CN113553097B - Model version management method and device - Google Patents
Model version management method and device Download PDFInfo
- Publication number
- CN113553097B CN113553097B CN202110875090.9A CN202110875090A CN113553097B CN 113553097 B CN113553097 B CN 113553097B CN 202110875090 A CN202110875090 A CN 202110875090A CN 113553097 B CN113553097 B CN 113553097B
- Authority
- CN
- China
- Prior art keywords
- model
- identifier
- business
- version
- configuring
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Stored Programmes (AREA)
Abstract
The utility model discloses a model version management method and a device, wherein the method comprises the steps of firstly configuring a first identifier in a first standard format for a model after the model is established; then responding to the received request for adjusting the model, and configuring an upgraded first identifier for the adjusted model; responding to a received request for releasing any model, acquiring and storing current information of any model, and acquiring a business model corresponding to any model; and finally, configuring a second identifier in a second standard format for the business model based on the first identifier of the arbitrary model, so that the business model is issued in the form of the second identifier. The management of models of different versions is efficiently and intuitively realized.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a model version management method and apparatus.
Background
In the big data era, an enterprise utilizes machine learning to establish a model in a specific field and guide the production development of the enterprise, which becomes an important mode. When the model is established by an enterprise, the model is firstly established in a development environment and iterated for multiple times, and the trained model is released to a production environment for business personnel to use. Due to the fact that the types of businesses are various, modeling iteration is required to be carried out on a certain business for being arranged in a production environment for many times, and therefore enterprises can build a great number of machine learning models.
In the related art, management of the model is inefficient.
Disclosure of Invention
The present disclosure is directed to a method and an apparatus for managing model versions.
In order to achieve the above object, according to a first aspect of the present disclosure, there is provided a model version management method including: after the model is built, configuring a first identifier in a first standard format for the model; responding to a received request for adjusting the model, and configuring an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained by the last adjustment; responding to a received request for releasing any model, acquiring and storing current information of any model, and acquiring a business model corresponding to any model; and configuring a second identifier in a second standard format for the business model based on the first identifier of any model, so that the business model is issued in the form of the second identifier.
Optionally, after obtaining the service model, the method further includes: and carrying out Hash calculation on any model and the service model.
Optionally, configuring a second identifier in a second standard format for the business model based on the first identifier of any of the models, including: performing first expansion on a preset field contained in a first identifier of any model to obtain a target field; and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
Optionally, the method further comprises: before establishing the model, determining a sample set of the model to be established from a plurality of sample sets; labeling a label on a model to be established; and taking the sample set and the label as the identity of the model to be built.
According to a second aspect of the present disclosure, there is provided a model version management apparatus including: the first configuration unit is configured to configure a first identifier in a first standard format for the model after the model is established; a processing unit configured to adjust the model in response to receiving a request for adjusting the model, and configure an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained from a last adjustment; the acquisition unit is configured to respond to the received request for releasing any model, acquire and store the current information of any model, and obtain a business model corresponding to any model; and the second configuration unit is used for configuring a second identifier in a second standard format for the business model based on the first identifier of any model so as to enable the business model to be issued in the form of the second identifier.
Optionally, the apparatus further comprises: and carrying out Hash calculation on any model and the business model.
Optionally, configuring a second identifier in a second standard format for the business model based on the first identifier of any of the models, including: performing first expansion on a preset field contained in a first identifier of any model to obtain a target field; and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
Optionally, the apparatus further comprises: before establishing the model, determining a sample set of the model to be established from a plurality of sample sets; labeling a label on a model to be established; and taking the sample set and the label as the identity of the model to be built.
According to a third aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions for causing the computer to execute the model version management method according to any one of the embodiments of the first aspect.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the model version management method according to any one of the implementations of the first aspect.
In the embodiment of the disclosure, first, after the model is built, a first identifier in a first standard format is configured for the model; then responding to the received request for adjusting the model, and configuring an upgraded first identifier for the adjusted model; responding to a received request for issuing any model, acquiring and storing current information of any model, and acquiring a business model corresponding to any model; and finally, configuring a second identifier in a second standard format for the business model based on the first identifier of the arbitrary model, so that the business model is issued in the form of the second identifier. The model is divided into the development version and the production version, so that the model versions of the development environment and the production environment are mutually associated, the isolation of the model versions in the two environments is met, and the efficient and intuitive management of the models of different versions is realized. The technical problem of low efficiency in managing the version of the model in the related technology is solved.
Drawings
In order to more clearly illustrate the detailed description of the present disclosure or the technical solutions in the prior art, the drawings used in the detailed description or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow diagram of a model version management method according to an embodiment of the present disclosure;
FIG. 2 is a diagram of an application scenario of a model version management method according to an embodiment of the present disclosure;
FIG. 3 is another application scenario diagram of a model version management method according to an embodiment of the present disclosure;
fig. 4 is a block diagram of a model version management apparatus according to an embodiment of the present disclosure.
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those skilled in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only some embodiments of the present disclosure, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged as appropriate for the embodiments of the disclosure described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the present disclosure, the embodiments and the features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
According to an embodiment of the present disclosure, there is provided a model version management method, as shown in fig. 1, the method includes the following steps 101 to 104:
step 101: after the model is built, a first identifier in a first standard format is configured for the model.
In this embodiment, since the model is generally divided into a development environment and a production environment when the machine learning project is developed, the development environment may be an environment in which a developer can debug and develop when the sample set data is processed, the model is built, and the model is adjusted.
In the development environment, after the model is built, the model may be configured with a first identifier having a standard format, which may identify a development version of the current model in the development environment. The standard format may be a "string + number" format, where a "string" may be custom-defined at the time of first naming, such as "V", "Version", or other strings; the "number" is specified by the system. For example 1. In addition to the automated configuration naming, the system will also generate a timestamp for the current version (e.g., V1), ensuring that the modeling-related data for the model version remains unchanged.
As an optional implementation manner of this embodiment, before the model is established, a sample set of the model to be established is determined from a plurality of sample sets; labeling a label on a model to be established; and taking the sample set and the label as the identity of the model to be built.
In this alternative implementation, the sample set is the data set used in building the model. The labels are used for further distinguishing the models in the same sample set, and can be objects of modeling (such as 'forecast weather' or 'forecast temperature' in weather data) or characteristics of business (such as 'identifying the position of an automobile image' or 'identifying the brand of an automobile' in an automobile picture data set). Thus, a developer may select a particular sample set and note the tags in the development environment. The model version corresponds to the sample set and the label of a specific combination, a model can be established according to the selected sample set and label, and version management is carried out on the model under the sample set and the label.
Step 102: responding to a received request for adjusting the model, and configuring an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained by the last adjustment.
In this embodiment, in a development environment, in order to obtain a model most suitable for a modeling target, the model may be adjusted in real time, and the adjustment manner may include modifying the content of the feature quantity, the feature processing manner, the feature cleaning manner, the algorithm parameter, and the like during modeling. And automatically configuring the upgraded first identifier for the model aiming at the model obtained after each adjustment is completed. The first identifier after each upgrade is determined based on the identifier of the previous version. For example, each time the operation is completed and a new model is generated, the system automatically names the version number of the new model in a mode of increasing the number of the "character string + number" (if the second operation is completed (adjustment is completed), the version name is V2, if the nth operation is completed, the version name is Vn), at this time, the "character string" is consistent with the character string set in the first-step naming, and the "number" is automatically increased by 1. While the system will generate a timestamp for each new model version, the data for each specific version of the model remains unchanged. The naming rule based on the first identifier has the characteristics of systematicness, pertinence and intuition.
Thus, a series of versions of the model under the sample set and the label are obtained in the development environment, and the larger the version number is, the newer the modeling time is. And the version numbers are not related to each other if different sample sets or versions under different labels of the same sample set. By adopting the mode of the embodiment, the systematic naming of the model version in the development environment is simply and efficiently realized. The method can effectively distinguish and manage the model versions established under different sample sets, the same label of the same sample set and the different labels of the same sample set.
When a machine learning model is built for a business target and a specific model is adjusted, operations such as cleaning, modeling, adjusting and the like are generally required for several times, and the operations can generate different model results. Version management of the development environment is used to manage these model results.
Step 103: and responding to a received request for issuing any model, acquiring and storing the current information of any model, and acquiring a business model corresponding to any model.
In this embodiment, the production environment generally refers to an environment that is released online after the model is developed, and at this time, the model can be used normally or called externally. The model version of the production environment is independent of the development version and can only be applied in the production environment.
Specifically, a sample set of a model to be released in a development environment and a version of the model built under a label are checked in a production environment, the version to be released is selected to be released, and a version model which is the same as the version to be released is generated in the production environment to serve as a business model during releasing. The generation process may be to freeze the state of the current time point of the model to be released and all current data, and copy and store the current state and data to obtain the data of the current time as the current business model. When problems occur in the release through the generation process, the data at the moment can be called at any time for analysis.
For the generated business model, a second identifier may be configured.
Step 104: and configuring a second identifier in a second standard format for the business model based on the first identifier of any model, so that the business model is issued in the form of the second identifier.
As an optional implementation manner of this embodiment, configuring, based on the first identifier of any of the models, a second identifier in a second standard format for the service model includes: performing first expansion on a preset field contained in a first identifier of any model to obtain a target field; and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
The preset character may be a version number of the development environment, and the standard format of the second identifier may be a "string + development environment version number" name (e.g., releaseV 6), where the "string" may be customized when the version is released for the first time, such as "R", "Release", or other strings, and metadata information such as Release time is added. The naming rule based on the second identifier has the characteristics of systematicness, pertinence and intuition.
As an optional implementation manner of this embodiment, after obtaining the service model, the method further includes: and carrying out Hash calculation on any model and the business model.
In this alternative implementation, a hash algorithm may be used to compute the electronic data of any model and business model to ensure consistency of the release version (e.g., releaseV 6) and the development environment version (e.g., V6) of the production environment. After release, this version is ready for use in a production environment.
Specifically, the data of the version model of the development environment can be used as raw data (referring to the data of the "whole model" of the version model of the development environment, the data of the "whole model" includes the data of the machine learning algorithm used by the model, the parameter configuration of each algorithm, the used feature name and weight, and the like) through the algorithms such as MD5 and SHA. And computes a second hash value on the data of the corresponding business model (the "whole business model" data, including the data of the used machine learning algorithm, the parameter configuration of the algorithm, the used feature name and weight, etc.). By comparing the two hash values (the comparison can be performed when the business model is generated and the second hash value is obtained through calculation), whether the issued business model is tampered or not is determined, so that the issued version model is not tampered finally, and the consistency of the issued version of the production environment and the version of the development environment is ensured. After the consistency of the release version of the production environment and the development environment is ensured, the version model is automatically released.
After the model in the production environment (e.g., releaseV 6) is applied to the actual business, the developer in the development environment can continue to adjust the version model (e.g., V6) of the development environment without affecting the model in the development environment. When a new model version needs to be released, the steps can be repeated, so that the replacement of the model version of the production environment is realized.
The production environment version is a clone of a specific version of the development environment, and the two versions are kept consistent by using a hash algorithm, and are mutually associated but independent. The production environment version is not only related to the version number of the development version, but also has metadata information such as release time and the like, and subsequent operation and maintenance are facilitated.
The version number of the embodiment comprises modeling sequence information, relationship information of versions in development and production environments and timestamp information, and the versions of the production environment and the development environment can be visually associated. The historical information of the model can be traced through the version number of the production environment model; meanwhile, after the model version is released, the model is not influenced when the model is operated by the development environment, and version disorder and the influence of the development environment on the production environment model are avoided.
Referring to fig. 3, fig. 3 illustrates an application scenario diagram of the model version management method, and by dividing the model into a development version and a production version, it is possible to not only correlate the model versions of the development environment and the production environment, but also satisfy the isolation of the model versions in the two environments. Referring to fig. 2, any "sample set and label" may be selected in a development environment, and then modeling is performed on the "sample set and label", and a version number is configured for the model after the model is obtained; then judging whether an adjustment request is received or not, if the adjustment request is received, adjusting the model to obtain a new model, and then continuing to configure a version number for the new model; and circulating in this way, and obtaining a series of models with the first identifiers in the circulating process. In a production environment, after a user (for example, operation and maintenance personnel) views models of various versions in a development environment, the model of any version is determined (or selected), then a business model corresponding to the version model is generated, and finally the business model is updated (i.e., a second identifier is configured for the business model). And circulating in this way, and obtaining a series of business models with second identifiers in the circulating process.
Referring to fig. 3, fig. 3 shows an application scenario diagram of the model version management method, 21 model versions are successively established in a development environment for a sample set and a tag, the latest model version is V21, and the relevant information of the model versions, such as the feature quantity, the feature processing mode, the feature cleaning mode, the algorithm parameter, and the like, of each version in the sample set and the tag is guaranteed to be fixed and unchangeable by a timestamp. After checking each version of the model, operation and maintenance personnel clone the V2 version of the development environment, and after ensuring the consistency of the model by using a Hash algorithm, the model is released to the production environment by the name of ReleaseV2 and applied to actual services. After that, the operation and maintenance personnel clone the V20 version of the development environment and release the V20 version under the name of ReleaseV20 under the condition of ensuring consistency, and the updating of the model version used for actual business in the production environment is completed.
The naming method of the machine learning model version iteration in the embodiment has the characteristics of systematicness, pertinence and intuition. The model version number under a specific sample set and label which are easy to read are automatically generated. The version number comprises the modeling sequence, the development and production version information and the timestamp information, so that the establishment sequence and the environment of the version can be intuitively known. The isolation of the machine learning model version in the production environment and the development environment is realized, the normal operation of the version in one environment cannot be influenced by the updating of the version in the other environment, and the chaos and misoperation of version replacement are avoided.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present disclosure, there is also provided an apparatus for implementing the model version management method, as shown in fig. 4, the apparatus includes: a first configuration unit 401 configured to configure a first identifier in a first standard format for a model after the model is built; a processing unit 402 configured to adjust the model in response to receiving a request for adjusting the model, and configure an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained from a last adjustment; an obtaining unit 403, configured to, in response to receiving a request for publishing any of the models, obtain and store current information of any of the models, and obtain a business model corresponding to any of the models; a second configuration unit 404, configured to configure a second identifier in a second standard format for the business model based on the first identifier of any of the models, so that the business model is published in the form of the second identifier.
As an optional implementation manner of this embodiment, the apparatus further includes: and carrying out Hash calculation on any model and the service model.
As an optional implementation manner of this embodiment, configuring, based on the first identifier of any of the models, a second identifier in a second standard format for the service model includes: performing first expansion on a preset field contained in a first identifier of any model to obtain a target field; and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
As an optional implementation manner of this embodiment, the apparatus further includes: before establishing the model, determining a sample set of the model to be established from a plurality of sample sets; labeling a label on a model to be established; and taking the sample set and the label as the identity of the model to be built.
The naming method of the machine learning model version iteration in the embodiment has the characteristics of systematicness, pertinence and intuition. The automatic generation of the model version number under a specific sample set and label which are easy to read is realized. The version number comprises the modeling sequence, the development and production version information and the timestamp information, so that the establishment sequence and the environment of the version can be intuitively known. The isolation of the machine learning model version in the production environment and the development environment is realized, the normal operation of the version in one environment cannot be influenced by the updating of the version in the other environment, and the chaos of version replacement and misoperation are avoided.
The embodiment of the present disclosure provides an electronic device, as shown in fig. 5, the electronic device includes one or more processors 51 and a memory 52, where one processor 51 is taken as an example in fig. 5.
The controller may further include: an input device 53 and an output device 54.
The processor 51, the memory 52, the input device 53 and the output device 54 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The processor 51 may be a Central Processing Unit (CPU). The processor 51 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 52, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the control methods in the embodiments of the present disclosure. The processor 51 executes various functional applications of the server and data processing, i.e., implements the model version management method of the above-described method embodiment, by running non-transitory software programs, instructions, and modules stored in the memory 52.
The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing device operated by the server, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, which may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 53 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing device of the server. The output device 54 may include a display device such as a display screen.
One or more modules are stored in the memory 52, which when executed by the one or more processors 51 perform the method as shown in FIG. 1.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the motor control methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random Access Memory (RAM), a flash memory (FlashMemory), a hard disk (hard disk drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims.
Claims (8)
1. A model version management method, comprising:
before establishing the model, determining a sample set of the model to be established from a plurality of sample sets;
labeling a label on a model to be established;
taking the sample set and the label as the identity of the model to be built;
after the model is built, configuring a first identifier in a first standard format for the model;
responding to a received request for adjusting the model, and configuring an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained by last adjustment;
responding to a received request for releasing any model, acquiring and storing current information of any model, and acquiring a business model corresponding to any model;
and configuring a second identifier in a second standard format for the business model based on the first identifier of any model, so that the business model is issued in the form of the second identifier.
2. The model version management method of claim 1, wherein after obtaining the business model, the method further comprises:
and carrying out Hash calculation on any model and the service model.
3. The model version management method according to claim 1, wherein configuring a second identifier in a second standard format for the business model based on the first identifier of any of the models comprises:
performing first expansion on a preset field contained in a first identifier of any model to obtain a target field;
and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
4. A model version management apparatus, comprising:
the device comprises a first configuration unit, a second configuration unit and a third configuration unit, wherein the first configuration unit determines a sample set of a model to be established from a plurality of sample sets before the model is established; labeling a label on a model to be established; taking the sample set and the label as the identity of the model to be built; a first identifier configured to configure a first standard format for a model after model building is complete;
a processing unit configured to adjust the model in response to receiving a request for adjusting the model, and configure an upgraded first identifier for the adjusted model, wherein the upgraded first identifier is determined based on an identifier obtained from a last adjustment;
the acquisition unit is configured to respond to the received request for releasing any model, acquire and store the current information of any model, and obtain a business model corresponding to any model;
and the second configuration unit is used for configuring a second identifier in a second standard format for the business model based on the first identifier of any model so that the business model is issued in the form of the second identifier.
5. The model version management apparatus according to claim 4, characterized in that said apparatus further comprises: and carrying out Hash calculation on any model and the service model.
6. The model version management device according to claim 4, wherein configuring a second identifier in a second standard format for the business model based on the first identifier of any of the models comprises:
performing first expansion on a preset field contained in a first identifier of any model to obtain a target field;
and on the basis of the target field, taking the time when the request is issued as second extended content to obtain a second identifier.
7. A computer-readable storage medium, characterized in that it stores computer instructions for causing the computer to execute the model version management method according to any one of claims 1 to 3.
8. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the model version management method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110875090.9A CN113553097B (en) | 2021-07-30 | 2021-07-30 | Model version management method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110875090.9A CN113553097B (en) | 2021-07-30 | 2021-07-30 | Model version management method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113553097A CN113553097A (en) | 2021-10-26 |
| CN113553097B true CN113553097B (en) | 2022-11-18 |
Family
ID=78133470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110875090.9A Active CN113553097B (en) | 2021-07-30 | 2021-07-30 | Model version management method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553097B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335389A (en) * | 2014-07-09 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Business visualization method and system |
| CN110168556A (en) * | 2016-11-10 | 2019-08-23 | 惠普发展公司，有限责任合伙企业 | Traceability identifier |
| CN110580305A (en) * | 2018-05-22 | 2019-12-17 | 北京京东尚科信息技术有限公司 | Method, apparatus, system, and medium for generating identifier |
| CN111782254A (en) * | 2020-07-02 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for upgrading object |
| CN111782637A (en) * | 2020-07-03 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Model construction method, device and equipment |
| CN112288092A (en) * | 2019-07-23 | 2021-01-29 | 百度时代网络技术（北京）有限公司 | Model evaluation method, model evaluation device, electronic device and storage medium |
| CN112363997A (en) * | 2020-11-10 | 2021-02-12 | 中国平安人寿保险股份有限公司 | Data version management method, device and storage medium |
| CN112529624A (en) * | 2020-12-15 | 2021-03-19 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating business prediction model |
| CN112947919A (en) * | 2019-11-26 | 2021-06-11 | 北京京东振世信息技术有限公司 | Method and device for constructing service model and processing service request |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8041120B2 (en) * | 2007-06-26 | 2011-10-18 | Microsoft Corporation | Unified digital ink recognition |
| US11138514B2 (en) * | 2017-03-23 | 2021-10-05 | Futurewei Technologies, Inc. | Review machine learning system |
| WO2019113122A1 (en) * | 2017-12-04 | 2019-06-13 | Conversica, Inc. | Systems and methods for improved machine learning for conversations |
| CN111104482A (en) * | 2019-12-18 | 2020-05-05 | 北京百度网讯科技有限公司 | Data processing method and device |
-
2021
- 2021-07-30 CN CN202110875090.9A patent/CN113553097B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335389A (en) * | 2014-07-09 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Business visualization method and system |
| CN110168556A (en) * | 2016-11-10 | 2019-08-23 | 惠普发展公司，有限责任合伙企业 | Traceability identifier |
| CN110580305A (en) * | 2018-05-22 | 2019-12-17 | 北京京东尚科信息技术有限公司 | Method, apparatus, system, and medium for generating identifier |
| CN112288092A (en) * | 2019-07-23 | 2021-01-29 | 百度时代网络技术（北京）有限公司 | Model evaluation method, model evaluation device, electronic device and storage medium |
| CN112947919A (en) * | 2019-11-26 | 2021-06-11 | 北京京东振世信息技术有限公司 | Method and device for constructing service model and processing service request |
| CN111782254A (en) * | 2020-07-02 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for upgrading object |
| CN111782637A (en) * | 2020-07-03 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Model construction method, device and equipment |
| CN112363997A (en) * | 2020-11-10 | 2021-02-12 | 中国平安人寿保险股份有限公司 | Data version management method, device and storage medium |
| CN112529624A (en) * | 2020-12-15 | 2021-03-19 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating business prediction model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113553097A (en) | 2021-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190286509A1 (en) | Hierarchical fault determination in an application performance management system | |
| US10942801B2 (en) | Application performance management system with collective learning | |
| CN113448862B (en) | Software version testing method and device and computer equipment | |
| CN110865806B (en) | Code processing method, device, server and storage medium | |
| CN114416703A (en) | Method, device, equipment and medium for automatically monitoring data integrity | |
| WO2019148657A1 (en) | Method for testing associated environments, electronic device and computer readable storage medium | |
| US11153183B2 (en) | Compacted messaging for application performance management system | |
| US20230384750A1 (en) | Efficient controller data generation and extraction | |
| CN113553097B (en) | Model version management method and device | |
| CN110007946B (en) | Method, device, equipment and medium for updating algorithm model | |
| CN116578497A (en) | Automatic interface testing method, system, computer equipment and storage medium | |
| US20160366021A1 (en) | User interface for an application performance management system | |
| CN107015831A (en) | A kind of client updating management method upgraded based on server end and system | |
| CN110716804A (en) | Method and device for automatically deleting useless resources, storage medium and electronic equipment | |
| CN116303320A (en) | Real-time task management method, device, equipment and medium based on log file | |
| CN115203306A (en) | Data exporting method and device, computer equipment and readable storage medium | |
| US10817396B2 (en) | Recognition of operational elements by fingerprint in an application performance management system | |
| CN109525642B (en) | LIMS system client data automatic reporting method under user mechanism | |
| CN111159988A (en) | Model processing method and device, computer equipment and storage medium | |
| CN113760723B (en) | Business process debugging method and device | |
| US20240078467A1 (en) | Predicting the intent of a network operator for making config changes | |
| CN117240711B (en) | Automatic updating method, device and equipment for cluster management tool configuration file | |
| CN112907221B (en) | Self-service method, device and system | |
| CN117194254A (en) | Operation and maintenance method and device | |
| CN113778842A (en) | Fault-tolerant test method and device, electronic equipment and storage medium |
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 |