Interaction method and device with digital assistant, equipment, storage medium and program product

Abstract

The embodiment of the invention provides an interaction method and device with a digital assistant, equipment, a storage medium and a program product. The method comprises the following steps: receiving first input information input by a first user through a first interactive interface of a first digital assistant; based on the first input information, a target digital assistant for the first input information is determined from a plurality of second digital assistants, and different digital assistants in the plurality of second digital assistants are used for executing different types of tasks; and presenting target response information for the first input information in the first interactive interface, wherein the target response information is obtained at least partially based on processing of the first input information by the target digital assistant. In this way, the target digital assistant for processing the input information can be automatically determined based on the input information of the user. In this way, the cost for the user to understand the digital assistant function and manually select the digital assistant needing to be used is remarkably reduced, and the user experience and convenience are improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to methods, devices, apparatuses, computer-readable storage media, and computer program products for interacting with digital assistants. Background Art

[0002] With the development of information technology, digital assistants such as voice assistants, robots (BOTs), and intelligent agents have been greatly developed and applied. Various types of digital assistants have brought great convenience to users in many aspects. Users can use digital assistants to achieve various functions, such as getting answers to certain questions by asking and answering questions with digital assistants, or quickly processing a business with the help of digital assistants. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for interacting with a digital assistant is provided. The method includes: receiving first input information input by a first user through a first interactive interface of a first digital assistant. Based on the first input information, determining a target digital assistant for the first input information from a plurality of second digital assistants, wherein different digital assistants among the plurality of second digital assistants are used to perform different types of tasks. And presenting target response information for the first input information on the first interactive interface, the target response information being obtained at least in part based on the processing of the first input information by the target digital assistant.

[0004] In a second aspect of the present disclosure, a device for interacting with a digital assistant is provided. The device includes: an information receiving module, configured to receive first input information of a first user through a first interactive interface of a first digital assistant. A target digital assistant determination module, configured to determine a target digital assistant for the first input information from a plurality of second digital assistants based on the first input information, wherein different digital assistants among the plurality of second digital assistants are used to perform different types of tasks. And an information presentation module, configured to present target response information for the first input information on the first interactive interface, wherein the target response information is obtained at least in part based on the processing of the first input information by the target digital assistant.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which includes a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart illustrating an example process for interacting with a digital assistant according to some embodiments of the present disclosure;

[0012] Figure 3 A flowchart illustrating an example process for generating processing results according to some embodiments of the present disclosure;

[0013] Figure 4 A flowchart illustrating an example process for processing target information according to some embodiments of the present disclosure;

[0014] Figure 5 A flowchart of a method of interacting with a digital assistant according to some embodiments of the present disclosure is shown;

[0015] Figure 6 An exemplary structural block diagram of an interactive device with a digital assistant according to some embodiments of the present disclosure is shown; and

[0016] Figure 7 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0019] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0020] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0021] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0022] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0023] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0024] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0025] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0026] As mentioned earlier, various types of digital assistants have been greatly developed and applied. At present, for organizations (for example, enterprises, groups), different digital assistants (such as intelligent agents) are usually built or introduced to form a multi-digital assistant system to help organization members (such as corporate employees, users) handle different businesses or obtain different types of information according to the needs of different departments or different business scenarios. In the process of application, these digital assistants usually need to be fully and effectively utilized due to limited resources, so that they can be distributed to people in need as much as possible. However, due to the large number of digital assistants, organization members need to find the digital assistants they need among multiple digital assistants, which increases the time cost of using digital assistants for organization members and reduces convenience.

[0027] In view of this, according to an embodiment of the present disclosure, an improved scheme for interacting with a digital assistant is provided. According to the scheme of an embodiment of the present disclosure, first input information input by a first user is received through a first interactive interface of a first digital assistant. Based on the first input information, a target digital assistant for the first input information is determined from a plurality of second digital assistants, and different digital assistants among the plurality of second digital assistants are used to perform different types of tasks. And target response information for the first input information is presented on the first interactive interface, and the target response information is obtained at least in part based on the processing of the first input information by the target digital assistant.

[0028] In this way, the target digital assistant for processing the input information can be automatically determined based on the user's input information. In this way, the cost of the user's understanding of the digital assistant function and manually selecting the digital assistant to be used is significantly reduced, greatly improving the user experience and convenience of using the multi-digit digital system.

[0029] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0030] Figure 1A schematic diagram of an example environment 100 in which an embodiment of the present disclosure can be implemented is shown. A system management platform 110 may be included in the example environment 100. The system management platform 110 may be deployed with a first digital assistant 112 and multiple second digital assistants 114, such as a second digital assistant 114-1, a second digital assistant 114-2, and a second digital assistant 114-3 (these digital assistants may be collectively referred to as second digital assistants 114). Although these digital assistants are shown as being deployed on the system management platform 110, it should be understood that in some embodiments some or all of these digital assistants may be deployed at other devices or platforms and may be accessed by the system management platform 110. Users may log in to the system management platform 110 via various terminal devices or client devices to interact with the first digital assistant 112 and / or multiple second digital assistants 114.

[0031] In some embodiments, the first digital assistant 112 is used to interact with the user 140, thereby outputting information to the user 140 and / or receiving information from the user 140. The first digital assistant 112 can determine a target digital assistant for the input information from the plurality of second digital assistants 114 based on the input information of the user 140, thereby invoking the target digital assistant to process the input information of the user 140, and returning target response information to the user 140.

[0032] In some embodiments, multiple different second digital assistants 114 can be configured in the system management platform for an organization or user set using the system management platform 110. Multiple second digital assistants 114 are used to implement different types of functions. For example, the second digital assistant 114-1 is used to handle finance-related issues or business. The second digital assistant 114-2 is used to handle administration-related issues or business. The second digital assistant 114-3 is used to handle IT-related issues or business. It should be understood that the second digital assistants configured for the system management platform 110 can be different or the same for different organizations.

[0033] In some embodiments, at least some of the functions of the system management platform 110 can be implemented based on the target model 120. In the process of the system management platform 110 presenting the response information for the user input information, one or more target models 120 can be called, such as the capabilities of the target model 120. As used herein, the term "model" can learn the association relationship between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for the given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article. In some embodiments, each of the first digital assistant 112 and the plurality of second digital assistants 114 can be configured with one or more processing models or machine learning models. In some embodiments, the system management platform 110 can be configured with a plurality of different public processing models, and the first digital assistant 112 and the plurality of second digital assistants 114 can call different processing models as needed to process the information input by the user.

[0034] In the embodiments of the present disclosure, each second digital assistant can be a digital assistant based on a rule engine, or a digital assistant based on a machine learning model. The first digital assistant and each second digital assistant can have a corresponding machine learning model, or they can share a machine learning model to complete their respective tasks. The machine learning model here can be a large language model (LLM), or it can be an expert model trained using vertical field data.

[0035] The system management platform 110 may be deployed locally on the terminal device of the user 140, and / or may be supported by a server device. For example, the terminal device of the user 140 may run a client of the system management platform, and the client may support the interaction between the user and the system management platform provided by the server. In the case where the system management platform runs locally on the user's terminal device, the user 140 may directly interact with the local system management platform using the terminal device. In the case where the system management platform runs on the server device, the server device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The system management platform 110 may present a corresponding interface 142 to the user 140 based on the operation of the user 140, so as to output information to the user 140 and / or receive information from the user 140.

[0036] The system management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the system management platform 110 can be implemented based on cloud services.

[0037] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0038] Figure 2 A flowchart of an example process 200 for interacting with a digital assistant according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to Figure 1 In the environment 100, the process 200 may be implemented in the system management platform 110, but some operations may be performed by requesting a server device (not shown).

[0039] In some embodiments, the system management platform 110 may present a corresponding interface 142 to the user 140 based on successful authentication of the login information 210 of the user 140. In the interface 142, the system management platform 110 may present to the user 140 the digital assistants that the user 140 can access and use among the first digital assistant 112 and the plurality of second digital assistants 114.

[0040] In some embodiments, the system management platform 110 can determine the second digital assistants 114 that are accessible / usable to the user among the multiple second digital assistants 114 based on the login information of the user 140. In other words, in the embodiments of the present disclosure, different second digital assistants 114 that are accessible and usable can be configured for different users 140. This allows different second digital assistants 114 to be provided to the target users as much as possible, ensuring full utilization of the second digital assistants 114.

[0041] In some embodiments, the system management platform 110 may present the first interactive interface of the first digital assistant 112 to the user 140 based on the login information or preset operation of the user 140. The first interactive interface may be the same as the interface 142, or may be different from the interface 142. The system management platform 110 may receive the first input information 220 input by the user 140 in the first interactive interface through the first digital assistant 112. The first input information 220 may be various information, such as "what to do if the application cannot be accessed", "help me solve the computer freeze", "help me process and analyze data", "what is the attendance system like", etc. The first digital assistant 112 may determine the target digital assistant for the first input information 220 from the plurality of second digital assistants 114 based on the first input information 220. The plurality of second digital assistants 114 may be different types of digital assistants, and may be used to perform different types of functions. For example, digital assistant 1 may be a first type of intelligent agent. Digital assistant 2 may be a second type of intelligent agent. Digital assistant 3 may be a third type of intelligent agent. Digital assistant 4 may be a fourth type of intelligent agent.

[0042] Exemplarily, digital assistants 1-4 can be used to perform processing of administrative, IT, financial and other related information, respectively. For example, digital assistant 1 can perform operations such as question and answer, analysis or query of financial information. Digital assistant 2 can perform operations such as question and answer, analysis or query of administrative information. Digital assistant 3 can perform operations such as question and answer, analysis or query of IT-related information. After determining the target digital assistant, the first digital assistant 112 sends the first input information 220 to the target digital assistant, such as digital assistant 1, so that the target digital assistant performs processing on the first input information 220 to obtain the processing result 230. After the target digital assistant completes the processing of the first input information 220, the processing result 230 is returned to the first digital assistant 112. The first digital assistant 112 generates a target response information 240 for the first input information 220 based at least in part on the processing result 230, and presents the target response information 240 on the first interactive interface.

[0043] In some embodiments, the first digital assistant 112 can use the machine learning model associated with the first digital assistant 112 to determine the type of target task indicated by the first input information 220. Then, the first digital assistant 112 determines the target digital assistant for the first input information 220 from multiple second digital assistants 114 based on the target task type. Exemplarily, the machine learning model associated with the first digital assistant 112 can be a language model (LM). The first digital assistant 112 can use LM to determine the type of task the user wants to perform from the first input information 220. For example, when the first input information is "query the company's cash flow in September and analyze it", the LM model can be used to determine that the task the user wants to perform is of a financial type, so a digital assistant 114 related to finance can be determined from multiple second digital assistants 114 as the target digital assistant.

[0044] In some embodiments, the first digital assistant 112 may determine a candidate digital assistant for the first input information 220 from a plurality of second digital assistants 114 based on the first input information 220. The determination method of the candidate digital assistant may be similar to the determination direction of the aforementioned target digital assistant, which will not be repeated here. Then the candidate digital assistant is used to process the first input information 220 and obtain the processing result 230. The first digital assistant 112 uses a machine learning model (e.g., LM) associated with the first digital assistant 112 to determine whether the processing result 230 matches the first input information 220. In response to the processing result 230 matching the first input information, the first digital assistant 112 may present the target response information 240 generated based on the processing result 230 on the first interactive interface. In response to the processing result 230 not matching the first input information, the first digital assistant 112 may use the machine learning model associated with the first digital assistant 112 to determine a digital assistant different from the candidate digital assistant from a plurality of second digital assistants 114 as the target digital assistant to process the first input information 220.

[0045] In some embodiments, the system management platform 110 may present to the user 140, in the interface 142, a digital assistant accessible and usable by the user 140 from among multiple second digital assistants 114 in response to the login information 210 of the user 140. In response to the user 140's selection of a target digital assistant from the accessible and usable digital assistants, a second interactive interface of the target digital assistant may be presented. The second interactive interface is different from the first interactive interface. The system management platform 110 may receive second input information input by the user 140 through the second interactive interface of the target digital assistant. And the response information obtained by the target digital assistant processing the second input information is presented on the second interactive interface. The second input information may be processed by the target digital assistant calling the corresponding model execution.

[0046] Figure 3 FIG. 3 is a flow chart of an example process 300 for generating processing results according to some embodiments of the present disclosure. Figure 1 In the environment 100, the process 300 may be implemented in the system management platform 110, but some operations may be performed by requesting a service-side device (not shown).

[0047] In some embodiments, the system management platform 110 may present a corresponding interface 142 to the user 140 based on successful authentication of the login information 210 of the user 140. In the interface 142, the system management platform 110 may present to the user 140 a plurality of digital assistants that are accessible and usable by the user 140 from the second digital assistants 114. The system management platform 110 or the first digital assistant 112 may determine the target digital assistant 310 for the first input information 220 from the digital assistants that are accessible and usable by the user 140 based on the first input information 220 input by the user and / or the user's selection operation. The determination process of the target digital assistant 310 is described in conjunction with the foregoing Figure 2 The determination of the target digital assistant in the described process 200 will not be repeated here.

[0048] In some embodiments, the system management platform 110 may verify the login information 210 of the user 140 based on single sign-on (SSO). Single sign-on allows the user 140 to access the system management platform 110 and multiple systems or applications related to the system management platform 110 but independent of each other using a set of login information 210. For example, the system management platform 110 may provide an application to the user 140. After the user 140 logs in to the application, the system management platform 110 may obtain the login information of the user 140.

[0049] In some embodiments, the system management platform 110 can determine the permission information of the user 140 based on the login information 210 of the user 140. The permission information of the user 140 can be associated with the identity, role, etc. of the user. That is, the system management platform 110 can grant different permissions to the user 140 based on the identity, role, etc. of the user. In some embodiments, the system management platform 110 can determine the digital assistants that the user 140 can access and use among the multiple second digital assistants 114 based on the permission information of the user 140. In some embodiments, the system management platform 140 can use the role-based access control permission model (RBAC) to assign permissions to different resources in the system management platform 110 to different users 140. For example, the financial personnel of the organization are given the permission of the digital assistant related to stable processing, and the marketing department personnel of the organization are given the permission of the digital assistant related to data analysis. In this way, the identity of the user 140 accessing the system management platform 110 can be guaranteed to be credible, and different digital assistants, knowledge bases, functional modules and / or data permissions can be assigned to different user roles to ensure the effective use of resources and data security.

[0050] In some embodiments, the target digital assistant 310 can obtain the permission information of the user 140 from the system management platform 110 or the first digital assistant 112, and determine the knowledge base and / or function module that the user 140 can access or have permission to from the knowledge base 320 or the function module 330 based on the permission information. Then, the first input information 220 can be processed using the knowledge base and / or function module that the user 140 can access or have permission to obtain the processing result 230. In some embodiments, the system management platform 110 or the target digital assistant 310 can assign different knowledge base or function module permissions to the user based on the permission information of the user 140. Figure 3 For example, the permission information may indicate that user 140 can use knowledge base 1, but cannot use knowledge base 2 and knowledge base 3. The permission information may also indicate that user 140 can use function module 2, but cannot use function module 1 and function module 3. The target digital assistant 310 may call knowledge base 2 and function module 2 to perform processing on the first input information to obtain the processing result 230.

[0051] In some embodiments, the knowledge base 320 may be a knowledge base configured for the target digital assistant 310, or a knowledge base accessible to the target digital assistant 310. The functional module 330 may be a functional module configured for the target digital assistant 310, or a functional module accessible to the target digital assistant 310. In some embodiments, the knowledge base may be a knowledge base associated with the system management platform 110 and / or the operation of the organization, such as an operation and maintenance manual, system information, management methods, business descriptions, development experience, market guides, etc. Different knowledge base permissions may be assigned to different permissions of different users 140. For example, knowledge base permissions for operation and maintenance manuals, system information, management methods, etc. may be assigned to IT users. Knowledge base permissions for business descriptions, development experience, market guides, etc. may be assigned to market personnel. Functional modules may be configured or accessible for various functional plug-ins for the system management platform 110, such as plug-ins for customer relationship management systems (CRM), office automation systems (OA), IT service management systems (ITSM), enterprise resource planning systems (ERP), and human resources systems (HR).

[0052] In some embodiments, the target digital assistant 310 may obtain the permission information of the user 140 from the system management platform 110 or the first digital assistant 112, and determine the data and / or database that the user 140 can access or have permission to in or associated with the knowledge base 320 and / or the function module 330 based on the permission information. Then, the first input information 220 may be processed using the data and / or database that the user 140 can access or have permission to obtain the processing result 230. Figure 3 For example, the permission information of user 140 indicates that user 140 can use data 1 in function module 2, but cannot use data 2 in function module 2. Therefore, the target digital assistant 310 can process the first input information 220 based on data 1 in function module 2 to obtain the processing result 230.

[0053] In some embodiments, the target digital assistant 230 can call the target model 120 associated with the target digital assistant 310 to perform processing on the first input information 220.

[0054] Figure 4 FIG. 4 is a flow chart of an example process 400 for processing target information according to some embodiments of the present disclosure. Figure 1 In the environment 100, the process 400 may be implemented in the system management platform 110, but some operations may be performed by requesting a service-side device (not shown).

[0055] In some embodiments, for the sake of data security, the system management platform 110 can identify the target information of the processing result 230 to determine whether the target information exists in the processing result. Exemplarily, after the first digital assistant 112 obtains the processing result 230, the first digital assistant 112 can call the target information identification engine 410 to identify the processing result to determine whether the target information exists in the processing result 230. In some embodiments, the target information can be information of a predetermined type or information including predetermined attribute data, such as an organization's internal information, research and development data, etc. Alternatively or additionally, in some embodiments, the target information can be information associated with the permission information of the user 140, such as data within the organization that the user 140 does not have permission to access.

[0056] In some embodiments, the target information identification engine 410 may include a built-in data identification template. The target information identification engine 410 may determine sensitive text content within the organization through the built-in data identification and classification template, and determine sensitive text information and data classification and classification based on this.

[0057] In some embodiments, the target information identification engine 410 may configure a blocking strategy for the target information. For example, when the target information of an organization is included in the processing result 230, the risk may be avoided by prohibiting the sending of the information.

[0058] In some embodiments, the system management platform 110 may present the processing result 230 as target response information 240 in the first interactive interface of the first digital assistant 112 in response to the recognition result 240 indicating that the target information is not recognized in the processing result 230. In some embodiments, the system management platform 110 may update the processing result 230 based on the blocking strategy in response to the recognition result 240 indicating that the target information is recognized in the processing result 230, and present the updated processing result as target response information 240 in the first interactive interface.

[0059] It should be understood that the blocking strategy can be uniformly configured based on the organization members, or different blocking strategies can be configured according to different member permissions.

[0060] The blocking strategy may include various appropriate strategies. In some embodiments, the blocking strategy may include a replacement strategy. In this case, the system management platform 110 may replace the processing result 230 with preset information, thereby updating the processing result 230. Exemplarily, the preset information may inform the user 140 that the processing result contains inaccessible content and cannot be presented. For example, the system management platform 110 may replace the processing result 230 with "the processing result contains special information and cannot be displayed" as the target response information 240. In some embodiments, the blocking strategy may include a removal strategy. In this case, the system management platform 110 may remove the target information from the processing result 230, thereby updating the processing result 230. That is, in this case, information other than the target information in the processing result 230 may be presented to the user 140. In some embodiments, the blocking strategy may include a mask strategy. The system management platform 110 may apply a mask to the target information, thereby updating the processing result 230. For example, the target information in the processing result 230 may be replaced with a preset symbol, etc.

[0061] Today, when artificial intelligence technology is enabling all kinds of business applications, in the work systems of various organizations such as enterprises, government agencies, and teams, there will be digital assistants to complete various types of tasks. Users in the organization need to choose the corresponding digital assistants according to their own task types to assist in completing tasks. When the number of digital assistants increases, it is also a cumbersome task to correctly select the digital assistant corresponding to the task. In addition, different digital assistants in an organization may have different open scopes to members within the organization, so there is an urgent need to manage and control the use rights of digital assistants within the organization. The solution disclosed in the present invention solves the above problems well by using the first digital assistant as the unified entrance.

[0062] Figure 5 FIG. 5 is a flow chart showing an interaction process 500 with a digital assistant according to some embodiments of the present disclosure. For ease of discussion, reference will be made to FIG. Figure 1 Process 500 is described with reference to environment 100 of FIG. 500 . Process 500 may be implemented at system management platform 110 .

[0063] In box 510, the system management platform 110 receives first input information input by a first user through a first interactive interface of a first digital assistant.

[0064] In box 520, the system management platform 110 determines a target digital assistant for the first input information from a plurality of second digital assistants based on the first input information, and different digital assistants among the plurality of second digital assistants are used to perform different types of tasks.

[0065] In some embodiments, the system management platform 110 determines a target digital assistant for the first input information from the plurality of second digital assistants 114, including: using a machine learning model associated with the first digital assistant 112, determining the type of target task indicated by the first input information. And based on the type of the target task, determining the target digital assistant from at least one second digital assistant in the plurality of second digital assistants 114. The at least one second digital assistant is at least one second digital assistant in the plurality of second digital assistants 114 that is accessible and usable by the user 140.

[0066] In box 530, the system management platform 110 presents target response information for the first input information on the first interactive interface, and the target response information is obtained at least in part based on the processing of the first input information by the target digital assistant.

[0067] In some embodiments, the target response information is determined by: obtaining a processing result for the first input information provided by the target digital assistant; and using the first digital assistant to generate the target response information based on the processing result.

[0068] In some embodiments, determining a target digital assistant for first input information from multiple second digital assistants includes: obtaining a processing result for the first input information provided by a candidate digital assistant among the multiple second digital assistants; and in response to the processing result not matching the first input information or the processing result indicating a processing failure, using a machine learning model associated with the first digital assistant, determining a digital assistant among the multiple second digital assistants that is different from the candidate digital assistant as a target digital assistant.

[0069] In some embodiments, presenting target response information for first input information in a first interaction interface includes: identifying the target information in a processing result for the first input information provided by a target digital assistant; and in response to failure to identify the target information, presenting the processing result as target response information in the first interaction interface.

[0070] In some embodiments, process 500 further includes updating a processing result based on a configured blocking strategy in response to identifying the target information; and presenting the updated processing result as target response information in the first interactive interface.

[0071] In some embodiments, updating the processing result includes one of: replacing the processing result with preset information, the preset information indicating that the processing result contains the target information and cannot be presented, removing the target information from the processing result, or applying a mask to the target information.

[0072] In some embodiments, determining a target digital assistant for the first input information from a plurality of second digital assistants includes: determining permission information of the first user based on login information of the first user. Based on the permission information, determining at least one second digital assistant accessible to the first user from a plurality of second digital assistants. And determining the target digital assistant from at least one second digital assistant based on the first input information.

[0073] In some embodiments, process 500 also includes providing permission information to the target digital assistant so that the target digital assistant determines a knowledge base or functional module accessible to the first user based on the permission information.

[0074] In some embodiments, process 500 further includes receiving second input information input by the first user through a second interactive interface of the target digital assistant, and presenting response information obtained by the target digital assistant processing the second input information on the second interactive interface.

[0075] In summary, according to the embodiments of the present disclosure. The target digital assistant for processing the input information can be automatically determined based on the user's input information. In this way, the digital assistant interaction portals created by the organization through different platforms can be unified into one portal, and the intelligent scheduling of the digital assistant can be completed through the unified portal. This makes it possible to support users to use the unified portal as the only digital assistant interaction portal without affecting the reply effect of the intelligent body. And no matter what the problem is, you can consult the digital assistant through the unified portal to get replies and more accurate solutions from different digital assistants. Therefore, the embodiments of the present disclosure significantly reduce the cost of users understanding the functions of digital assistants and manually selecting the digital assistants they need to use, and greatly improve the user experience and convenience of using multi-digital digital systems. In addition, the embodiments of the present disclosure also support the hierarchical classification of custom target information, and ensure the security and compliance of the output information of the digital assistant by identifying the defined target information and blocking the sending of target information.

[0076] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 6 An exemplary structural block diagram of an interactive device 600 with a digital assistant according to some embodiments of the present disclosure is shown. The device 600 may be implemented as or included in the client device 110 and / or the server device 120. Each module / component in the device 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0077] like Figure 6As shown, the device 600 includes an information receiving module 610, which is configured to receive first input information of a first user through a first interactive interface of a first digital assistant. A target digital assistant determination module 620 is configured to determine a target digital assistant for the first input information from a plurality of second digital assistants based on the first input information, and different digital assistants among the plurality of second digital assistants are used to perform different types of tasks. An information presentation module 630 is configured to initiate a business request associated with a target business in response to selection of a business portal, at least based on the first identification result.

[0078] In some embodiments, the target digital assistant determination module 620 is further configured to: determine the type of the target task indicated by the first input information using a machine learning model associated with the first digital assistant. And based on the type of the target task, determine the target digital assistant from at least one second digital assistant among the plurality of second digital assistants. The at least one second digital assistant is at least one second digital assistant that is accessible and usable by the user among the plurality of second digital assistants.

[0079] In some embodiments, the target response information is determined by: obtaining a processing result for the first input information provided by the target digital assistant; and using the first digital assistant to generate the target response information based on the processing result.

[0080] In some embodiments, the target digital assistant determination module 620 is also configured to: obtain a processing result for the first input information provided by a candidate digital assistant among multiple second digital assistants; and in response to the processing result not matching the first input information or the processing result indicating a processing failure, using a machine learning model associated with the first digital assistant, determine a digital assistant among the multiple second digital assistants that is different from the candidate digital assistant as a target digital assistant.

[0081] In some embodiments, the information presentation module 630 is further configured to: identify target information in the processing results for the first input information provided by the target digital assistant; and in response to failure to identify the target information, present the processing results as target response information in the first interaction interface.

[0082] In some embodiments, the information presentation module 630 is further configured to: in response to identifying the target information, update the processing result based on the configured blocking strategy; and present the updated processing result as target response information in the first interactive interface.

[0083] In some embodiments, the information presentation module 630 is further configured to replace the processing result with preset information, the preset information indicating that the processing result contains the target information and cannot be presented, remove the target information from the processing result, or apply a mask to the target information.

[0084] In some embodiments, the target digital assistant determination module 620 is further configured to: determine the permission information of the first user based on the login information of the first user. Based on the permission information, determine at least one second digital assistant accessible to the first user from multiple second digital assistants. And based on the first input information, determine the target digital assistant from at least one second digital assistant.

[0085] In some embodiments, the device 600 also includes an information transmission module configured to provide permission information to the target digital assistant so that the target digital assistant determines the knowledge base or functional module accessible to the first user based on the permission information.

[0086] In some embodiments, the information receiving module 610 is further configured to receive second input information input by the first user through the second interactive interface of the target digital assistant. The information presenting module 630 is further configured to present response information obtained by the target digital assistant processing the second input information on the second interactive interface.

[0087] The units and / or modules included in the device 600 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 600 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary 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), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0088] It should be understood that one or more steps in the above method can be performed by a suitable electronic device or a combination of electronic devices. Such an electronic device or a combination of electronic devices may include, for example, a computer that runs Figure 1 The system manages the devices of the platform 110.

[0089] Figure 7 1 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown may include or be implemented as Figure 1 System management platform 110 or Figure 6 Device 600.

[0090] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.

[0091] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 700.

[0092] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0093] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0094] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0095] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0096] According to an exemplary implementation of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 5 The methods provided in the various optional methods are therefore not described in detail here.

[0097] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0098] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0099] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0100] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0101] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for interacting with a digital assistant, comprising: Receiving first input information input by a first user through a first interactive interface of a first digital assistant; Based on the first input information, determining a target digital assistant for the first input information from a plurality of second digital assistants, wherein different digital assistants among the plurality of second digital assistants are used to perform different types of tasks; as well as Target response information for the first input information is presented on the first interactive interface, and the target response information is obtained at least in part based on processing of the first input information by the target digital assistant.

2. The method of claim 1, wherein determining a target digital assistant for the first input information from a plurality of second digital assistants comprises: Determine, using a machine learning model associated with the first digital assistant, a type of target task indicated by the first input information; as well as Based on the type of the target task, the target digital assistant is determined from at least one second digital assistant among the multiple second digital assistants.

3. The method according to claim 1, wherein the target response information is determined by: Obtaining a processing result for the first input information provided by the target digital assistant; and Utilizing the first digital assistant, the target response information is generated based on the processing result.

4. The method of claim 1, wherein determining a target digital assistant for the first input information from a plurality of second digital assistants comprises: Obtaining a processing result for the first input information provided by a candidate digital assistant among the plurality of second digital assistants; as well as In response to the processing result not matching the first input information or the processing result indicating a processing failure, a digital assistant among the multiple second digital assistants that is different from the candidate digital assistant is determined as the target digital assistant using a machine learning model associated with the first digital assistant.

5. The method according to claim 1, wherein presenting target response information for the first input information on the first interactive interface comprises: Identifying target information in a processing result for the first input information provided by the target digital assistant; as well as In response to the target information not being identified, presenting the processing result in the first interactive interface as the target response information.

6. The method according to claim 5, further comprising: In response to identifying the target information, updating the processing result based on the configured blocking strategy; as well as The updated processing result is presented in the first interactive interface as the target response information.

7. The method according to claim 6, wherein updating the processing result comprises one of the following: replacing the processing result with preset information, wherein the preset information indicates that the processing result contains the target information and cannot be presented, remove the target information from the processing result, or A mask is applied to the target information.

8. The method of claim 1, wherein determining a target digital assistant for the first input information from a plurality of second digital assistants comprises: Determining permission information of the first user based on the login information of the first user; Based on the permission information, determining at least one second digital assistant accessible to the first user from among the plurality of second digital assistants; as well as Based on the first input information, the target digital assistant is determined from the at least one second digital assistant.

9. The method according to claim 8, further comprising: The permission information is provided to the target digital assistant so that the target digital assistant determines the knowledge base or functional module accessible to the first user based on the permission information.

10. The method according to claim 1, further comprising: Receiving second input information input by the first user through the second interactive interface of the target digital assistant; as well as The response information obtained by the target digital assistant processing the second input information is presented on the second interactive interface.

11. An interactive device with a digital assistant, comprising: An information receiving module, configured to receive first input information of a first user through a first interactive interface of a first digital assistant; a target digital assistant determining module, configured to determine a target digital assistant for the first input information from a plurality of second digital assistants based on the first input information, wherein different digital assistants among the plurality of second digital assistants are used to perform different types of tasks; as well as The information presentation module is configured to present target response information for the first input information on the first interactive interface, and the target response information is at least partially obtained based on the processing of the first input information by the target digital assistant.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product, comprising a computer program, wherein the computer program implements the method according to any one of claims 1 to 10 when executed by a processor.

Images