CN109542505B - Method and device for updating resources in shared goods shelf - Google Patents
Method and device for updating resources in shared goods shelf Download PDFInfo
- Publication number
- CN109542505B CN109542505B CN201811484460.0A CN201811484460A CN109542505B CN 109542505 B CN109542505 B CN 109542505B CN 201811484460 A CN201811484460 A CN 201811484460A CN 109542505 B CN109542505 B CN 109542505B
- Authority
- CN
- China
- Prior art keywords
- updated
- updating
- resource
- project
- opinion
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/71—Version control; Configuration management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for updating resources in a shared goods shelf, belonging to the technical field of computers, wherein the method comprises the following steps: the method comprises the following steps of obtaining the field of project resources to be updated in a shared goods shelf; dividing resource modules of project resources to be updated to obtain function classification of each module; inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating suggestion; the resource updating model is obtained by training according to the project resources of the updated project resources when the project resources are not updated, the field of the updated project resources, the functional classification of the updated modules in the updated project resources and the actual updating opinions of the updated project resources; updating the project resources to be updated according to the recommended updating opinions to obtain updated project resources; the problem that the efficiency of updating the project resources is low when the user updates the project resources can be solved; the efficiency of updating project resources can be improved.
Description
Technical Field
The invention relates to a method and a device for updating resources in a shared goods shelf, and belongs to the technical field of computers.
Background
With the development of software project development technology, the project supports independent uploading and sharing of individual resources in a sharing shelf, and different resources can be used in different technical fields. The shared shelf refers to a platform for storing project resources uploaded by an uploader, and the project resources refer to code resources for creating project templates.
Project resources stored in the shared shelf need to be optimized over time, and a traditional optimization mode is that updated project resources are uploaded to the shared shelf again by a user of the project resources.
However, when the user updates the project resource, the user is required to manually screen the module to be updated, and then the step of uploading the updated project resource is executed, so that the efficiency of updating the project resource is low.
Disclosure of Invention
The invention aims to provide a method and a device for updating resources in a shared shelf. In order to achieve the purpose, the invention provides the following technical scheme:
in a first aspect, a method for updating resources in a shared shelf is provided, the method comprising:
the method comprises the following steps of obtaining the field of project resources to be updated in a shared goods shelf;
dividing the resource modules of the project resources to be updated to obtain the function classification of each module;
inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating opinion; the resource updating model is obtained by training according to the project resource of the updated project resource when the project resource is not updated, the field of the updated project resource, the functional classification of the updated module in the updated project resource and the actual updating opinion of the updated project resource;
and updating the project resource to be updated according to the recommendation updating opinion to obtain the updated project resource.
Optionally, before inputting the project resource to be updated, the domain to which the project resource belongs, and the function classification of each module into a resource update model trained in advance to obtain a recommendation update opinion, the method further includes:
obtaining the field of each updated project resource in the shared shelf;
acquiring the function classification of the updated module in the updated project resource;
acquiring the actual updating opinion of each updated module;
generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions;
inputting at least one group of the affiliated fields, the function classification and the project resources before updating in the training set into a preset neural network model to obtain a training result;
comparing the training result with the corresponding actual updating opinion in the training set;
and when the probability of matching between the training result and the corresponding actual updating opinion does not reach the preset probability value, adjusting the network parameters in the neural network model until the probability of matching between the training result and the actual updating opinion reaches the preset probability value, and obtaining the resource updating model.
Optionally, after the updating the item resource to be updated according to the recommendation update opinion and obtaining the updated item resource, the method further includes:
acquiring an actual updating opinion of the updated project resource;
and updating the resource updating model by using the actual updating opinion, the updated project resource, the field of the updated project resource and the functional classification corresponding to the actual updating opinion.
Optionally, the network parameters in the resource update model include: the weight corresponding to each field and the weight corresponding to each function type.
In a second aspect, there is provided an apparatus for updating resources on a shared shelf, the apparatus comprising:
the first field acquisition module is used for acquiring the field of the project resource to be updated in the shared goods shelf;
the first classification acquisition module is used for dividing the resource modules of the project resources to be updated to obtain the function classification of each module;
the first opinion acquisition module is used for inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommended updating opinion; the resource updating model is obtained by training according to the project resource of the updated project resource when the project resource is not updated, the field of the updated project resource, the functional classification of the updated module in the updated project resource and the actual updating opinion of the updated project resource;
and the resource updating module is used for updating the project resource to be updated according to the recommendation updating opinion to obtain the updated project resource.
Optionally, the apparatus further comprises:
the second field acquisition module is used for inputting the project resources to be updated, the affiliated fields and the function classification of each module into a pre-trained resource updating model, and acquiring the affiliated fields of each updated project resource in the shared shelf before the recommended updating opinions are obtained;
the second classification acquisition module is used for acquiring the function classification of the updated module in the updated project resource;
the second opinion acquisition module is used for acquiring the actual updating opinion of each updated module;
the training set acquisition module is used for generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions;
a training result obtaining module, configured to input at least one group of the domains, the function classifications, and the pre-update project resources in the training set into a preset neural network model to obtain a training result;
the result comparison module is used for comparing the training result with the actual updating opinion corresponding to the training set;
and the model training module is used for adjusting the network parameters in the neural network model when the matched probability between the training result and the corresponding actual updating opinion does not reach the preset probability value, and stopping until the matched probability between the training result and the actual updating opinion reaches the preset probability value to obtain the resource updating model.
Optionally, the apparatus further comprises:
a third opinion obtaining module, configured to obtain an actual update opinion for the updated project resource after the update of the project resource to be updated is performed according to the recommended update opinion and the updated project resource is obtained;
and the model updating module is used for updating the resource updating model by using the actual updating opinion, the updated project resource, the field to which the updated project resource belongs and the functional classification corresponding to the actual updating opinion.
Optionally, the network parameters in the resource update model include: the weight corresponding to each field and the weight corresponding to each function type.
The invention has the beneficial effects that: the method comprises the following steps of obtaining the field of project resources to be updated in a shared goods shelf; dividing resource modules of project resources to be updated to obtain function classification of each module; inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating suggestion; the resource updating model is obtained by training according to the project resources of the updated project resources when the project resources are not updated, the field of the updated project resources, the functional classification of the updated modules in the updated project resources and the actual updating opinions of the updated project resources; updating the project resources to be updated according to the recommended updating opinions to obtain updated project resources; the problem that when a user updates the project resources, the user needs to manually screen the modules to be updated and then executes the step of uploading the updated project resources, and the efficiency of updating the project resources is low can be solved; the efficiency of updating project resources can be improved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is a flow diagram of a method for updating resources in a shared shelf provided by an embodiment of the present application;
FIG. 2 is a flow diagram of a method for updating resources on a shared shelf according to another embodiment of the present application;
fig. 3 is a block diagram of an apparatus for updating resources in a shared shelf according to an embodiment of the present application.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Optionally, the present application takes an execution subject of each step in each embodiment as an example of a device running a shared shelf, where the device may be a server; alternatively, the device may be a terminal such as a computer, a personal computer, or a tablet computer, and the present embodiment does not limit the type of the device.
FIG. 1 is a flowchart of a method for updating resources on a shared shelf according to an embodiment of the present application. The method at least comprises the following steps:
The project resource to be updated is code uploaded into the shared shelf by the uploader for creating a project module.
Alternatively, the art includes, but is not limited to: the method includes the following steps that the social field, the enterprise management field, the electronic transaction field and the like are adopted, and the division mode of the field to which the project resource to be updated belongs is not limited.
Optionally, the field of project resources to be updated may be uploaded by developers; or, the device may be obtained after scanning by a code scanning tool; or, the information may also be input by a manager of the device, and the embodiment does not limit the obtaining manner in the related art.
And 102, dividing resource modules of project resources to be updated to obtain the function classification of each module.
Optionally, the resource module of the project resource to be updated includes at least two modules, each module is used for implementing a corresponding function, such as: iteration function, check function, etc., and the present embodiment does not limit the division manner of the function classification of the module.
103, inputting the project resources to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating suggestion; the resource updating model is obtained by training according to the project resources of the updated project resources when the project resources are not updated, the field of the updated project resources, the functional classification of the updated modules in the updated project resources and the actual updating opinions of the updated project resources.
And 104, updating the item resources to be updated according to the recommended updating opinions to obtain the updated item resources.
Optionally, the device identifies the recommended update opinion to generate an update instruction, and updates the item resource to be updated according to the update instruction by using a code editing tool, so as to obtain an updated item resource.
In summary, the method for updating resources in a shared shelf provided by this embodiment obtains the field of the resource of the item to be updated in the shared shelf; dividing resource modules of project resources to be updated to obtain function classification of each module; inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating suggestion; the resource updating model is obtained by training according to the project resources of the updated project resources when the project resources are not updated, the field of the updated project resources, the functional classification of the updated modules in the updated project resources and the actual updating opinions of the updated project resources; updating the project resources to be updated according to the recommended updating opinions to obtain updated project resources; the problem that when a user updates the project resources, the user needs to manually screen the modules to be updated and then executes the step of uploading the updated project resources, and the efficiency of updating the project resources is low can be solved; the efficiency of updating project resources can be improved.
In addition, the resource updating model is used for updating the project resources to be updated in the shared shelf, and managers of the shared shelf do not need to update the project resources to be updated manually, so that the efficiency of classifying the target project resources can be improved.
In addition, the recommendation updating opinions of the project resources to be updated are determined according to the affiliated field of the updated project resources in the shared shelf and the function classification of the updated modules, and the obtained recommendation updating opinions meet the updating requirement of a user with high accuracy, so that the error rate in updating the project resources to be updated can be reduced.
Optionally, fig. 2 is a flowchart of a method for updating resources in a shared shelf according to an embodiment of the present application. Before step 101, the method further comprises the following steps:
The classification manner of the domain to which the updated project resource belongs is the same as the classification manner of the domain to which the project resource is to be updated.
The functional classification of the updated module is divided in the same manner as the functional classification of the module in the project resource to be updated.
Alternatively, the actual update opinion of the updated module may be fed back by the user using the updated project resource to which the updated module belongs before the updated project resource; alternatively, the update result may be generated according to an update operation performed by the user when the updated project resource is not updated, and the manner of acquiring the actual update opinion is not limited in this embodiment.
And step 204, generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions.
Alternatively, the Neural Network model may be a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN), or the like, and the present embodiment does not limit the type of the Neural Network model.
And step 207, when the matching probability between the training result and the corresponding actual updating opinion does not reach the preset probability value, adjusting network parameters in the neural network model until the matching probability between the training result and the actual updating opinion reaches the preset probability value, and obtaining the resource updating model.
The preset probability value may be 90%, 98%, etc., and the value of the preset probability value is not limited in this embodiment.
Optionally, the network parameters in the resource update model include: the weight corresponding to each field and the weight corresponding to each function type.
In summary, according to the method for updating resources in a shared shelf provided by this embodiment, the neural network model is trained to obtain the resource update model according to the field to which the updated project resource in the shared shelf belongs and the function classification of the updated module, so that the error rate when the update suggestion is determined can be reduced.
Optionally, based on the above embodiment, after step 205, the method further includes: acquiring actual updating opinions of the updated project resources; and updating the resource updating model by using the actual updating opinions, the updated project resources, the field to which the updated project resources belong and the functional classification corresponding to the actual updating opinions.
Fig. 3 is a block diagram of an apparatus for updating resources in a shared shelf according to an embodiment of the present application. The device at least comprises the following modules: a first domain obtaining module 310, a first classification obtaining module 320, a first opinion obtaining module 330 and a resource updating module 340.
A first domain obtaining module 310, configured to obtain a domain to which a project resource to be updated in a shared shelf belongs;
a first classification obtaining module 320, configured to divide resource modules of the project resource to be updated to obtain a function classification of each module;
a first opinion obtaining module 330, configured to input the item resource to be updated, the domain to which the item belongs, and the function classification of each module into a pre-trained resource update model to obtain a recommended update opinion; the resource updating model is obtained by training according to the project resource of the updated project resource when the project resource is not updated, the field of the updated project resource, the functional classification of the updated module in the updated project resource and the actual updating opinion of the updated project resource;
and the resource updating module 340 is configured to update the item resource to be updated according to the recommendation update opinion, so as to obtain an updated item resource.
Reference is made to the above-described method embodiments for relevant content.
Optionally, based on the embodiment shown in fig. 3, the apparatus further includes:
the second field acquisition module is used for inputting the project resources to be updated, the affiliated fields and the function classification of each module into a pre-trained resource updating model, and acquiring the affiliated fields of each updated project resource in the shared shelf before the recommended updating opinions are obtained;
the second classification acquisition module is used for acquiring the function classification of the updated module in the updated project resource;
the second opinion acquisition module is used for acquiring the actual updating opinion of each updated module;
the training set acquisition module is used for generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions;
a training result obtaining module, configured to input at least one group of the domains, the function classifications, and the pre-update project resources in the training set into a preset neural network model to obtain a training result;
the result comparison module is used for comparing the training result with the actual updating opinion corresponding to the training set;
and the model training module is used for adjusting the network parameters in the neural network model when the matched probability between the training result and the corresponding actual updating opinion does not reach the preset probability value, and stopping until the matched probability between the training result and the actual updating opinion reaches the preset probability value to obtain the resource updating model.
Optionally, the apparatus further comprises:
a third opinion obtaining module, configured to obtain an actual update opinion for the updated project resource after the update of the project resource to be updated is performed according to the recommended update opinion and the updated project resource is obtained;
and the model updating module is used for updating the resource updating model by using the actual updating opinion, the updated project resource, the field to which the updated project resource belongs and the functional classification corresponding to the actual updating opinion.
Optionally, the network parameters in the resource update model include: the weight corresponding to each field and the weight corresponding to each function type.
It should be noted that: in the above embodiment, when performing the project development management, the project development management apparatus is only illustrated by dividing the functional modules, and in practical applications, the function distribution may be performed by different functional modules according to needs, that is, the internal structure of the project development management apparatus may be divided into different functional modules to perform all or part of the functions described above. In addition, the project development management apparatus and the project development management method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method for updating resources in a shared shelf, the method comprising:
the method comprises the following steps of obtaining a field of project resources to be updated in a shared shelf, wherein the shared shelf is a platform used for storing project resources uploaded by an uploader, the project resources are code resources used for creating project templates, and the project resources to be updated are codes uploaded to the shared shelf by the uploader and used for creating project modules;
dividing the resource modules of the project resources to be updated to obtain the function classification of each module;
inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommendation updating opinion; the resource updating model is obtained by training according to the project resource of the updated project resource when the project resource is not updated, the field of the updated project resource, the functional classification of the updated module in the updated project resource and the actual updating opinion of the updated project resource;
and updating the project resource to be updated according to the recommendation updating opinion to obtain the updated project resource.
2. The method according to claim 1, wherein before inputting the resource of the item to be updated, the domain and the function of each module into a resource updating model trained in advance to obtain a recommendation updating opinion, the method further comprises:
obtaining the field of each updated project resource in the shared shelf;
acquiring the function classification of the updated module in the updated project resource;
acquiring the actual updating opinion of each updated module;
generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions;
inputting at least one group of the affiliated fields, the function classification and the project resources before updating in the training set into a preset neural network model to obtain a training result;
comparing the training result with the corresponding actual updating opinion in the training set;
and when the probability of matching between the training result and the corresponding actual updating opinion does not reach a preset probability value, adjusting network parameters in the neural network model until the probability of matching between the training result and the actual updating opinion reaches the preset probability value, and obtaining the resource updating model.
3. The method according to claim 1, wherein after the updating the item resource to be updated according to the recommendation and update opinion to obtain an updated item resource, the method further comprises:
acquiring an actual updating opinion of the updated project resource;
and updating the resource updating model by using the actual updating opinion, the updated project resource, the field of the updated project resource and the functional classification corresponding to the actual updating opinion.
4. The method of claim 1, wherein the network parameters in the resource update model comprise: the weight corresponding to each field and the weight corresponding to each function type.
5. An apparatus for updating resources in a shared shelf, the apparatus comprising:
the system comprises a first field acquisition module, a first storage module and a second field acquisition module, wherein the first field acquisition module is used for acquiring the field of to-be-updated project resources in a shared shelf, the shared shelf is a platform for storing the project resources uploaded by an uploader, the project resources are code resources for creating a project template, and the to-be-updated project resources are codes uploaded to the shared shelf by the uploader and used for creating the project module;
the first classification acquisition module is used for dividing the resource modules of the project resources to be updated to obtain the function classification of each module;
the first opinion acquisition module is used for inputting the project resource to be updated, the affiliated field and the function classification of each module into a pre-trained resource updating model to obtain a recommended updating opinion; the resource updating model is obtained by training according to the project resource of the updated project resource when the project resource is not updated, the field of the updated project resource, the functional classification of the updated module in the updated project resource and the actual updating opinion of the updated project resource;
and the resource updating module is used for updating the project resource to be updated according to the recommendation updating opinion to obtain the updated project resource.
6. The apparatus of claim 5, further comprising:
the second field acquisition module is used for inputting the project resources to be updated, the affiliated fields and the function classification of each module into a pre-trained resource updating model, and acquiring the affiliated fields of each updated project resource in the shared shelf before the recommended updating opinions are obtained;
the second classification acquisition module is used for acquiring the function classification of the updated module in the updated project resource;
the second opinion acquisition module is used for acquiring the actual updating opinion of each updated module;
the training set acquisition module is used for generating a training set according to the field to which each updated project resource belongs, the function classification, the project resources when not updated and the corresponding actual updating opinions;
a training result obtaining module, configured to input at least one group of the domains, the function classifications, and the pre-update project resources in the training set into a preset neural network model to obtain a training result;
the result comparison module is used for comparing the training result with the actual updating opinion corresponding to the training set;
and the model training module is used for adjusting the network parameters in the neural network model when the matched probability between the training result and the corresponding actual updating opinion does not reach the preset probability value, and stopping until the matched probability between the training result and the actual updating opinion reaches the preset probability value to obtain the resource updating model.
7. The apparatus of claim 5, further comprising:
a third opinion obtaining module, configured to obtain an actual update opinion for the updated project resource after the update of the project resource to be updated is performed according to the recommended update opinion and the updated project resource is obtained;
and the model updating module is used for updating the resource updating model by using the actual updating opinion, the updated project resource, the field to which the updated project resource belongs and the functional classification corresponding to the actual updating opinion.
8. The apparatus of claim 5, wherein the network parameters in the resource update model comprise: the weight corresponding to each field and the weight corresponding to each function type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811484460.0A CN109542505B (en) | 2018-12-06 | 2018-12-06 | Method and device for updating resources in shared goods shelf |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811484460.0A CN109542505B (en) | 2018-12-06 | 2018-12-06 | Method and device for updating resources in shared goods shelf |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109542505A CN109542505A (en) | 2019-03-29 |
| CN109542505B true CN109542505B (en) | 2022-03-22 |
Family
ID=65853917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811484460.0A Active CN109542505B (en) | 2018-12-06 | 2018-12-06 | Method and device for updating resources in shared goods shelf |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109542505B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102455897A (en) * | 2010-10-27 | 2012-05-16 | 无锡江南计算技术研究所 | Iterative compilation method and device based on embodiment |
| CN105512163A (en) * | 2015-09-28 | 2016-04-20 | 张新长 | Self-adaptive vector data incremental updating method |
| CN107273436A (en) * | 2017-05-24 | 2017-10-20 | 北京京东尚科信息技术有限公司 | The training method and trainer of a kind of recommended models |
| EP3382417A2 (en) * | 2017-03-28 | 2018-10-03 | Siemens Healthcare GmbH | Magnetic resonance image reconstruction system and method |
| CN108733358A (en) * | 2018-05-21 | 2018-11-02 | 浪潮软件集团有限公司 | Spark-based machine learning workflow construction method and device |
-
2018
- 2018-12-06 CN CN201811484460.0A patent/CN109542505B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102455897A (en) * | 2010-10-27 | 2012-05-16 | 无锡江南计算技术研究所 | Iterative compilation method and device based on embodiment |
| CN105512163A (en) * | 2015-09-28 | 2016-04-20 | 张新长 | Self-adaptive vector data incremental updating method |
| EP3382417A2 (en) * | 2017-03-28 | 2018-10-03 | Siemens Healthcare GmbH | Magnetic resonance image reconstruction system and method |
| CN107273436A (en) * | 2017-05-24 | 2017-10-20 | 北京京东尚科信息技术有限公司 | The training method and trainer of a kind of recommended models |
| CN108733358A (en) * | 2018-05-21 | 2018-11-02 | 浪潮软件集团有限公司 | Spark-based machine learning workflow construction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109542505A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10380500B2 (en) | Version control for asynchronous distributed machine learning | |
| US8498950B2 (en) | System for training classifiers in multiple categories through active learning | |
| CN109815471A (en) | Contract text generation method, device, computer equipment and storage medium | |
| Lai et al. | FSMRank: Feature selection algorithm for learning to rank | |
| CN112613917A (en) | Information pushing method, device and equipment based on user portrait and storage medium | |
| WO2019223145A1 (en) | Electronic device, promotion list recommendation method and system, and computer-readable storage medium | |
| CN110196943A (en) | A kind of position intelligent recommendation system, method and its system | |
| CN112464042A (en) | Task label generation method according to relation graph convolution network and related device | |
| CN110837356A (en) | Data processing method and device | |
| CN111445319A (en) | Voucher generation method and device, computer equipment and storage medium | |
| CN112817560B (en) | Computing task processing method, system and computer readable storage medium based on table function | |
| CN108550019B (en) | Resume screening method and device | |
| US11055666B2 (en) | Systems and methods for automation of corporate workflow processes via machine learning techniques | |
| CN109542505B (en) | Method and device for updating resources in shared goods shelf | |
| CN117236624A (en) | Issue repairer recommendation method and apparatus based on dynamic graph | |
| WO2023035940A1 (en) | Target object recommendation method and system | |
| CN112214602A (en) | Text classification method and device based on humor, electronic equipment and storage medium | |
| CN111949697A (en) | Data processing method, device, terminal and medium based on search engine | |
| CN116820714A (en) | Scheduling method, device, equipment and storage medium of computing equipment | |
| CN115543428A (en) | Simulated data generation method and device based on strategy template | |
| CN115481615A (en) | Document generation method and device, electronic equipment and nonvolatile storage medium | |
| CN114611477A (en) | Design recommendation method and device for data table, electronic equipment and medium | |
| CN113822215A (en) | Equipment operation guide file generation method and device, electronic equipment and storage medium | |
| CN113239034A (en) | Big data resource integration method and system based on artificial intelligence and cloud platform | |
| Ribeiro et al. | Improving productive processes using a process mining approach |
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 |