CN109327484A - Acquisition methods, device, server and the storage medium of characteristic value collection - Google Patents
Acquisition methods, device, server and the storage medium of characteristic value collection Download PDFInfo
- Publication number
- CN109327484A CN109327484A CN201710639827.0A CN201710639827A CN109327484A CN 109327484 A CN109327484 A CN 109327484A CN 201710639827 A CN201710639827 A CN 201710639827A CN 109327484 A CN109327484 A CN 109327484A
- Authority
- CN
- China
- Prior art keywords
- value set
- node
- feature vector
- characteristic value
- input feature
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/34—Network arrangements or protocols for supporting network services or applications involving the movement of software or configuration parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a kind of acquisition methods of characteristic value collection, receives the acquisition request for being directed to target signature value set；It is prestored in node from multiple, searches destination node corresponding with the target signature value set；According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, the output characteristic value set of the destination node is obtained；Wherein, the input feature vector value set of the destination node is determined by the information in the acquisition request, or relies on the output characteristic value set acquisition of other nodes.Node in the embodiment of the present application can provide characteristic value collection for multiple parties in request, the identical node that different demands side needs only needs to develop once, each node directly can provide service for party in request, when needed, server-side calls corresponding node, it can also be called when needed for other nodes, to realize that node is multiplexed, reduce development cost.
Description
Technical field
This application involves the acquisition methods of Internet technical field more particularly to characteristic value collection, device, server and deposit
Storage media.
Background technique
For certain service providers, since different demands for services may be faced, it is thus possible to can be by difference
Team develop different service systems.Service system is realized based on machine learning model, needs to select when constructing machine learning model
One or more suitable features and constitutive characteristic set are taken, for characteristic set, it is also necessary to develop corresponding characteristic value collection
Acquisition rule.After model is online, model can be directed to specific demand, execute the acquisition rule of characteristic value collection, obtain
Corresponding characteristic value collection is obtained, and then operation is carried out according to characteristic value collection, obtains output result.
Different service systems are developed by different team in the related technology, each team needs to develop corresponding characteristic value collection
The acquisition rule of conjunction.The case where some different service systems of physical presence need certain same characteristic features, and different exploitation groups
Team respectively develops the acquisition rule of characteristic value, so as to cause the excess waste of development cost.
Summary of the invention
To overcome the problems in correlation technique, this application provides the acquisition methods of characteristic value collection, device, services
Device and storage medium.
A kind of acquisition methods of characteristic value collection, which comprises
Receive the acquisition request for being directed to target signature value set；
It is prestored in node from multiple, searches destination node corresponding with the target signature value set；It is described to prestore node
For providing the processing rule for utilizing input feature vector value set to obtain output characteristic value set and the node and other nodes
Dependence；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
In information determine, or rely on other nodes output characteristic value set obtain.
Optionally, the multiple to prestore in node, the corresponding information of each node includes: to be obtained using input feature vector value set
Whether the input feature vector value set of the processing rule and the node that obtain output characteristic value set needs to rely on other described nodes
Output characteristic value set obtain.
Optionally, according to the input feature vector value set of the destination node, the corresponding processing rule of the destination node are executed
Then, the output characteristic value set of the destination node is obtained, comprising:
Call the destination node, comprising:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, if the input feature vector value set of the destination node needs not rely on it
His node, the input feature vector value set of the destination node are determined by the information in the acquisition request；If the destination node
Input feature vector value set need to rely on other nodes, will acquire request and be supplied to and be relied on node, section is relied on described in calling
After point, the input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, execute the invocation target
The step of node.
Optionally, the multiple node that prestores is recorded using digraph, and the arc in the digraph indicates the section
Dependence between point.
Optionally, the processing rule that output characteristic value set is obtained using input feature vector value set, including it is such as next
Kind is a variety of:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；
By access preset data source address, output spy is obtained using input feature vector value set from the preset data source
Value indicative set；
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Screening is carried out to output data using parameter preset and obtains output characteristic value set；
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Operation is carried out to output data in the way of default operation and obtains output characteristic value set.
Optionally, the destination node there are it is multiple it is described be relied on node in the case where, it is described call it is described by according to
Rely node, comprising:
Node is relied on described in concurrent invocation.
Optionally, node is relied on described in the concurrent invocation, comprising:
It opens simultaneously and is relied on node described in multiple thread dispatchings.
Optionally, the multiple node that prestores is stored in a configuration file, by the configuration file to the node
It is grouped, increases, operation is deleted or modified.
A kind of acquisition device of characteristic value collection, described device include:
Request receiving module is used for: receiving the acquisition request for being directed to target signature value set；
Searching module is used for: being prestored in node from multiple, is searched target section corresponding with the target signature value set
Point；The node that prestores is for providing the processing for utilizing input feature vector value set to obtain output characteristic value set rule and the section
The dependence of point and other nodes；
Execution module is used for: according to the input feature vector value set of the destination node, it is corresponding to execute the destination node
Processing rule, obtains the output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node by
Information in the acquisition request determines, or relies on the output characteristic value set acquisition of other nodes.
Optionally, the multiple to prestore in node, the corresponding information of each node includes: to be obtained using input feature vector value set
Whether the input feature vector value set of the processing rule and the node that obtain output characteristic value set needs to rely on other described nodes
Output characteristic value set obtain.
Optionally, the execution module, is specifically used for:
Call the destination node:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, if the input feature vector value set of the destination node needs not rely on it
His node, the input feature vector value set of the destination node are determined by the information in the acquisition request；If the destination node
Input feature vector value set need to rely on other nodes, will acquire request and be supplied to and be relied on node, section is relied on described in calling
After point, the input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, re-execute the calling
The treatment process of invocation target node in module.
Optionally, the multiple node that prestores is recorded using digraph, and the arc in the digraph indicates the section
Dependence between point.
Optionally, the processing rule that output characteristic value set is obtained using input feature vector value set, including it is such as next
Kind is a variety of:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；
By access preset data source address, output spy is obtained using input feature vector value set from the preset data source
Value indicative set；
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Screening is carried out to output data using parameter preset and obtains output characteristic value set；
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Operation is carried out to output data in the way of default operation and obtains output characteristic value set.
Optionally, the execution module, is also used to: in the destination node, there are multiple described the case where being relied on node
Under, node is relied on described in concurrent invocation.
Optionally, the execution module, is also used to:
It opens simultaneously and is relied on node described in multiple thread dispatchings.
Optionally, the multiple node that prestores is stored in a configuration file, by the configuration file to the node
It is grouped, increases, operation is deleted or modified.
A kind of server, the server include: processor；Memory for storage processor executable instruction；Wherein,
The processor is configured to:
Receive the acquisition request for being directed to target signature value set；
It is prestored in node from multiple, searches destination node corresponding with the target signature value set；It is described to prestore node
For providing the processing rule for utilizing input feature vector value set to obtain output characteristic value set and the node and other nodes
Dependence；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
In information determine, or rely on other nodes output characteristic value set obtain.
A kind of computer storage medium, program instruction is stored in the storage medium, and described program instruction includes:
Receive the acquisition request for being directed to target signature value set；
It is prestored in node from multiple, searches destination node corresponding with the target signature value set；It is described to prestore node
For providing the processing rule for utilizing input feature vector value set to obtain output characteristic value set and the node and other nodes
Dependence；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
In information determine, or rely on other nodes output characteristic value set obtain.
The technical solution that embodiments herein provides can include the following benefits:
Multiple nodes can be constructed in the application in advance, node can be mentioned towards different parties in request for multiple parties in request
For characteristic value collection, the identical node that different demands side needs only needs to develop once, and each node can be needed directly
Corresponding node is called in the side's of asking offer service, when needed, server-side, can also be called when needed for other nodes,
To realize that node is multiplexed, development cost is reduced.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the application
Example, and together with specification it is used to explain the principle of the application.
Fig. 1 is a kind of node schematic diagram in the acquisition scheme of characteristic value collection provided herein.
Fig. 2 is another node schematic diagram in the acquisition scheme of characteristic value collection provided herein.
Fig. 3 A is a kind of the application flow chart of the acquisition methods of characteristic value collection shown according to an exemplary embodiment.
Fig. 3 B is the application one shown according to an exemplary embodiment comprising there are two the signals of the digraph of node
Figure.
Fig. 3 C is the signal of the application one shown according to an exemplary embodiment digraph for including seven nodes
Figure.
Fig. 4 is a kind of the application block diagram of the acquisition device of characteristic value collection shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
Often refer to obtain the demand of characteristic value collection in many application scenarios.For example, in data analysis field, it may
The characteristic value for needing the extraction section feature from a large number of users data carries out various analyses using the characteristic value extracted；
In machine learning techniques field, after the online application of model, when needed, model can extract characteristic value collection to input data
It closes, and carries out operation using characteristic value collection, obtain operation result etc..
For certain service providers, since different demands for services may be faced, it is thus possible to can be by difference
Team develop different service systems.Service system is realized based on machine learning model, needs to select when constructing machine learning model
One or more suitable features and constitutive characteristic set are taken, for characteristic set, it is also necessary to develop corresponding characteristic value collection
Acquisition rule.After model is online, model can be directed to specific demand, execute the acquisition rule of characteristic value collection, obtain
Corresponding characteristic value collection is obtained, and then operation is carried out according to characteristic value collection, obtains output result.
Different service systems are developed by different team in the related technology, each team needs to develop corresponding characteristic value collection
The acquisition rule of conjunction.The case where some different service systems of physical presence need certain same characteristic features, and different exploitation groups
Team respectively develops the acquisition rule of characteristic value, so as to cause the excess waste of development cost.
The acquisition scheme of characteristic value collection provided by the embodiment of the present application receives the acquisition for being directed to target signature value set
Request；It is prestored in node from multiple, searches destination node corresponding with the target signature value set；According to the destination node
Input feature vector value set, execute the destination node corresponding processing rule, obtain the output characteristic value of the destination node
Set；Wherein, the input feature vector value set of the destination node is determined by the information in the acquisition request, or relies on it
The output characteristic value set of his node obtains.Node in the embodiment of the present application can provide characteristic value collection for multiple parties in request
It closes, the identical node that different demands side needs only needs to develop once, and each node directly can provide clothes for party in request
Corresponding node is called in business, when needed, server-side, can also be called when needed for other nodes, to realize section
Point multiplexing, reduces development cost.
Fig. 1 show a kind of node schematic diagram in the acquisition scheme of characteristic value collection provided herein, wherein
Node1, Node2 and Node4 are node, respectively correspond a kind of characteristic value collection, the line table with the arrow between Fig. 1 interior joint
Show the dependence between node, arrow is directed toward Node4 between Node1 and Node4, indicates the input feature vector value set of Node4
The output characteristic value set for needing to rely on Node1 obtains, and similarly, the arrow between Node2 and Node4 is directed toward Node4, indicates
The output characteristic value set that the input feature vector value set of Node4 also needs to rely on Node2 obtains.Between Node1 and Node2 mutually
It is independent.
It can be seen that by the schematic diagram between above-mentioned node, it is assumed that a party in request initiates obtaining for a characteristic value collection
Request is taken, according to the acquisition request, inquiring corresponding node is Node4, and the corresponding nodal information of Node4 includes: using defeated
Enter characteristic value collection and obtains the processing rule of output characteristic value set and the input feature vector value set needs of node Node4
The output characteristic value set for relying on node Node1 and Node2 obtains.
Therefore, it calls Node4, Node4 that can will acquire request and is supplied to Node1 and Node2, wait Node1 and Node2
Its output characteristic value set is provided respectively.
According to the corresponding nodal information of Node1 and Node2, determine the input feature vector value set of Node1 do not need according to
Rely other nodes, the input feature vector value set of Node2 also needs not rely on other nodes.Node1 and Node2 is called respectively,
After Node1 determines input feature vector value set according to the information in acquisition request, its corresponding processing rule is executed, Node1 is obtained
Output characteristic value set.After Node2 determines input feature vector value set according to the information in acquisition request, its corresponding place is executed
Reason rule, obtains the output characteristic value set of Node2.
Node4 according to the call result of Node1 and Node2, obtain Node1 output characteristic value set and Node2 it is defeated
The input feature vector value set of characteristic value collection and determining Node4 out executes the corresponding processing rule of Node4, obtains the defeated of Node4
Characteristic value collection out.
Fig. 2 show another node schematic diagram of the acquisition scheme of characteristic value collection provided herein, wherein
Node1, Node2, Node4 and Node8 are node, respectively correspond a kind of characteristic value collection, with the arrow between Fig. 2 interior joint
Line indicates the dependence between node, and arrow is directed toward Node4 between Node1 and Node4, indicates the input feature vector of Node4
The output characteristic value set that value set needs to rely on Node1 obtains, and similarly, the arrow between Node2 and Node4 is directed toward Node4,
Indicate that the input feature vector value set of Node4 also needs to rely on the output characteristic value set acquisition of Node2.Between Node4 and Node8
Arrow is directed toward Node8, indicates that the input feature vector value set of Node8 needs to rely on the output characteristic value set acquisition of Node4.
It can be seen that by the schematic diagram between above-mentioned node, it is assumed that a party in request initiates obtaining for a characteristic value collection
Request is taken, according to the acquisition request, inquiring corresponding node is Node8, and the corresponding nodal information of Node8 includes: using defeated
Enter characteristic value collection and obtains the processing rule of output characteristic value set and the input feature vector value set needs of node Node8
The output characteristic value set for relying on node Node4 obtains.
Therefore, it calls Node8, Node8 that can will acquire after request is supplied to Node4, waits Node4 to provide its output special
Value indicative set.
It calls Node4, Node4 that can will acquire request and is supplied to Node1 and Node2, wait Node1 and Node2 difference
Its output characteristic value set is provided.
According to the corresponding nodal information of Node1 and Node2, determine the input feature vector value set of Node1 do not need according to
Rely other nodes, the input feature vector value set of Node2 also needs not rely on other nodes.After calling Node1 and Node2 respectively,
Obtain the output characteristic value set of Node1 and the output characteristic value set of Node2.
Node4 according to the call result of Node1 and Node2, obtain Node1 output characteristic value set and Node2 it is defeated
The input feature vector value set of characteristic value collection and determining Node4 out executes the corresponding processing rule of Node4, obtains the defeated of Node4
Characteristic value collection out.
Node8 merges the input feature vector value set for determining Node8 according to the output characteristic value collection of Node4, executes Node8 pairs
The processing rule answered, obtains the output characteristic value set of Node8.
Comprehensive earlier figures 1 and embodiment illustrated in fig. 2, the acquisition scheme of the characteristic value collection as shown in Fig. 3 A can be summarized
Are as follows:
In step 302, the acquisition request for being directed to target signature value set is received；
In step 304, it is prestored in node from multiple, searches destination node corresponding with the target signature value set；
The node that prestores is for providing the processing for utilizing input feature vector value set to obtain output characteristic value set rule and the node
With the dependence of other nodes；
Within step 306, according to the input feature vector value set of the destination node, the corresponding place of the destination node is executed
Reason rule, obtains the output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by institute
The information stated in acquisition request determines, or relies on the output characteristic value set acquisition of other nodes.
The scheme of the embodiment of the present application, can be applied to server-side, provide it for the party in request with characteristic value collection demand
Required characteristic value collection.In some examples, application scenarios can be machine learning field, and server-side specifically includes feature work
Journey server-side, this feature Engineering Service end can provide characteristic value collection towards multiple machine learning models, and each operation has machine
The acquisition request for characteristic value collection that the equipment of learning model can be initiated to Feature Engineering server-side, is taken by Feature Engineering
Business end runs the scheme of the present embodiment, provides the characteristic value collection of needs for machine learning model.In other examples, application
Scene can be the network architecture of client and server-side, and party in request can be client, and certain functional modules of client exist
When needing certain characteristic value collections, the acquisition request of characteristic value collection can be initiated from client to server-side.In other examples
In, application scenarios can also be that data analyze scene, and data analyst may be needed to extract characteristic value collection to data, be calculated
Equipment can apply the provided scheme of the present embodiment, and calling interdependent node extracts the characteristic value collection of data to be analyzed and defeated
Out.In practical application, the scheme of the present embodiment can be flexibly applied to a variety of different scenes, the present embodiment does not limit this
System.
Node is prestored for multiple, the demand of characteristic value collection, these characteristic value collection can be collected in practical application in advance
The demand of conjunction can be provided by party in request, such as the developer or the developer of client etc. of machine learning model above-mentioned
Deng.For the demand of collected characteristic value collection, the acquisition side of one or more features involved in different demands is determined
Formula.The multiple to prestore in node in the present embodiment for the ease of management node, the corresponding information of each node includes: to utilize
Input feature vector value set obtains the processing rule of output characteristic value set and whether the input feature vector value set of the node needs
The output characteristic value set for relying on other nodes obtains.These nodal informations can also be stored in a configuration file, be led to
The configuration file is crossed to be grouped the node, increase, operation is deleted or modified.By the above-mentioned means, art technology
Personnel can be convenient multiple nodes that prestore and be managed, neatly node is grouped when needed, modify node,
Increase new node or the old node of deletion etc. operation.
In practical application, the acquisition modes of feature can in conjunction with concrete scene flexible configuration.For example, an acquisition user
The demand of the ambient conditions of present position, required output characteristic value set includes: that temperature characteristic value, wind-force are special under the demand
Value indicative, critical precipitation value and contamination characteristics value, these characteristic values, it is thus necessary to determine that behind user present position, from weather information service
It is obtained at end, it is thus determined that input feature vector value set includes geographic location feature value, acquisition modes are to access weather information service
The interface provided is provided, by input feature vector value set (including geographic location feature value), this area that is returned according to the interface
Weather related information obtains temperature characteristic value, wind feature value, critical precipitation value and contamination characteristics value.
Based on above-mentioned analysis, the ambient conditions demand that can just provide according to demand constructs a related ambient conditions
The information of node, the node obtains output characteristic value set including the use of input feature vector value set (including geographic location feature value)
(access weather information service end mentions the processing rule of (temperature characteristic value, wind feature value, critical precipitation value and contamination characteristics value)
The interface of confession), the input feature vector value set of the node needs not rely on other nodes.
In practical application, nodal information be can recorde in configuration file, show one related " weather " as follows
Nodal information:
Wherein, the title (name) of the node is weather (indicating weather)；
Handling class (clazz) is com.node.Weather；
Output characteristic value set (output) includes: temperature (indicating temperature), and type (type) is float；
Wind (indicates wind-force), and type (type) is float；
Input feature vector value set (input) includes: lat (indicating latitude), is determined by the latitude information in acquisition request
(request.lat)；Lng (indicates longitude), determines (request.lng) by the longitude information in acquisition request；
Parameter (param) includes: data source information (source), which is xxnet.
In other examples, it is possible to which party in request provides many demands, and may have feature required for multiple demands
It needs to acquire using identical input feature vector, in such cases, dependence can be established between node, to will relate to
And the node of the same characteristic features is supplied to multiple parties in request and calls.
As an example it is assumed that the demand for the characteristic value collection collected includes:
1. obtaining online driver's quantity on some 3000 meters of passenger present position periphery
2. obtaining all passengers quantities for needing to distribute order on some 3000 meters of passenger present position periphery
3. obtaining driver's quantity on some 3000 meters of passenger present position periphery and the ratio of passengers quantity
Wherein, 1. demand all includes requested user's geographic location feature value, demand with the input feature vector collection of demand 2.
3. input feature vector value set be the demand 1. output characteristic value set with demand 2..
Based on this, it can establish three nodes, 1., 2. and 3. three nodes respectively correspond the demand, wherein node is 1.
1., which includes: to obtain output spy using input feature vector value set (the geographic location feature value of user) to corresponding demand
Processing rule (driver's data at access net about vehicle online service end of value indicative set (online driver's quantity on 3000 meters of periphery)
Maintenance module), the input feature vector value set of the node needs not rely on other nodes.
2. 2. node corresponds to demand, which includes: to utilize the input feature vector value set (geographic location feature of user
Value) obtain output characteristic value set (all passengers quantities for needing to distribute order on 3000 meters of present position periphery) processing rule
Then (the passenger data maintenance module at access net about vehicle online service end), the input feature vector value set of the node needs not rely on it
His node.
3. 3. node corresponds to demand, which includes: to utilize input feature vector value set (passenger present position periphery
3000 meters of online driver's quantity, 3000 meters of passenger present position periphery all passengers quantities for needing to distribute order) obtain
Obtain the processing rule of output characteristic value set (driver's quantity on 3000 meters of passenger present position periphery and the ratio of passengers quantity)
1. and 2. (by driver's quantity divided by passengers quantity), the input feature vector value set of the node need to rely on node, 3. node exists
Two are relied on node.
It is appreciated that obtaining output characteristic value set using input feature vector value set involved in above-mentioned two example
Processing rule only illustrates, and in practical application, can according to need flexible configuration processing rule.For example, in processing rule
May include following one or more:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；Wherein, the fortune
Calculation mode indicates to obtain the calculating process of output characteristic value set, such as special how using the progress operation of input feature vector value set
Levy conversion, feature branch mailbox, feature normalization or feature union operation etc..
By access preset data source address, output spy is obtained using input feature vector value set from the preset data source
Value indicative set；Data source information indicates which position to obtain output characteristic value set from, may include the interface of required access
Address data memory etc. in address, the IP address of server-side, file storage address or database.
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Screening is carried out to output data using parameter preset and obtains output characteristic value set；Wherein, which may include holding
Required various parameters when row processing rule, for example, aforementioned nodes 1. in 3000 meters of periphery etc..
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Operation is carried out to output data in the way of default operation and obtains output characteristic value set.
By above-mentioned example as it can be seen that based on party in request to the needs of characteristic value collection, server-side can construct multiple nodes, section
Point can provide characteristic value collection, the identical node that different demands side needs towards different parties in request for multiple parties in request
It only needs to develop once, each node directly can provide service for party in request, and when needed, server-side calls corresponding section
Point can also be called when needed for other nodes, to realize that node is multiplexed, reduce development cost.Wherein, if node
1. and 2. be relied on node there are multiple, such as 3. above-mentioned node exists and is relied on node, call node 3. after, node 3. defeated
Enter characteristic value collection need to rely on call node 1. and 2. after output as a result, at this point it is possible to concurrent invocation is each to be relied on section
Point, for example, can open simultaneously in the preferable situation of process performance for calculating equipment and be relied on section described in multiple thread dispatchings
Point meets requirement of the more multi-thread upper mold type to real-time so as to improve the acquisition efficiency of characteristic value collection.
There is Such analysis it is found that corresponding to the destination node of acquisition request, it may be necessary to rely on other nodes, it is also possible to no
Need to rely on other nodes, the present embodiment also provides a kind of processing side of output characteristic value set for being quickly obtained destination node
Formula optionally according to the input feature vector value set of the destination node, executes the corresponding processing rule of the destination node, obtains
Obtain the output characteristic value set of the destination node, comprising:
Call the destination node, comprising:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, if the input feature vector value set of the destination node needs not rely on it
His node, the input feature vector value set of the destination node are determined by the information in the acquisition request；If the destination node
Input feature vector value set need to rely on other nodes, will acquire request and be supplied to and be relied on node, section is relied on described in calling
After point, the input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, execute the invocation target
The step of node.
It is illustrated in conjunction with oriented graph data structure.For the ease of recording nodal information, quickly search between nodal information
Dependence, in the present embodiment, it is the multiple prestore node and can use digraph stored, the arc in the digraph
Indicate the dependence between the node.
It is made of in digraph the side between multiple nodes and each node there are direction, which is also referred to as
For arc.As shown in Figure 3B, be one comprising there are two the schematic diagram of the digraph of node, node V to node W there are an arc,
Node W is directed toward from node V in the direction of the arc, indicates that node V is adjacent to node W, and it is the adjoining of V from node V, W that node W is adjacent
Point.Therefore, it can use the arc in digraph and record dependence between the present embodiment interior joint, be based on this, nodal information
It is recorded using the data structure of digraph, and the storage organization of digraph can use adjacency matrix, neighbour in the related technology
Table, orthogonal list or adjacency multilist etc. are connect, it can be clever according to the consideration such as space performance or time performance in practical application
Selection living.
It as shown in Figure 3 C, is the schematic diagram of a digraph for including 7 nodes.If receiving for a certain characteristic value
The acquisition request of set, finding corresponding node according to the request is Node7, calls Node7, can by the digraph in Fig. 3 C
To learn, the input feature vector value set of Node7 needs to rely on the output characteristic value set of Node2, Node4, Node5 and Node6,
Concurrent invocation Node2, Node4, Node5 and Node6；Learnt by digraph, Node2 is not relied on node, Node2 according to
The input feature vector value set needed for it is requested, corresponding processing rule is executed, obtains the output characteristic value set of Node2.
Node4 is called, for Node4 there are two node Node1 and Node2 is relied on, Node1 is called process again,
Obtain the output characteristic value set of Node1.Node4 is according to the output characteristic value set of Node1 and the output characteristic value of Node2
Set, determines the input feature vector value set of Node4.Wherein, the process of the determination input feature vector value set of the present embodiment, can be
One or more output characteristic values in the output characteristic value set of Node1 are chosen, are chosen in the output characteristic value set of Node2
One or more output characteristic values, constitute the input feature vector value set of the Node4, it is regular that Node4 executes corresponding processing, obtains
Obtain the output characteristic value set of Node4.
Node5, Node5 is called to have one to be relied on node Node3, Node3 is called process again, obtains
The output characteristic value set of Node3.Later, the input feature vector value collection of Node5 is determined according to the output characteristic value set of Node3
It closes, Node5 executes corresponding processing rule, obtains the output characteristic value set of Node5.
Similarly, Node6 is called, the output characteristic value set of Node6 is obtained.
Node7 determines the input feature vector of Node7 according to the output characteristic value set of Node2, Node4, Node5 and Node6
Value set executes corresponding processing rule, obtains the output characteristic value set of Node7.
Corresponding with the embodiment of the acquisition methods of preceding feature value set, present invention also provides obtaining for characteristic value collection
Take the embodiment of device and its applied server-side.
As shown in figure 4, Fig. 4 is a kind of the application acquisition device of characteristic value collection shown according to an exemplary embodiment
Block diagram, described device includes:
Request receiving module 41, is used for: receiving the acquisition request for being directed to target signature value set.
Searching module 42, is used for: prestoring in node from multiple, searches target section corresponding with the target signature value set
Point；The node that prestores is for providing the processing for utilizing input feature vector value set to obtain output characteristic value set rule and the section
The dependence of point and other nodes.
Execution module 43, is used for: according to the input feature vector value set of the destination node, it is corresponding to execute the destination node
Processing rule, obtain the output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node
It is determined by the information in the acquisition request, or relies on the output characteristic value set acquisition of other nodes.
Node is prestored for multiple, the demand of characteristic value collection, these characteristic value collection can be collected in practical application in advance
The demand of conjunction can be provided by party in request, such as the developer or the developer of client etc. of machine learning model above-mentioned
Deng.For the demand of collected characteristic value collection, the acquisition side of one or more features involved in different demands is determined
Formula.The multiple to prestore in node in the present embodiment for the ease of management node, the corresponding information of each node includes: to utilize
Input feature vector value set obtains the processing rule of output characteristic value set and whether the input feature vector value set of the node needs
The output characteristic value set for relying on other nodes obtains.These nodal informations can also be stored in a configuration file, be led to
The configuration file is crossed to be grouped the node, increase, operation is deleted or modified.By the above-mentioned means, art technology
Personnel can be convenient multiple nodes that prestore and be managed, neatly node is grouped when needed, modify node,
Increase new node or the old node of deletion etc. operation.
In practical application, the acquisition modes of feature can in conjunction with concrete scene flexible configuration.For example, an acquisition user
The demand of the ambient conditions of present position, required output characteristic value set includes: that temperature characteristic value, wind-force are special under the demand
Value indicative, critical precipitation value and contamination characteristics value, these characteristic values, it is thus necessary to determine that behind user present position, from weather information service
It is obtained at end, it is thus determined that input feature vector value set includes geographic location feature value, acquisition modes are to access weather information service
The interface provided is provided, by input feature vector value set (including geographic location feature value), this area that is returned according to the interface
Weather related information obtains temperature characteristic value, wind feature value, critical precipitation value and contamination characteristics value.
Based on above-mentioned analysis, the ambient conditions demand that can just provide according to demand constructs a related ambient conditions
The information of node, the node obtains output characteristic value set including the use of input feature vector value set (including geographic location feature value)
(access weather information service end mentions the processing rule of (temperature characteristic value, wind feature value, critical precipitation value and contamination characteristics value)
The interface of confession), the input feature vector value set of the node needs not rely on other nodes.
In other examples, it is possible to which party in request provides many demands, and may have feature required for multiple demands
It needs to acquire using identical input feature vector, in such cases, dependence can be established between node, to will relate to
And the node of the same characteristic features is supplied to multiple parties in request and calls.
As an example it is assumed that the demand for the characteristic value collection collected includes:
1. obtaining online driver's quantity on some 3000 meters of passenger present position periphery
2. obtaining all passengers quantities for needing to distribute order on some 3000 meters of passenger present position periphery
3. obtaining driver's quantity on some 3000 meters of passenger present position periphery and the ratio of passengers quantity
Wherein, 1. demand all includes requested user's geographic location feature value, demand with the input feature vector collection of demand 2.
3. input feature vector value set be the demand 1. output characteristic value set with demand 2..
Based on this, it can establish three nodes, 1., 2. and 3. three nodes respectively correspond the demand, wherein node is 1.
1., which includes: to obtain output spy using input feature vector value set (the geographic location feature value of user) to corresponding demand
Processing rule (driver's data at access net about vehicle online service end of value indicative set (online driver's quantity on 3000 meters of periphery)
Maintenance module), the input feature vector value set of the node needs not rely on other nodes.
2. 2. node corresponds to demand, which includes: to utilize the input feature vector value set (geographic location feature of user
Value) obtain output characteristic value set (all passengers quantities for needing to distribute order on 3000 meters of present position periphery) processing rule
Then (the passenger data maintenance module at access net about vehicle online service end), the input feature vector value set of the node needs not rely on it
His node.
3. 3. node corresponds to demand, which includes: to utilize input feature vector value set (passenger present position periphery
3000 meters of online driver's quantity, 3000 meters of passenger present position periphery all passengers quantities for needing to distribute order) obtain
Obtain the processing rule of output characteristic value set (driver's quantity on 3000 meters of passenger present position periphery and the ratio of passengers quantity)
1. and 2. (by driver's quantity divided by passengers quantity), the input feature vector value set of the node need to rely on node, 3. node exists
Two are relied on node.
It is appreciated that obtaining output characteristic value set using input feature vector value set involved in above-mentioned two example
Processing rule only illustrates, and in practical application, can according to need flexible configuration processing rule.For example, in processing rule
May include following one or more:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；Wherein, the fortune
Calculation mode indicates to obtain the calculating process of output characteristic value set, such as special how using the progress operation of input feature vector value set
Levy conversion, feature branch mailbox, feature normalization or feature union operation etc..
By access preset data source address, output spy is obtained using input feature vector value set from the preset data source
Value indicative set；Data source information indicates which position to obtain output characteristic value set from, may include the interface of required access
Address data memory etc. in address, the IP address of server-side, file storage address or database.
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Screening is carried out to output data using parameter preset and obtains output characteristic value set；Wherein, which may include holding
Required various parameters when row processing rule, for example, aforementioned nodes 1. in 3000 meters of periphery etc..
Access preset data source address obtains output data using input feature vector value set from the preset data source,
Operation is carried out to output data in the way of default operation and obtains output characteristic value set.
By above-mentioned example as it can be seen that based on party in request to the needs of characteristic value collection, server-side can construct multiple nodes, section
Point can provide characteristic value collection, the identical node that different demands side needs towards different parties in request for multiple parties in request
It only needs to develop once, each node directly can provide service for party in request, and when needed, server-side calls corresponding section
Point can also be called when needed for other nodes, to realize that node is multiplexed, reduce development cost.Wherein, if node
1. and 2. be relied on node there are multiple, such as 3. above-mentioned node exists and is relied on node, call node 3. after, node 3. defeated
Enter characteristic value collection need to rely on call node 1. and 2. after output as a result, at this point it is possible to concurrent invocation is each to be relied on section
Point, for example, can open simultaneously in the preferable situation of process performance for calculating equipment and be relied on section described in multiple thread dispatchings
Point meets requirement of the more multi-thread upper mold type to real-time so as to improve the acquisition efficiency of characteristic value collection.
There is Such analysis it is found that corresponding to the destination node of acquisition request, it may be necessary to rely on other nodes, it is also possible to no
Need to rely on other nodes, the present embodiment also provides a kind of processing side of output characteristic value set for being quickly obtained destination node
Formula, optionally, the execution module are specifically used for:
Call the destination node:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, if the input feature vector value set of the destination node needs not rely on it
His node, the input feature vector value set of the destination node are determined by the information in the acquisition request；If the destination node
Input feature vector value set need to rely on other nodes, will acquire request and be supplied to and be relied on node, section is relied on described in calling
After point, the input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, re-execute the calling
The treatment process of invocation target node in module.
It is illustrated in conjunction with oriented graph data structure.For the ease of recording nodal information, quickly search between nodal information
Dependence, in the present embodiment, it is the multiple prestore node and can use digraph stored, the arc in the digraph
Indicate the dependence between the node.
It is made of in digraph the side between multiple nodes and each node there are direction, which is also referred to as
For arc.As shown in Figure 3B, be one comprising there are two the schematic diagram of the digraph of node, node V to node W there are an arc,
Node W is directed toward from node V in the direction of the arc, indicates that node V is adjacent to node W, and it is the adjoining of V from node V, W that node W is adjacent
Point.Therefore, it can use the arc in digraph and record dependence between the present embodiment interior joint, be based on this, nodal information
It is recorded using the data structure of digraph, and the storage organization of digraph can use adjacency matrix, neighbour in the related technology
Table, orthogonal list or adjacency multilist etc. are connect, it can be clever according to the consideration such as space performance or time performance in practical application
Selection living.
The function of modules and the realization process of effect are specifically detailed in above-mentioned in the acquisition device of features described above value set
The realization process of step is corresponded in method, details are not described herein.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The module of explanation may or may not be physically separated, and the component shown as module can be or can also be with
It is not physical module, it can it is in one place, or may be distributed on multiple network modules.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize application scheme.Those of ordinary skill in the art are not paying
Out in the case where creative work, it can understand and implement.
Correspondingly, the embodiment of the present application also provides a kind of server, which includes: processor；It is handled for storage
The memory of device executable instruction；Wherein, the processor is configured to:
Receive the acquisition request for being directed to target signature value set；
It is prestored in node from multiple, searches destination node corresponding with the target signature value set；It is described to prestore node
For providing the processing rule for utilizing input feature vector value set to obtain output characteristic value set and the node and other nodes
Dependence；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
In information determine, or rely on other nodes output characteristic value set obtain.
Correspondingly, the embodiment of the present application also provides a kind of computer storage medium, program is stored in the storage medium
Instruction, described program instruction include:
Receive the acquisition request for being directed to target signature value set；
It is prestored in node from multiple, searches destination node corresponding with the target signature value set；It is described to prestore node
For providing the processing rule for utilizing input feature vector value set to obtain output characteristic value set and the node and other nodes
Dependence；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, is obtained
The output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
In information determine, or rely on other nodes output characteristic value set obtain.
It is (including but unlimited that the storage medium for wherein including program code in one or more can be used in the embodiment of the present application
In magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer can use storage
Medium includes permanent and non-permanent, removable and non-removable media, can be accomplished by any method or technique information
Storage.Information can be computer readable instructions, data structure, the module of program or other data.The storage medium of computer
Example include but is not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory
(DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), digital versatile disc
(DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
Those skilled in the art will readily occur to its of the application after considering specification and practicing the invention applied here
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
The common knowledge in the art that person's adaptive change follows the general principle of the application and do not apply including the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by following
Claim is pointed out.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
The foregoing is merely the preferred embodiments of the application, not to limit the application, all essences in the application
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the application protection.
Claims (17)
1. a kind of acquisition methods of characteristic value collection, which is characterized in that the described method includes:
Receive the acquisition request for being directed to target signature value set；
Destination node corresponding with the target signature value set is searched in node from multiple prestore, the node that prestores is for mentioning
It is closed for the dependence for handling rule and the node and other nodes for obtaining output characteristic value set using input feature vector value set
System；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, described in acquisition
The output characteristic value set of destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
Information determines, or relies on the output characteristic value set acquisition of other nodes.
2. the method according to claim 1, wherein the multiple prestore in node, the corresponding letter of each node
Breath includes: to obtain the processing rule of output characteristic value set and the input feature vector value of the node using input feature vector value set
The output characteristic value set whether set needs to rely on other nodes obtains.
3. the method according to claim 1, wherein being held according to the input feature vector value set of the destination node
The corresponding processing rule of the row destination node, obtains the output characteristic value set of the destination node, comprising:
Call the destination node, comprising:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, described in acquisition
The output characteristic value set of destination node；Wherein, if the input feature vector value set of the destination node needs not rely on other sections
The input feature vector value set of point, the destination node is determined by the information in the acquisition request；If the destination node is defeated
Enter characteristic value collection and need to rely on other nodes, will acquire request and be supplied to and be relied on node, after being relied on node described in calling,
The input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, execute the invocation target node
The step of.
4. the method according to claim 1, wherein the multiple node that prestores is stored using digraph,
Arc in the digraph indicates the dependence between the node.
5. the method according to claim 1, wherein described obtain output characteristic value using input feature vector value set
The processing rule of set, including following one or more:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；
By access preset data source address, output characteristic value is obtained using input feature vector value set from the preset data source
Set；
Access preset data source address obtains output data using input feature vector value set from the preset data source, utilizes
Parameter preset carries out screening to output data and obtains output characteristic value set；
Access preset data source address obtains output data using input feature vector value set from the preset data source, utilizes
Default operation mode carries out operation to output data and obtains output characteristic value set.
6. according to the method described in claim 3, it is characterized in that, described being relied on node there are multiple in the destination node
In the case where, node is relied on described in the calling, comprising:
Node is relied on described in concurrent invocation.
7. according to the method described in claim 6, it is characterized in that, being relied on node described in the concurrent invocation, comprising:
It opens simultaneously and is relied on node described in multiple thread dispatchings.
8. the method according to claim 1, wherein the multiple node that prestores is stored in a configuration file,
The node is grouped by the configuration file, increases, operation is deleted or modified.
9. a kind of acquisition device of characteristic value collection, which is characterized in that described device includes:
Request receiving module is used for: receiving the acquisition request for being directed to target signature value set；
Searching module is used for: node checks destination node corresponding with the target signature value set is prestored from multiple, it is described pre-
Node is deposited for providing the processing for utilizing input feature vector value set to obtain output characteristic value set rule and the node and other
The dependence of node；
Execution module is used for: according to the input feature vector value set of the destination node, executing the corresponding processing of the destination node
Rule obtains the output characteristic value set of the destination node；Wherein, the input feature vector value set of the destination node is by described
Information in acquisition request determines, or relies on the output characteristic value set acquisition of other nodes.
10. device according to claim 9, which is characterized in that the multiple to prestore in node, the corresponding letter of each node
Breath includes: to obtain the processing rule of output characteristic value set and the input feature vector value of the node using input feature vector value set
The output characteristic value set whether set needs to rely on other nodes obtains.
11. device according to claim 9, which is characterized in that the execution module is specifically used for:
Call the destination node:
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, described in acquisition
The output characteristic value set of destination node；Wherein, if the input feature vector value set of the destination node needs not rely on other sections
The input feature vector value set of point, the destination node is determined by the information in the acquisition request；If the destination node is defeated
Enter characteristic value collection and need to rely on other nodes, will acquire request and be supplied to and be relied on node, after being relied on node described in calling,
The input feature vector value set of the destination node is determined using the output characteristic value set for being relied on node；
Wherein, it is described be relied on node it is called when, node will be relied on as destination node, re-execute the calling module
The treatment process of middle invocation target node.
12. device according to claim 9, which is characterized in that the multiple node that prestores is recorded using digraph,
Arc in the digraph indicates the dependence between the node.
13. device according to claim 9, which is characterized in that described to obtain output feature using input feature vector value set
The processing rule of value set, including following one or more:
By presetting operation mode, operation is carried out to input feature vector value set and obtains output characteristic value set；
By access preset data source address, output characteristic value is obtained using input feature vector value set from the preset data source
Set；
Access preset data source address obtains output data using input feature vector value set from the preset data source, utilizes
Parameter preset carries out screening to output data and obtains output characteristic value set；
Access preset data source address obtains output data using input feature vector value set from the preset data source, utilizes
Default operation mode carries out operation to output data and obtains output characteristic value set.
14. device according to claim 9, which is characterized in that the execution module is also used to: in the destination node
There are it is multiple it is described be relied on node in the case where, node is relied on described in concurrent invocation.
15. device according to claim 9, which is characterized in that the execution module is also used to:
It opens simultaneously and is relied on node described in multiple thread dispatchings.
16. a kind of server, which is characterized in that the server includes: processor；For depositing for storage processor executable instruction
Reservoir；Wherein, the processor is configured to:
Receive the acquisition request for being directed to target signature value set；
Node checks destination node corresponding with the target signature value set is prestored from multiple, the node that prestores is for providing
The processing rule of output characteristic value set and the dependence of the node and other nodes are obtained using input feature vector value set；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, described in acquisition
The output characteristic value set of destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
Information determines, or relies on the output characteristic value set acquisition of other nodes.
17. a kind of computer storage medium, which is characterized in that be stored with program instruction in the storage medium, described program refers to
Order includes:
Receive the acquisition request for being directed to target signature value set；
Node checks destination node corresponding with the target signature value set is prestored from multiple, the node that prestores is for providing
The processing rule of output characteristic value set and the dependence of the node and other nodes are obtained using input feature vector value set；
According to the input feature vector value set of the destination node, the corresponding processing rule of the destination node is executed, described in acquisition
The output characteristic value set of destination node；Wherein, the input feature vector value set of the destination node is by the acquisition request
Information determines, or relies on the output characteristic value set acquisition of other nodes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710639827.0A CN109327484B (en) | 2017-07-31 | 2017-07-31 | Method and device for acquiring characteristic value set, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710639827.0A CN109327484B (en) | 2017-07-31 | 2017-07-31 | Method and device for acquiring characteristic value set, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109327484A true CN109327484A (en) | 2019-02-12 |
| CN109327484B CN109327484B (en) | 2021-09-28 |
Family
ID=65244743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710639827.0A Active CN109327484B (en) | 2017-07-31 | 2017-07-31 | Method and device for acquiring characteristic value set, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109327484B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418200A (en) * | 2021-01-25 | 2021-02-26 | 成都点泽智能科技有限公司 | Object detection method and device based on thermal imaging and server |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298681A (en) * | 2011-06-22 | 2011-12-28 | 西北大学 | Software identification method based on data stream sliced sheet |
| CN102945311A (en) * | 2012-10-08 | 2013-02-27 | 南京航空航天大学 | Method for diagnosing fault by functional fault directed graph |
| CN103124279A (en) * | 2011-11-18 | 2013-05-29 | 浪潮(北京)电子信息产业有限公司 | System for outputting resource information and method for achieving the same |
| CN103440339A (en) * | 2013-09-09 | 2013-12-11 | 中国农业银行股份有限公司 | Method, device and system for searching application system change association objects |
| CN103780629A (en) * | 2014-02-14 | 2014-05-07 | 北京工业大学 | Concurrent access request incidence relation-oriented access control harmonizing method and device |
| CN104298677A (en) * | 2013-07-16 | 2015-01-21 | 中国移动通信集团浙江有限公司 | Method and system of identifying dependency relationship of concerns |
| CN104486105A (en) * | 2014-12-05 | 2015-04-01 | 广东省电信规划设计院有限公司 | Transmission network service configuration method and system |
| CN105721527A (en) * | 2014-12-04 | 2016-06-29 | 金蝶软件（中国）有限公司 | Data processing method and server |
| CN106657261A (en) * | 2016-11-08 | 2017-05-10 | 西安电子科技大学宁波信息技术研究院 | Coalition game and distance prediction based inter-vehicle data transmission method in Internet of Vehicles |
-
2017
- 2017-07-31 CN CN201710639827.0A patent/CN109327484B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298681A (en) * | 2011-06-22 | 2011-12-28 | 西北大学 | Software identification method based on data stream sliced sheet |
| CN103124279A (en) * | 2011-11-18 | 2013-05-29 | 浪潮(北京)电子信息产业有限公司 | System for outputting resource information and method for achieving the same |
| CN102945311A (en) * | 2012-10-08 | 2013-02-27 | 南京航空航天大学 | Method for diagnosing fault by functional fault directed graph |
| CN104298677A (en) * | 2013-07-16 | 2015-01-21 | 中国移动通信集团浙江有限公司 | Method and system of identifying dependency relationship of concerns |
| CN103440339A (en) * | 2013-09-09 | 2013-12-11 | 中国农业银行股份有限公司 | Method, device and system for searching application system change association objects |
| CN103780629A (en) * | 2014-02-14 | 2014-05-07 | 北京工业大学 | Concurrent access request incidence relation-oriented access control harmonizing method and device |
| CN105721527A (en) * | 2014-12-04 | 2016-06-29 | 金蝶软件（中国）有限公司 | Data processing method and server |
| CN104486105A (en) * | 2014-12-05 | 2015-04-01 | 广东省电信规划设计院有限公司 | Transmission network service configuration method and system |
| CN106657261A (en) * | 2016-11-08 | 2017-05-10 | 西安电子科技大学宁波信息技术研究院 | Coalition game and distance prediction based inter-vehicle data transmission method in Internet of Vehicles |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418200A (en) * | 2021-01-25 | 2021-02-26 | 成都点泽智能科技有限公司 | Object detection method and device based on thermal imaging and server |
| CN112418200B (en) * | 2021-01-25 | 2021-04-02 | 成都点泽智能科技有限公司 | Object detection method and device based on thermal imaging and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109327484B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9858348B1 (en) | System and method for presentation of media related to a context | |
| US9817895B2 (en) | Associating video content with geographic maps | |
| CN105900087B (en) | For inquiring the abundant content of answer | |
| US20110173176A1 (en) | Automatic Generation of an Interest Network and Tag Filter | |
| US7650287B2 (en) | Regional attribute determination method, regional attribute determination device, and regional attribute determination program | |
| CA2860172A1 (en) | System and method for generating, accessing, and updating geofeeds | |
| US7783636B2 (en) | Personalized information retrieval search with backoff | |
| CN108932257A (en) | The querying method and device of multi-dimensional data | |
| CN108733715A (en) | The determination method and device of building entrance | |
| CN106649426A (en) | Data analysis method, data analysis platform and server | |
| US10375454B1 (en) | Audio data and image data integration | |
| CN101908057B (en) | Information processing apparatus and information processing method | |
| CN107968807A (en) | Automatically update the method and device of local cache resource | |
| Ramtohul et al. | A prototype mobile augmented reality systems for cultural heritage sites | |
| CN105847320A (en) | Resource obtaining method and device | |
| He et al. | A hierarchical matrix factorization approach for location-based web service QoS prediction | |
| Schuster et al. | Scalable online conformance checking using incremental prefix-alignment computation | |
| CN109327484A (en) | Acquisition methods, device, server and the storage medium of characteristic value collection | |
| Corradi et al. | Automatic extraction of POIs in smart cities: Big data processing in ParticipAct | |
| Tous et al. | Multimedia big data computing for in-depth event analysis | |
| Kliment et al. | Publishing OGC resources discovered on the mainstream web in an SDI catalogue | |
| Wang et al. | Informative image selection for crowdsourcing-based mobile location recognition | |
| US20130081028A1 (en) | Receiving discrete interface device subtask result data and acquiring task result data | |
| CN113435948A (en) | E-commerce platform data monitoring method and system | |
| US20200117755A1 (en) | Intelligent video bridge for a closed circuit television system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |