3 by priori decision model
Type, judges that the ownership of new species refers to：
Step 41, the root decision point choosing priori decision model is as current decision point；
In step 42, optionally this current decision point, a set of properties is as current attribute group, if new species and this current set of properties
Attribute is identical, then new species belong to this current set of properties；
Otherwise, repeat step 42, till all of set of properties is all different from new species attribute in this current decision point；
Step 43, if all of set of properties is all different from new species attribute in this current decision point, chooses priori decision model
Next layer of decision point of root decision point, repeat step 42, till judging new species attribute.
6. pedigree tree constructing method as claimed in claim 1 is it is characterised in that the returning according to new species described in step 4
Belong to, update initial genealogical tree and refer to：According to new species attribute, obtain the decision point that this new species is belonged to, by new species grafting
In initial pedigree tree node corresponding in its decision point, obtain the initial genealogical tree updating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610810480.7A CN106446531B (en) | 2016-09-08 | 2016-09-08 | A kind of pedigree tree constructing method based on priori decision model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610810480.7A CN106446531B (en) | 2016-09-08 | 2016-09-08 | A kind of pedigree tree constructing method based on priori decision model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106446531A true CN106446531A (en) | 2017-02-22 |
| CN106446531B CN106446531B (en) | 2019-03-22 |
Family
ID=58165275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610810480.7A Active CN106446531B (en) | 2016-09-08 | 2016-09-08 | A kind of pedigree tree constructing method based on priori decision model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446531B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108509764A (en) * | 2018-02-27 | 2018-09-07 | 西北大学 | A kind of extinct plants and animal pedigree evolution analysis method based on genetic property yojan |
| CN109326328A (en) * | 2018-11-02 | 2019-02-12 | 西北大学 | A kind of extinct plants and animal pedigree evolution analysis method based on pedigree cluster |
| CN112817959A (en) * | 2021-02-25 | 2021-05-18 | 西北大学 | Construction method of ancient biomorphic phylogenetic tree based on multi-metric index weight |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101082925A (en) * | 2007-07-09 | 2007-12-05 | 山西大学 | Rough set property reduction method based on SQL language |
| CN103093118A (en) * | 2013-02-07 | 2013-05-08 | 中国科学院计算机网络信息中心 | Rebuilding method of phylogenetic tree |
-
2016
- 2016-09-08 CN CN201610810480.7A patent/CN106446531B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101082925A (en) * | 2007-07-09 | 2007-12-05 | 山西大学 | Rough set property reduction method based on SQL language |
| CN103093118A (en) * | 2013-02-07 | 2013-05-08 | 中国科学院计算机网络信息中心 | Rebuilding method of phylogenetic tree |
Non-Patent Citations (4)
| Title |
|---|
| ALEXANDRA GAVRYUSHKINA ET AL.: "Recursive algorithms for phylogenetic tree counting", 《 ALGORITHMS FOR MOLECULAR BIOLOGY》 * |
| JOHN J. WIENS: "Missing data and the design of phylogenetic analyses", 《JOURNAL OF BIOMEDICAL INFORMATICS》 * |
| 张腾飞 等: "粗糙集理论中属性相对约简算法", 《电子学报》 * |
| 郑巍 等: "系统发育分析中的最大简约法及其优化", 《昆虫学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108509764A (en) * | 2018-02-27 | 2018-09-07 | 西北大学 | A kind of extinct plants and animal pedigree evolution analysis method based on genetic property yojan |
| CN108509764B (en) * | 2018-02-27 | 2020-06-16 | 西北大学 | Ancient organism pedigree evolution analysis method based on genetic attribute reduction |
| CN109326328A (en) * | 2018-11-02 | 2019-02-12 | 西北大学 | A kind of extinct plants and animal pedigree evolution analysis method based on pedigree cluster |
| CN112817959A (en) * | 2021-02-25 | 2021-05-18 | 西北大学 | Construction method of ancient biomorphic phylogenetic tree based on multi-metric index weight |
| CN112817959B (en) * | 2021-02-25 | 2023-03-24 | 西北大学 | Construction method of ancient biomorphic phylogenetic tree based on multi-metric index weight |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106446531B (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104717124B (en) | A kind of friend recommendation method, apparatus and server | |
| CN103812872B (en) | A kind of network navy behavioral value method and system based on mixing Di Li Cray process | |
| CN103927398B (en) | The microblogging excavated based on maximum frequent itemsets propagandizes colony's discovery method | |
| CN101980210A (en) | Marked word classifying and grading method and system | |
| CN101937436B (en) | Text classification method and device | |
| CN106446531A (en) | Family tree construction method based on prior decision model | |
| CN105046287B (en) | A kind of online more strokes repeat the cluster and approximating method of skeletonizing | |
| CN108764242A (en) | Off-line Chinese Character discrimination body recognition methods based on deep layer convolutional neural networks | |
| CN102289522A (en) | Method of intelligently classifying texts | |
| CN106791221B (en) | A kind of kith and kin's circle relation recognition method based on call | |
| CN110377659A (en) | A kind of intelligence chart recommender system and method | |
| CN109598307A (en) | Data screening method, apparatus, server and storage medium | |
| CN110532399A (en) | Knowledge mapping update method, system and the device of object game question answering system | |
| CN104008177B (en) | Rule base structure optimization and generation method and system towards linguistic indexing of pictures | |
| CN107944487B (en) | Crop breeding variety recommendation method based on mixed collaborative filtering algorithm | |
| CN104598648A (en) | Interactive gender identification method and device for microblog user | |
| CN104573701B (en) | A kind of automatic testing method of Tassel of Corn | |
| Nathan et al. | The nature of species in evolution | |
| CN109299473B (en) | Developer portrait-based software engineering task recommendation method | |
| CN107301426A (en) | A kind of multi-tag clustering method of shoe sole print image | |
| KR101655948B1 (en) | Relationship Circle Processing Method and System, and Computer Storage Medium | |
| CN112785156B (en) | Industrial collar and sleeve identification method based on clustering and comprehensive evaluation | |
| CN105337842B (en) | A kind of rubbish mail filtering method unrelated with content | |
| CN109472307A (en) | A kind of method and apparatus of training image disaggregated model | |
| CN1614607A (en) | Filtering method and system for e-mail refuse |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191018 Address after: 710065 room 20305, 3 / F, unit 2, building 2, leading Times Plaza (block B), No. 86, Gaoxin Road, hi tech Zone, Xi'an City, Shaanxi Province Patentee after: Shaanxi nugget Data Technology Co. Ltd. Address before: 710069 Shaanxi city of Xi'an province Taibai Road No. 229 Patentee before: Northwest University |