Agent deployment method, development method, medium, electronic device, and program product

Abstract

An agent deployment method, a development method, a medium, an electronic device and a program product, relate to the technical field of computers and agents, and the agent deployment method can include: in response to an acquisition instruction, acquiring a base image corresponding to an agent, wherein the base image is constructed by a second platform in a development stage of the agent; based on the base image and obtained configuration information of the agent, deploying the agent in the first platform, so that the agent deployed in the first platform can provide a conversation service in a running stage, wherein the configuration information is configured by the second platform in the development stage of developing the agent. The first platform and the second platform are two independent platforms, so that the environments dependent on the development stage and the running stage of the agent are separated, thereby avoiding the influence of environmental failures caused by the development stage on the running of the agent, and further avoiding the influence on the provision of the conversation service.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer technology and agent technology, and in particular, to an agent deployment method, a development method, a medium, an electronic device, and a program product. BACKGROUND

[0002] By designing the workflow of the agent and developing the agent by using available tools, the developed agent can provide a conversation service. Before running the agent, the agent needs to be deployed, and before deployment, the agent is developed and debugged, etc.

[0003] However, in the related art, the development, debugging, deployment, and running of the agent are all completed in the same environment, so if the environment fails during development or debugging, the running of the deployed agent will be affected, and thus the provision of the conversation service will be affected. SUMMARY

[0004] This summary is provided to introduce a selection of concepts, which will be described with greater specificity below in the detailed description section. This summary is not intended to identify key or essential features of the claimed technology, nor is it intended to limit the scope of the claimed technology.

[0005] In a first aspect, the present disclosure provides an agent deployment method, executed by a first platform, comprising:

[0006] In response to an acquisition instruction, acquiring a base image corresponding to an agent, wherein the base image is constructed by a second platform in a development stage of developing the agent;

[0007] Based on the base image and obtained configuration information of the agent, deploying the agent in the first platform, so that the deployed agent in the first platform can provide a conversation service in a running stage, wherein the configuration information is configured by the second platform in the development stage of developing the agent.

[0008] In a second aspect, the present disclosure provides an agent development method, executed by a second platform, comprising:

[0009] Developing an agent to obtain a developed agent, wherein the development includes configuring a base image of the agent and configuration information of the agent;

[0010] The first platform is configured to acquire, in response to an acquisition instruction, a base image corresponding to an agent, and deploy the agent in the first platform based on the base image and obtained configuration information of the agent, so that the deployed agent in the first platform can provide a conversation service in a running stage.

[0011] In a third aspect, the disclosure provides an agent deployment apparatus applied to a first platform, comprising:

[0012] a first obtaining module configured to obtain a base image of an agent in response to an obtaining instruction, wherein the base image is constructed by a second platform in a development stage of developing the agent;

[0013] a deployment module configured to deploy the agent in the first platform based on the base image and configuration information of the agent obtained, so that the agent deployed in the first platform can provide a conversation service in a running stage, wherein the configuration information is configured by the second platform in the development stage of developing the agent.

[0014] In a fourth aspect, the disclosure provides an agent development apparatus applied to a second platform, comprising:

[0015] a development module configured to develop an agent to obtain a developed agent, wherein the development comprises configuring a base image of the agent and configuration information of the agent;

[0016] wherein the first platform is configured to obtain the base image of the agent in response to an obtaining instruction, and deploy the agent in the first platform based on the base image and the configuration information of the agent obtained, so that the agent deployed in the first platform can provide a conversation service in a running stage.

[0017] In a fifth aspect, the disclosure provides a computer readable medium having a computer program stored thereon, which, when executed by a processing apparatus, implements the steps of the method of the first aspect or the steps of the method of the second aspect.

[0018] In a sixth aspect, the disclosure provides an electronic device, comprising:

[0019] a storage apparatus having a computer program stored thereon;

[0020] a processing apparatus configured to execute the computer program in the storage apparatus to implement the steps of the method of the first aspect or the steps of the method of the second aspect.

[0021] In a seventh aspect, the disclosure provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method of the first aspect or the steps of the method of the second aspect.

[0022] By the technical solution, the agent is deployed by the first platform, so that the agent deployed in the first platform can provide the dialogue service in the running stage; in addition, the agent is implemented by the second platform in the development stage, such as development, debugging and publishing, and the first platform and the second platform are two independent platforms. Therefore, the environments relied on by the development stage and the running stage of the agent are separated, so as to avoid the influence of the environment failure caused by the development stage on the running of the agent, and further avoid the influence on the provision of the dialogue service.

[0023] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0024] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail the following specific embodiments in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale. In the drawings:

[0025] Figure 1 is an architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0026] Figure 2 is an architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0027] Figure 3 is a flowchart of an agent deployment method according to an embodiment of the present disclosure;

[0028] Figure 4 is a process diagram of implementing development and running of an agent according to an embodiment of the present disclosure;

[0029] Figure 5 is another architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0030] Figure 6 is another architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0031] Figure 7 is another architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0032] Figure 8 is another architecture diagram of an environment for implementing development and running of an agent according to an embodiment of the present disclosure;

[0033] Figure 9is another architecture diagram of an environment for development and running of an agent according to an embodiment of the present disclosure;

[0034] Figure 10 is another architecture diagram of an environment for development and running of an agent according to an embodiment of the present disclosure;

[0035] Figure 11 is a block diagram of an agent deployment apparatus according to an embodiment of the present disclosure;

[0036] Figure 12 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] Embodiments of the present disclosure will be described in more detail with reference to the drawings. While certain embodiments of the present disclosure will be shown in the drawings, it should be understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather should be understood to include all modifications, equivalents, and / or alternatives falling within the spirit and scope of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the present disclosure.

[0038] It should be understood that each step recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.

[0039] The term “comprising” and variations thereof as used herein are used inclusively, i.e., “comprising but not limited to.” The term “based on” is “based at least in part on.” The term “one embodiment” means “at least one embodiment.” The term “another embodiment” means “at least one additional embodiment.” The term “some embodiments” means “at least some embodiments.” Related definitions are given below in the description of the application.

[0040] It should be noted that the terms “first”, “second”, and the like used in the present disclosure are merely used to distinguish different devices, modules or units, and do not imply the order or interdependence of the functions performed by these devices, modules or units.

[0041] It should be noted that the terms “one”, “multiple”, and the like used in the present disclosure are illustrative and not limiting, and those skilled in the art should understand that “one or more” should be understood unless otherwise explicitly stated in the context.

[0042] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are merely used for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0043] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0044] For example, in response to receiving an active request of a user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium, etc. that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0045] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0046] It can be understood that the above notification and obtaining of user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0047] Meanwhile, it can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solutions should comply with the requirements of relevant laws and regulations and relevant provisions.

[0048] By designing the workflow of the agent and developing the agent by using available tools, the developed agent can provide a conversation service. Before running the agent, the agent needs to be deployed, and before deployment, the development and debugging of the agent and the like are involved.

[0049] However, in the related art, the development, debugging, deployment and running of the agent are all completed in the same environment. Figure 1 is an architectural diagram of an environment for implementing the development and running of an agent in the related art according to the embodiments of the present disclosure. Referring to Figure 1In the development platform, the development, debugging, publishing and deployment of the agent are completed, so that the deployed agent is based on a model service, and the deployed agent is run in the development platform, so that the agent in the running stage is used to provide a dialogue service. The model service corresponds to various trained models, such as a LLM (Large Language Model) and a vector mapping model, and the like, which are used to support the implementation of the dialogue service. These model services can be model services in a dedicated resource pool or model services in a public resource pool.

[0050] In Figure 1 In the architecture shown, the development and debugging of the agent, the publishing of the agent and the deployment of the agent are all implemented in the development platform. If the environment fails during development or debugging, the running of the agent will be affected, and then the provision of the dialogue service will be affected.

[0051] Therefore, the embodiments of the present disclosure provide an agent deployment method, a deployment device, a development method, a development device, a medium, an electronic device and a program product. The embodiments of the present disclosure are explained and described below in combination with the drawings.

[0052] Figure 2 is an architecture diagram of a system for implementing the development and running of an agent according to an embodiment of the present disclosure. Referring to Figure 2 The deployment of the agent is implemented by the first platform, so that the agent deployed in the first platform can provide a dialogue service in the running stage. In addition, the development, debugging and publishing and the like involved in the development stage of the agent are implemented by the second platform. The first platform and the second platform are two independent platforms. Therefore, the environments relied on by the development stage and the running stage of the agent are separated, so that the environment failure caused by the development stage does not affect the running of the agent, and then the provision of the dialogue service is avoided.

[0053] Figure 3 is a flowchart of an agent deployment method according to an embodiment of the present disclosure. The agent deployment method can be executed by the first platform, for example Figure 2 The first platform shown, and the agent deployment method can be executed by an agent deployment device. The agent deployment device can be implemented by software and / or hardware, and the software and / or hardware can be configured in the first platform. Referring to Figure 3 The agent deployment method can include steps 310 and 320.

[0054] In step 310, in response to an acquisition instruction, a base image corresponding to an agent is acquired, wherein the base image is constructed by the second platform in the development stage of developing the agent.

[0055] The obtaining instruction can be initiated by a developer of the third party through the first platform, and the obtaining instruction is used to instruct to deploy the agent in the first platform.

[0056] The base image can be configured as a YAML (YAML Ain't Markup Language) file, and the YAML file is determined by the second platform in a development stage of implementing the agent. The base image includes underlying dependencies of deploying the agent, and provides an environment (for example, Python, Java, and the like) required for running of the agent (for example, Ubuntu, Alpine Linux, and the like), a code file, and an operating system, and the like. After the second platform builds the base image, the second platform can push the base image into an image repository of the third party, so that the first platform can obtain the base image of the agent from the image repository of the third party.

[0057] The image repository can be provided by a third platform provided by the third party. For an implementation of obtaining the base image of the agent from the image repository and the third platform, reference can be made to related embodiments described below, and details are not described herein again. With reference to the foregoing Figure 2 The publishing of the agent can implement building of the base image and pushing of the base image into the image repository of the third party.

[0058] In step 320, the agent is deployed in the first platform based on the base image and the obtained configuration information of the agent, so that the deployed agent in the first platform can provide the conversation service in a running stage. The configuration information is configured by the second platform in the development stage of developing the agent.

[0059] The configuration information of the agent can include a plug-in, a workflow, a knowledge base, and an agent base configuration, and the like. The configuration information of the agent can be configured by a developer of the agent developer through the second platform.

[0060] The deployed agent includes various components, and each component is used to implement different functions. For example, a code execution component is used to implement execution of a code when providing the conversation service. For another example, a conversation access component is used as a conversation entrance, and is used to receive a conversation request and provide an API (Application Programming Interface) of other components of the agent for a third-party application, for example, an API of a model access component. For another example, the model access component is used to connect different models, implement selection of the models, and transmit parameters of the models, and the like.

[0061] In the foregoing manner, the first platform implements deployment of the agent, so that the agent deployed in the first platform can provide the dialogue service in the running stage. In addition, the second platform implements development, debugging, and publishing of the agent in the development stage. The first platform and the second platform are two independent platforms. Thus, the environment relied on by the development stage and the running stage of the agent is separated, so as to avoid the influence of the environment failure caused by the development stage on the running of the agent, and further avoid the influence on the provision of the dialogue service.

[0062] In some embodiments, the agent deployed in the first platform can be encapsulated with the application (i.e., service) provided by the third party, so that the application provided by the third party has the dialogue capability.

[0063] Figure 4 is a process diagram for implementing development and running of an agent according to an embodiment of the present disclosure. An agent developer performs arrangement and debugging of the agent through the second platform, and completes development of the agent. The developed agent is published to the first platform, for example, a base image is pushed into an image repository of the third party. The third party sends an acquisition instruction through the first platform, so that the first platform deploys the agent based on the base image and obtained configuration information of the agent, and encapsulates the third-party application with the deployed agent, to obtain a group of target services. The target service includes the capability of the third-party application itself and the dialogue capability provided by the agent, in other words, the third-party application can have the dialogue capability.

[0064] In some embodiments, in the first platform, resources relied on by different agents deployed in the running stage to provide the dialogue service are independent of each other. In this way, the different agents in the running stage do not affect each other.

[0065] In some embodiments, in the first platform, resources relied on by different agents deployed in the running stage to provide the dialogue service can be shared. In this way, the utilization rate of the resources can be improved.

[0066] In some embodiments, in the first platform, resources relied on by the agent deployed in the running stage to provide the dialogue service can be shared with other deployed agents, and the resources relied on by the agent deployed in the running stage to provide the dialogue service can also be independent. Whether the agent shares the resources or independently owns the resources can be configured according to actual conditions.

[0067] In the foregoing embodiments, the resources relied on by the agent deployed in the running stage to provide the dialogue service can be server and database resources. For example, the agent deployed in the running stage to provide the dialogue service can rely on a server and a database. Figure 5For example, the agent 1 and the agent 2 share the database 1 when providing the conversation service in the running stage, and the agent 3 has the database 2 alone when providing the conversation service in the running stage. In this way, the database 2 relied on by the agent 3 when providing the conversation service in the running stage is not preempted by the agent 1 and the agent 2, and if the database 2 fails, it does not affect the agent 1 and the agent 2 to provide the conversation service. In addition, the agent 1 and the agent 2 share the database 1 when providing the conversation service in the running stage, which can improve the utilization efficiency of the database 1.

[0068] In some embodiments, the configuration information of the agent can be obtained by: in response to the acquisition instruction, sending a pull request to the second platform, so that the second platform authenticates based on the authentication information carried in the pull request, the pull request is used to pull the configuration information of the corresponding agent; in the case of passing the authentication, pulling the configuration information of the corresponding agent from the second platform.

[0069] From the above, it can be seen that the first platform can obtain the base image of the agent from the mirror warehouse. As an example, the agent information is carried in the acquisition instruction, which uniquely identifies an agent, and then the base image of the corresponding agent can be obtained based on the agent information. The explanation and description of the agent information can refer to the related embodiments described below, and this embodiment will not be repeated here.

[0070] The authentication information can be a user key, and the second platform manages the user key with the acquisition permission. The second platform authenticates the user key corresponding to the authentication information based on the user key managed by itself, and in the case of passing the authentication, it is determined that the authentication is passed, otherwise, it is determined that the authentication fails. In the case of passing the authentication, the second platform allows the first platform to pull the configuration information from the second platform.

[0071] In the above manner, in the case of passing the authentication, the first platform is allowed to pull the configuration information of the agent from the second platform, thereby improving the security.

[0072] In some embodiments, the second platform can provide a gateway server, and the gateway server intercepts the pull request. The gateway server authenticates based on the authentication information, and in the case of passing the authentication, the pull request is forwarded to the second platform by the gateway server, so that the first platform pulls the configuration information of the corresponding agent from the second platform. The explanation and description of the authentication information can refer to the related embodiments described above, and this embodiment will not be repeated here.

[0073] In some embodiments, the above step of pulling the configuration information of the corresponding agent from the second platform in the case of passing the authentication can include: in the case of passing the authentication, pulling the configuration information of the corresponding agent from the second platform based on the agent information carried in the pull request.

[0074] From the above, the agent information is used to uniquely identify an agent, and according to the agent information, the configuration information of the corresponding agent can be pulled.

[0075] The agent information can include an agent identifier. The second platform supports the development of different agents, and thus the agent identifier can be used to identify an agent, so as to ensure that different agents can be accurately identified, distinguished and managed in the multi-agent second platform. Further, the agent identifier is determined based on at least one of the following information:

[0076] An identity of the agent;

[0077] A name of the agent;

[0078] A name of a space where the agent is located.

[0079] The identity of the agent is globally unique, that is, the identity of the agent is the same in different spaces. The name of the agent can also be globally unique, that is, the name of the agent is the same in different spaces. The second platform can be divided into multiple spaces, and different spaces can be used to isolate different configuration information of agents, such as knowledge bases, workflows, plug-ins, etc. Therefore, in order to pull the configuration information in different spaces, the agent identifier can be uniquely determined in combination with the identity of the agent, the name of the agent and the name of the space where the agent is located.

[0080] The agent information can also include an agent version number. Since the second platform supports the development and release of multiple versions of agents, the agent version number can be used to accurately identify, distinguish and manage different versions of agents. The agent version number is used as a kind of agent information, so as to facilitate the pulling of the configuration information of the corresponding version of the agent. Thus, based on the agent identifier and the agent version number, the configuration information of an agent can be uniquely determined, and the corresponding configuration information can be pulled.

[0081] In some embodiments, the above-mentioned second platform can include multiple second platforms, each corresponding to a different environment, and the agent information can also include an environment parameter. In the case where the authentication is passed, the step of pulling the configuration information of the corresponding agent from the second platform based on the agent information carried in the pulling request can include: in the case where the authentication is passed, pulling the configuration information of the corresponding agent from a target second platform in the multiple second platforms based on the agent identifier, the agent version number and the environment parameter in the pulling request.

[0082] The explanations and descriptions of the agent identifier and the agent version number can be referred to the above-mentioned related embodiments, which will not be repeated here.

[0083] The target second platform is a second platform matched with the environment parameter. On this basis, the configuration information of the agent matched with the agent identifier and the agent version number is pulled from the target second platform based on the agent identifier and the agent version number.

[0084] The environment corresponding to the second platform in the embodiment can be a test environment and a production environment. The agent configuration in the test environment can be manually synchronized to the production environment. Since the agent release exists cross-environment release, i.e., needs to be released to the test environment and the production environment, and the two environments are completely isolated, in order to support cross-environment release, it is proposed that the configuration information of the corresponding agent can be pulled from different environments, thereby improving the diversity of the pulling mode of the configuration information.

[0085] In some embodiments, the configuration information of the agent can be pulled statically. Static pulling refers to that all configuration information is acquired at one time when the agent is deployed, and the configuration information is no longer updated in the subsequent running process. For example, the pulling of the configuration information is implemented in response to the acquisition instruction as described above.

[0086] In some embodiments, the configuration information of the agent can also be pulled dynamically. Dynamic pulling refers to that the agent acquires or updates certain configuration information in real time according to the needs in the running stage. When deployed, the agent is deployed based on the basic image, and the configuration information is acquired or updated in real time in the running stage, so as to provide a dialogue service based on the latest acquired or updated configuration information.

[0087] In some embodiments, the interfaces for providing the dialogue service in the first platform and the second platform are consistent. The interfaces can include a regenerated interface and an acquisition question reply interface, and the like.

[0088] In this way, the third party can define the same interface based on the interface document given by the second platform, thereby reducing the interface connection cost of the third party.

[0089] In some embodiments, the above deployment method can further include: collecting running data of the agent deployed in the first platform in the running stage; and uploading the running data to a third platform. The second platform and the third platform are platforms provided by the same third party.

[0090] Figure 6 is another architecture diagram of an environment for developing and running an agent according to an embodiment of the present disclosure. Referring to Figure 6 , the running data of the agent in the first platform can be uploaded to the third platform.

[0091] Among them, PaaS (Platform as a Service) can be a third platform, and the PaaS provides a database for storing running data.

[0092] The running data can include Loggings, Tracing and Metrics. The Loggings is a record generated in the process of running the agent, which records the events occurring in the running process in a structured or semi-structured text form. The Tracing is used to track the flow of a dialogue request in the agent. It focuses on the entire path from sending the dialogue request to the agent to finally completing, including the service components and call links of the agent passed through. The Metrics is a quantitative description of the running state of the agent, for example, the number of times of providing dialogue services and the response time of dialogue services provided by the agent in the running stage, etc.

[0093] As an example, in the case that the running data is synchronized to the third platform through the first platform, a data processing component can be configured in the agent deployed in the first platform, the running data of the agent in the running stage is collected through the data processing component, and is converted into a data format supported by the third platform, and then the converted data is uploaded to the third platform. Referring to Figure 7 , the PaaS is a third platform, and the first platform is deployed with a target service. The explanation and description of the target service can refer to the related embodiments described above. Figure 7 The component of the agent in the above-mentioned can realize the observation of the running data in the running stage, for example, the above-mentioned model access component, hereinafter referred to as a target component. The data processing component can be further configured in the target component, and the running data is processed by the data processing component, converted into a data format supported by the third platform, and uploaded to the PaaS.

[0094] As an example, in the case that the running data is synchronized to the third platform through the first platform, the target component in the agent deployed in the first platform can be rewritten through Java, so that the agent deployed in the first platform can access the third platform through Java agent, and then the running data observed by the target component in the agent deployed in the first platform is uploaded to the third platform based on the Java agent. Referring to Figure 8 , the PaaS is a third platform, and the first platform is deployed with a target service. The explanation and description of the target service can refer to the related embodiments described above. By rewriting the target component, the running data observed by the target component in the agent deployed in the first platform is uploaded to the third platform based on the Java agent.

[0095] As an example, in the case that the running data is synchronized to the third platform through the first platform, the first platform can access the third platform through an Adapter service, so that the running data observed by the target component in the agent deployed in the first platform is uploaded to the third platform. Referring to Figure 9 , the PaaS is the third platform, and the first platform deploys a target service. The explanation and description of the target service can refer to the related embodiments described above. By deploying the Adapter service in the agent, the running data observed by the target component in the agent deployed in the first platform is uploaded to the third platform based on the Java agent provided by the Adapter service.

[0096] As an example, in the case that the running data is synchronized to the third platform through the first platform, the observation of the running data can be implemented by an SDK (Software Development Kit) of a third-party application of the third platform. Since the third-party application and the third platform both belong to the third party, the third party can self-integrate and upload the observed running data to the third platform. Referring to Figure 10 , the PaaS is the third platform, and the first platform deploys a target service. The explanation and description of the target service can refer to the related embodiments described above. The observation of the running data is implemented by the SDK of the third-party application, and the SDK of the third-party application self-integrates the third platform based on the Java agent to upload the observed running data to the third platform.

[0097] In the above manner, the running data of the agent in the first platform is synchronized to the third platform, so that the running data can be provided to the developers of the third party for viewing.

[0098] In some embodiments, the running data can be uploaded to the second platform through the third platform or the first platform.

[0099] As an example, in the case that the running data is uploaded to the second platform through the third platform, the third platform can access the second platform through an Adapter service, so that the running data in the third platform is uploaded to the second platform.

[0100] As an example, in the case that the running data is uploaded to the second platform through the first platform, a data processing component can be configured in the first platform. The reporting process of the running data based on the data processing component can refer to the related embodiments described above, and this embodiment will not be described herein.

[0101] Based on the same concept, the embodiments of the present disclosure provide an agent development method, which can be executed by the second platform, for example Figure 2The second platform is shown, and the agent development method can be executed by an agent development device, wherein the agent development device can be implemented by software and / or hardware, and the software and / or hardware can be configured in the second platform.

[0102] The agent deployment method comprises: developing an agent to obtain a developed agent, wherein the development comprises configuring a base image of the agent and configuration information of the agent; and wherein the first platform is configured to, in response to an acquisition instruction, acquire the base image corresponding to the agent, and deploy the agent in the first platform based on the base image and the obtained configuration information of the agent, so that the agent deployed in the first platform can provide a conversation service in a running stage.

[0103] Based on the same concept, the embodiments of the present disclosure provide an agent deployment device applied to a first platform, Figure 11 is a block diagram of an agent deployment device according to an embodiment of the present disclosure. The agent deployment device 1100 comprises:

[0104] The first acquisition module 1101 is configured to, in response to an acquisition instruction, acquire a base image corresponding to an agent, wherein the base image is constructed by a second platform in a development stage of developing the agent;

[0105] The deployment module 1102 is configured to deploy the agent in the first platform based on the base image and obtained configuration information of the agent, so that the agent deployed in the first platform can provide a conversation service in a running stage, wherein the configuration information is configured by the second platform in the development stage of developing the agent.

[0106] Optionally, in the first platform, resources relied on by different agents deployed in the running stage to provide the conversation service are independent of each other.

[0107] Optionally, the agent deployment device 1100 further comprises a second acquisition module configured to obtain the configuration information of the agent, and the second acquisition module comprises:

[0108] The sending sub-module is configured to, in response to the acquisition instruction, send a pull request to the second platform to enable the second platform to perform authentication based on authentication information carried in the pull request, and the pull request is used to pull the configuration information of the corresponding agent.

[0109] The pulling sub-module is configured to, in the case of passing the authentication, pull the configuration information of the corresponding agent from the second platform.

[0110] Optionally, the pulling sub-module is configured to:

[0111] In a case where the authentication passes, configuration information of the corresponding agent is pulled from the second platform based on agent information carried in the pulling request, wherein the agent information comprises an agent identifier and an agent version number.

[0112] Optionally, the second platform comprises a plurality of second platforms, each of the second platforms corresponds to a different environment, the agent information further comprises an environment parameter, and the pulling submodule is further configured to:

[0113] In a case where the authentication passes, configuration information of the corresponding agent is pulled from a target second platform of the plurality of second platforms based on the agent identifier, the agent version number and the environment parameter carried in the pulling request.

[0114] Optionally, the agent identifier is determined based on at least one of the following information:

[0115] an identity of the agent;

[0116] a name of the agent;

[0117] a name of a space where the agent is located.

[0118] Optionally, an interface of the agent of the first platform and the second platform for providing the conversation service is consistent.

[0119] Optionally, the agent deployment apparatus 1100 further comprises:

[0120] a collection module configured to collect running data of the agent deployed in the first platform in the running stage;

[0121] an uploading module configured to upload the running data to a third platform, wherein the second platform and the third platform are platforms provided by a same third party.

[0122] Optionally, the running data is uploaded to the second platform through the third platform or the first platform.

[0123] Embodiments of each module in the agent deployment apparatus 1100 described above can refer to the related embodiments described above, and details are not repeated here.

[0124] Based on the same concept, the embodiments of the present disclosure provide an agent development apparatus applied to a second platform, comprising:

[0125] a development module configured to develop an agent to obtain a developed agent, wherein the development comprises configuring a base image of the agent and configuration information of the agent;

[0126] The first platform is used to respond to the acquisition command, acquire the base image of the corresponding intelligent agent, and deploy the intelligent agent in the first platform based on the base image and the acquired configuration information of the intelligent agent, so that the intelligent agent deployed in the first platform can provide dialogue services during the operation phase.

[0127] The implementation methods of each module in the above-mentioned intelligent agent development device can refer to the above-mentioned related embodiments, and will not be repeated here.

[0128] This disclosure also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the above-described agent deployment method or agent development method.

[0129] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described agent deployment method or agent development method.

[0130] This disclosure also provides an electronic device, including:

[0131] A storage device on which computer programs are stored;

[0132] A processing device is used to execute the computer program in the storage device to implement the steps of the above-described agent deployment method or the above-described agent development method.

[0133] The following is for reference. Figure 12 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 2 A schematic diagram of the structure of the first or second platform (1200) in this disclosure. The terminal device in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 12 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0134] like Figure 12As shown, the electronic device 1200 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1201 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1202 or loaded into a random access memory (RAM) 1203 from a storage device 1208. Various programs and data required for the operation of the electronic device 1200 are also stored in the RAM 1203. The processing device 1201, the ROM 1202, and the RAM 1203 are connected to each other through a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0135] In general, the following devices can be connected to the I / O interface 1205: input devices 1206 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1207 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1208 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1209. The communication devices 1209 can allow the electronic device 1200 to communicate wirelessly or wired with other devices to exchange data. Although Figure 12 The electronic device 1200 is shown with various devices, but it should be understood that not all of the shown devices are required to be implemented or present. More or fewer devices can alternatively be implemented or present.

[0136] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 1209, or installed from the storage devices 1208, or installed from the ROM 1202. When the computer program is executed by the processing device 1201, the above-described functions defined in the methods of embodiments of the present disclosure are performed.

[0137] It is noted that the aforementioned computer-readable medium of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium can be, for example and without limitation, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a computer-readable program code transmitted by a computer-readable medium or a carrier wave in a baseband or as part of a carrier wave. Such a propagated computer-readable signal medium can take many forms, including but not limited to, an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. The computer-readable signal medium can also be any computer-readable medium that is not a computer-readable storage medium and that can be used to carry or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to, wire, cable, RF (radio frequency), or the like, or any suitable combination of the foregoing.

[0138] In some embodiments, the first platform or the second platform can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communications (e.g., a communications network) of any form or medium, including the Internet. Examples of communications networks include local area networks ("LANs"), wide area networks ("WANs"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

[0139] The aforementioned computer-readable medium can be included in the aforementioned electronic device; or can exist separately from the electronic device and can not be assembled into the electronic device.

[0140] The computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, cause the electronic device to: in response to an acquisition instruction, acquire a base image of the corresponding agent, wherein the base image is constructed by a second platform in a development stage of developing the agent; and based on the base image and obtained configuration information of the agent, deploy the agent in the first platform, so that the agent deployed in the first platform can provide a conversation service in a running stage, wherein the configuration information is configured by the second platform in the development stage of developing the agent.

[0141] Alternatively, the computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, cause the electronic device to: develop an agent to obtain a developed agent, wherein the development includes configuring a base image of the agent and configuration information of the agent; and wherein the first platform is configured to, in response to an acquisition instruction, acquire a base image of the corresponding agent, and based on the base image and obtained configuration information of the agent, deploy the agent in the first platform, so that the agent deployed in the first platform can provide a conversation service in a running stage.

[0142] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0143] The computer program product of the first aspect can include one or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform the operations of the method of the first aspect. The computer program product of the first aspect can include a computer-readable medium storing instructions that, when executed, cause one or more processors to perform the operations of the method of the first aspect.

[0144] The modules involved in the embodiments of the present disclosure can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0145] The functions described above in the present document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, example types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0146] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage media can include, without limitation, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include one or more lines of electrical wire, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] The above description merely illustrates the preferred embodiment of the disclosure and a principle of applied technologies. It should be understood by those skilled in the art that the disclosed range of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by the combinations of the technical features described above or their equivalent features without departing from the disclosed concept. For example, the technical solutions formed by the mutual replacement of the above-described features and the technical features with similar functions disclosed in the disclosure (but not limited to) can be formed.

[0148] Furthermore, although operations are depicted in a particular, sequential order, this should not be understood as requiring or implying that the operations are performed in the order illustrated or sequentially. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, although specific implementation details are contained in the above discussion, these should not be construed as limiting the scope of the disclosure. Certain features described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

[0149] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely illustrative of the example forms of implementing the claims. As to the means for performing the operations of the apparatus in the above-described embodiments, the specific manner in which the various modules perform the operations has been described in detail in the embodiments related to the method, and will not be described here.

Claims

1. A method for deploying intelligent agents, characterized in that, Executed by the first platform, including: In response to the acquisition command, the base image of the corresponding intelligent agent is acquired, wherein the base image is constructed by the second platform during the development phase of the intelligent agent; Based on the base image and the obtained configuration information of the agent, the agent is deployed in the first platform so that the agent deployed in the first platform can provide dialogue services during the runtime phase. The configuration information is configured by the second platform during the development phase of the agent. The configuration information is obtained through dynamic or static retrieval. Static retrieval means that the agent is deployed according to the obtained configuration information and the configuration information does not need to be updated during the runtime phase of the agent. Dynamic retrieval means that the agent provides the dialogue service according to the configuration information obtained or updated in real time during the runtime phase. The second platform includes multiple spaces, each used to isolate different configuration information of the intelligent agent. Each second platform corresponds to a different environment, including a production environment or a testing environment. The configuration information is obtained by sending a pull request to each second platform, enabling each platform to authenticate based on the authentication information carried in the pull request, which is used to pull the configuration information of the corresponding intelligent agent. If authentication is successful, a target second platform matching the environment parameters is determined from the multiple second platforms based on the environment parameters carried in the intelligent agent information of the pull request. The configuration information of the corresponding intelligent agent is pulled from the target second platform based on the intelligent agent identifier and version number carried in the intelligent agent information. The agent information includes the agent identifier, the agent version number, and the environment parameters. The agent identifier is determined based on the agent's identity identifier, the agent's name, and the name of the space where the agent is located. The agent's identity identifier and the agent's name are globally unique. The pull request is used to implement the dynamic pull or the static pull.

2. The method according to claim 1, characterized in that, In the first platform, the resources relied upon by the different deployed intelligent agents when providing the dialogue service during the operation phase are independent of each other.

3. The method according to claim 1, characterized in that, The interfaces used by the intelligent agents of the first platform and the second platform to provide the dialogue service are consistent.

4. The method according to claim 1, characterized in that, The method further includes: Collect operational data of the intelligent agent deployed in the first platform during the operational phase; The operational data is uploaded to a third platform, wherein the second platform and the third platform are both provided by the same third party.

5. The method according to claim 4, characterized in that, The operational data is uploaded to the second platform via the third platform or the first platform.

6. A method for developing intelligent agents, characterized in that, Executed by a second platform, including: The intelligent agent is developed to obtain a developed intelligent agent, wherein the development includes configuring the base image of the intelligent agent and the configuration information of the intelligent agent; The first platform is used to respond to an acquisition command, acquire the base image of the corresponding intelligent agent, and deploy the intelligent agent in the first platform based on the base image and the acquired configuration information of the intelligent agent, so that the intelligent agent deployed in the first platform can provide dialogue services during the running phase. The configuration information is obtained through dynamic or static retrieval. Static retrieval means that the intelligent agent is deployed according to the acquired configuration information, and the configuration information does not need to be updated during the running phase of the intelligent agent. Dynamic retrieval means that the intelligent agent provides the dialogue service according to the configuration information acquired or updated in real time during the running phase. The second platform includes multiple spaces, each used to isolate different configuration information of the intelligent agent. The environment corresponding to the second platform includes a production environment or a test environment. The first platform obtains the configuration information by: sending a pull request to each of the second platforms, so that each of the second platforms performs authentication based on the authentication information carried in the pull request, the pull request being used to pull the configuration information of the corresponding intelligent agent; if the authentication is successful, based on the environment parameters carried in the intelligent agent information in the pull request, determining a target second platform that matches the environment parameters from among the multiple second platforms; and pulling the configuration information of the corresponding intelligent agent from the target second platform based on the intelligent agent identifier and version number carried in the intelligent agent information. The agent information includes the agent identifier, the agent version number, and the environment parameters. The agent identifier is determined based on the agent's identity identifier, the agent's name, and the name of the space where the agent is located. The agent's identity identifier and the agent's name are globally unique. The pull request is used to implement the dynamic pull or the static pull.

7. An intelligent agent deployment device, characterized in that, Applied to the first platform, including: The first acquisition module is used to acquire the base image of the corresponding intelligent agent in response to the acquisition command, wherein the base image is constructed by the second platform during the development phase of the intelligent agent; The deployment module is used to deploy the intelligent agent in the first platform based on the base image and the obtained configuration information of the intelligent agent, so that the intelligent agent deployed in the first platform can provide dialogue services during the running phase. The configuration information is configured by the second platform during the development phase of the intelligent agent. The configuration information is obtained through dynamic pulling or static pulling. Static pulling means that the intelligent agent is deployed according to the obtained configuration information, and the configuration information does not need to be updated during the running phase of the intelligent agent. Dynamic pulling means that the intelligent agent provides the dialogue service according to the configuration information obtained or updated in real time during the running phase. The second platform includes multiple spaces, each used to isolate different configuration information of the intelligent agent. Each second platform corresponds to a different environment, including a production environment or a testing environment. The configuration information is obtained by sending a pull request to each second platform, enabling each platform to authenticate based on the authentication information carried in the pull request, which is used to pull the configuration information of the corresponding intelligent agent. If authentication is successful, a target second platform matching the environment parameters is determined from the multiple second platforms based on the environment parameters carried in the intelligent agent information of the pull request. The configuration information of the corresponding intelligent agent is pulled from the target second platform based on the intelligent agent identifier and version number carried in the intelligent agent information. The agent information includes the agent identifier, the agent version number, and the environment parameters. The agent identifier is determined based on the agent's identity identifier, the agent's name, and the name of the space where the agent is located. The agent's identity identifier and the agent's name are globally unique. The pull request is used to implement the dynamic pull or the static pull.

8. An intelligent agent development device, characterized in that, Applications to the second platform include: A development module is used to develop an intelligent agent to obtain a developed intelligent agent, wherein the development includes configuring the base image of the intelligent agent and the configuration information of the intelligent agent; The first platform is used to respond to an acquisition command, acquire the base image of the corresponding intelligent agent, and deploy the intelligent agent in the first platform based on the base image and the acquired configuration information of the intelligent agent, so that the intelligent agent deployed in the first platform can provide dialogue services during the running phase. The configuration information is obtained through dynamic or static retrieval. Static retrieval means that the intelligent agent is deployed according to the acquired configuration information, and the configuration information does not need to be updated during the running phase of the intelligent agent. Dynamic retrieval means that the intelligent agent provides the dialogue service according to the configuration information acquired or updated in real time during the running phase. The second platform includes multiple spaces, each used to isolate different configuration information of the intelligent agent. The environment corresponding to the second platform includes a production environment or a test environment. The first platform obtains the configuration information by: sending a pull request to each of the second platforms, so that each of the second platforms performs authentication based on the authentication information carried in the pull request, the pull request being used to pull the configuration information of the corresponding intelligent agent; if the authentication is successful, based on the environment parameters carried in the intelligent agent information in the pull request, determining a target second platform that matches the environment parameters from among the multiple second platforms; and pulling the configuration information of the corresponding intelligent agent from the target second platform based on the intelligent agent identifier and version number carried in the intelligent agent information. The agent information includes the agent identifier, the agent version number, and the environment parameters. The agent identifier is determined based on the agent's identity identifier, the agent's name, and the name of the space where the agent is located. The agent's identity identifier and the agent's name are globally unique. The pull request is used to implement the dynamic pull or the static pull.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by a processing device, the computer program implements the steps of the method according to any one of claims 1-5, or the steps of the method according to claim 6.

10. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing apparatus for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-5, or the steps of the method according to claim 6.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1-5, or the steps of the method according to claim 6.

Images