Method, device and equipment for digital assistant interaction and storage medium

Abstract

The embodiment of the invention provides a digital assistant interaction method and device, equipment and a storage medium. The method comprises the following steps: based on storage configuration of a digital assistant, determining whether interaction information between a user and the digital assistant comprises or depends on information of a first type indicated by the storage configuration; if it is determined that the interaction information comprises the information of the first type and the information of the first type is not stored, the information of the first type is written into a storage area corresponding to the first type; if it is determined that the interaction information depends on the information of the first type and the information of the first type is stored, reading the stored information of the first type from a storage area corresponding to the first type; and determining a reply of the digital assistant to the user based on the stored or read information of the first type.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for digital assistant interaction. Background Art

[0002] Digital assistants are provided to assist users with various task processing needs in different applications and scenarios. Digital assistants usually have intelligent dialogue and task processing capabilities. In the process of interaction with the digital assistant, the user inputs an interactive message, and the digital assistant provides a reply message in response to the user input. Generally, a digital assistant can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability. This kind of interaction method has become a tool that people love and rely on because of its flexible and convenient characteristics. In the interaction between users and digital assistants, more improved solutions are expected. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for digital assistant interaction is provided. The method includes: based on the storage configuration of the digital assistant, determining whether the interaction information between the user and the digital assistant includes or depends on the first type of information indicated by the storage configuration; if it is determined that the interaction information includes the first type of information and the first type of information is not stored, writing the first type of information into the storage area corresponding to the first type; if it is determined that the interaction information depends on the first type of information and the first type of information has been stored, reading the stored first type of information from the storage area corresponding to the first type; and determining the digital assistant's reply to the user based on the stored or read first type of information.

[0004] In the second aspect of the present disclosure, a device for digital assistant interaction is provided. The device includes: an information determination module, configured to determine whether the interaction information between the user and the digital assistant includes or depends on the first type of information indicated by the storage configuration based on the storage configuration of the digital assistant; an information writing module, configured to write the first type of information into the storage area corresponding to the first type if it is determined that the interaction information includes the first type of information and the first type of information is not stored; an information reading module, configured to read the stored first type of information from the storage area corresponding to the first type if it is determined that the interaction information depends on the first type of information and the first type of information has been stored; and a reply determination module, configured to determine the digital assistant's reply to the user based on the stored or read first type of information.

[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] 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

[0008] 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:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 An example flow chart for digital assistant interaction according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic diagram showing a storage configuration for creating a digital assistant according to some embodiments of the present disclosure is shown;

[0012] Figure 4 An example of an interactive interface between a user and a digital assistant according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A flowchart showing a process for digital assistant interaction according to some embodiments of the present disclosure is shown;

[0014] Figure 6 A block diagram showing an apparatus for digital assistant interaction according to some embodiments of the present disclosure; and

[0015] 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

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] Digital assistants can be used as tools for people to work, study, and live effectively. Generally, the development of digital assistants is similar to the development of general applications. Developers with programming skills need to define the various capabilities of digital assistants by writing complex codes and deploying digital assistants on appropriate operating platforms so that users can download, install, and use digital assistants. With the diversification of application scenarios and the increasing availability of machine learning technology, digital assistants with different capabilities have been developed to support task processing in various segments or to meet the personalized needs of different users.

[0026] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 involves an assistant creation platform 110 and an assistant application platform 130.

[0027] like Figure 1 As shown, the assistant creation platform 110 can provide a digital assistant creation and publishing environment for the user 105. In some embodiments, the assistant creation platform 110 can be a low-code platform that provides a collection of tools for digital assistant creation. The assistant creation platform 110 can support the visual development of digital assistants, so that developers can skip the manual coding process and speed up the development cycle and cost of applications. The assistant creation platform 110 can support any appropriate platform for users to develop digital assistants and other types of applications, for example, it may include a platform based on application platform as a service (aPaaS). Such a platform can support users to efficiently develop applications and realize operations such as application creation and application function adjustment.

[0028] The assistant creation platform 110 can be deployed locally on the terminal device of the user 105, and / or can be supported by a remote server. For example, the terminal device of the user 105 can run a client of the assistant creation platform 110, which can support the interaction between the user and the assistant creation platform 110. In the case where the assistant creation platform 110 runs locally on the user's terminal device, the user 105 can directly use the client to interact with the local assistant creation platform 110. In the case where the assistant creation platform 110 runs on a server-side device, the server-side device can, based on the communication connection with the terminal device, realize the supply of services to the client running in the terminal device. The assistant creation platform 110 can present a corresponding page 122 to the user 105 based on the operation of the user 105, so as to output and / or receive information to the user 105.

[0029] In some embodiments, the assistant creation platform 110 can be associated with a corresponding database, which stores the data or information required for the digital assistant creation process supported by the assistant creation platform 110. For example, the database can store the code and description information corresponding to each functional module that constitutes the digital assistant. The assistant creation platform 110 can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where a digital assistant is to be created, the assistant creation platform 110 can call the corresponding functional blocks from the database to build a digital assistant.

[0030] In an embodiment of the present disclosure, a user 105 can create a digital assistant 120 as needed on an assistant creation platform 110 and publish the digital assistant 120. The digital assistant 120 can be published to any appropriate assistant application platform 130, as long as the assistant application platform 130 can support the operation of the digital assistant 120. After publishing, the digital assistant 120 can be used for dialogue interaction with the user 135. The client of the assistant application platform 130 can present an interactive window 132 of the digital assistant 120, such as a conversation window, in the client interface. As an intelligent assistant, the digital assistant 120 has intelligent dialogue and information processing capabilities. The user 135 can enter a conversation message in the conversation window, and the digital assistant 120 can determine the reply message based on the created configuration information and present it to the user in the interactive window 132. In some embodiments, depending on the configuration of the digital assistant 120, the interactive message with the digital assistant 120 may include messages in multimodal form, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0031] In this article, the user 105 who creates the digital assistant is sometimes also referred to as the assistant creator, assistant developer, etc. The user 135 who interacts with the created digital assistant is sometimes also referred to as the user, user, etc. of the digital assistant.

[0032] The assistant creation platform 110 and / or the assistant application platform 130 can run on appropriate electronic devices. The electronic device here can be any type of device with computing power, 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 assistant creation platform 110 and / or the assistant application platform 130 can be implemented based on cloud services.

[0033] The digital assistant creation process involved in the embodiments of the present disclosure can be implemented on an assistant creation platform, a terminal device installed with the assistant creation platform, and / or a server corresponding to the assistant creation platform. In the following examples, for the purpose of discussion, the description is from the perspective of the assistant creation platform, for example Figure 1 The assistant creation platform 110 shown. The page presented by the assistant creation platform 110 can be presented via the terminal device of the user 105, and the user input can be received via the terminal device of the user 105.

[0034] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Figure 1 A single user interacting with the assistant creation platform 110 and a single user interacting with the assistant application platform 130 are shown, but in fact multiple users can access the assistant creation platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0035] Usually, during the interaction between users and digital assistants, due to the limitations of model input length and other reasons, digital assistants can only extract limited contextual information from historical interactions to understand user input. However, for users interacting with digital assistants, they may expect digital assistants to retain long-term memory of certain information so that they can continue to provide more targeted responses. If the digital assistant needs to repeatedly ask for this information during the interaction with the digital assistant, it will cause a decline in user experience.

[0036] According to an embodiment of the present disclosure, an improved scheme for creating a digital assistant is provided. According to the scheme, the digital assistant has a persistent storage configuration to indicate one or more types of information. In the interaction between the user and the digital assistant, it is determined whether the interaction information includes or depends on a certain type of information indicated by the persistent storage configuration. If it is determined that the interaction information includes a certain type of information and the information of this type has not been stored, the information of this type is stored in a storage area corresponding to the type. If it is determined that the interaction information depends on the first type of information and the first type of information has been stored, the stored information of the first type is read from the storage area corresponding to the first type. The digital assistant's reply to the user is determined based on the stored or read first type of information.

[0037] Thus, during the interaction between the user and the digital assistant, specific types of information can be read and stored so that these types of information can be continuously used as interaction context to determine the user's response during the interaction between the digital assistant and the user. In this way, from the perspective of the interactive user of the digital assistant, the digital assistant can always remember certain key information, thereby obtaining a good interaction experience. This improves the accuracy and pertinence of the digital assistant's response and enhances the interaction experience.

[0038] Some example embodiments of the present disclosure will be described in detail below with reference to the examples of the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are only examples, and various page designs may actually exist. The various graphical elements in the page may have different arrangements and different visual representations, one or more elements may be omitted or updated, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect.

[0039] Figure 2 An example process 200 for digital assistant interaction according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to Figure 1process 200 is described in the context of an environment. Process 200 involves the application stage of the digital assistant 120 after creation, and can therefore be implemented on the assistant application platform 130. It should be understood that the operations described below regarding the assistant application platform 130 and / or the digital assistant 120 may specifically be performed by a terminal device and / or server running the assistant application platform 130 and / or the digital assistant 120, or may be understood to be performed with the aid of an application corresponding to the application assistant platform 130 and / or the digital assistant 120.

[0040] Digital assistant 120 is used to interact with a user (e.g., user 135). Figure 2 As shown, during the interaction between the user 135 and the digital assistant 120, the assistant application platform 130 can determine, based on the storage configuration 212 of the digital assistant 120, whether the interaction information 210 between the user 135 and the digital assistant 120 includes or depends on one or more types of information indicated by the persistent storage configuration. The persistent storage configuration indicates one or more types of information to be stored for the digital assistant 120, and can include a definition of one or more types of information to be stored for the digital assistant 120. During the interaction between the user 135 and the digital assistant 120, according to the storage configuration 212, the digital assistant 120 will store, update and / or query and read the indicated one or more types of information, and interact with the user 135 based on these types of information to determine a reply to the user.

[0041] In some embodiments, the digital assistant 120 will use a model to help perform interactions with the user. The digital assistant 120 will use the model to understand the user input and provide a response to the user based on the output of the model. The model used by the digital assistant 120 can be run locally on the assistant creation platform 110 or on a remote server. In some embodiments, the model can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). The language model can have question-and-answer capabilities by learning from a large amount of corpus. The model can also be based on other appropriate models.

[0042] During the interaction between the user and the digital assistant 120, the digital assistant will extract limited contextual information from the historical interaction to understand the user input at most due to reasons such as the length of the model input. However, for users interacting with the digital assistant, they may expect the digital assistant to be able to keep long-term memory of certain information, so that they can continue to provide more targeted replies. If the digital assistant needs to repeatedly ask for this information during the interaction with the digital assistant, it will cause a decline in user experience. Therefore, in an embodiment of the present disclosure, the digital assistant 120 will be configured with at least one type of information to be stored. Through this storage configuration, at least one type of information defined will be automatically extracted and stored in the interaction between the digital assistant 120 and the user for subsequent interactions. If the user updates a certain type of information during the interaction, the previously stored information of that type will be overwritten or updated. These defined types of information will be stored for a long time for specific users interacting with the digital assistant 120. Such a storage configuration for the digital assistant is also referred to as a persistent storage configuration. In this way, from the perspective of the interactive user of the digital assistant 120, the digital assistant 120 can always remember certain key information, thereby obtaining a good interactive experience.

[0043] Figure 3 A schematic diagram of creating a storage configuration 300 for a digital assistant 120 according to some embodiments of the present disclosure is shown. Figure 3 The interface 300 can be understood as a part of the creation page of the digital assistant 120. In the interface 300, the creator of the digital assistant 120 can configure the storage configuration of the digital assistant 120. The creator of the digital assistant 120 can add the type name and description of the information to be stored in the interface 300. Figure 3 In the example, suppose the configured type is "diet taste", which is to record the user's preference for food. In addition, the creator can also delete a type of information that has been added by deleting control 310, or add more types of information by adding control 302. In some embodiments, the storage configuration can define the type of information to be stored in a one-to-one form of key-value pairs (key-value), and the "key" information indicates the type to be stored, and the "value" indicates the specific information under the type. In some embodiments, more and more complex structured data can also be defined in the storage configuration. For example, a one-to-many data structure can be defined so that a certain type stores multiple information values. Alternatively, a many-to-many data structure can be defined so that multiple types store multiple information values. The format of the information to be stored for a long time is not specifically limited here.

[0044] In addition to the storage configuration 212 of the digital assistant 120 being defined by the creator of the digital assistant 120 at the creation stage, in some embodiments, the storage configuration 212 of the digital assistant 120 can optionally be customized at the application stage between the user 135 and the digital assistant 120. The embodiments of the present disclosure are not limited to this.

[0045] After the storage configuration 212 of the digital assistant 120 is defined, as mentioned above, during the interaction between the digital assistant 120 and the user 135, it can be determined whether the interaction information 210 of each interaction includes or depends on one or more types of information indicated by the storage configuration 212. Here, the interaction information 210 to be used for judgment may include one or more conversation messages (also referred to as "user queries") input by the user 135 to the digital assistant 120, and / or one or more rounds of conversation messages including the user 135 and the digital assistant 120. The digital assistant 120 has the ability to extract interaction information in combination with the conversation context.

[0046] In some embodiments, it may be determined whether part or all of the information in the interaction information 210 can match the name of one or more types indicated by the storage configuration 212. For example, the name of one or more types indicated by the storage configuration 212 may be defined as a “keyword”, and then by matching the keyword of the interaction information 210, it is determined whether the interaction information 210 can match the name of one or more types indicated by the storage configuration 212.

[0047] The interaction information 210 includes one or more types of information indicated by the storage configuration 212, which means that the interaction information 210 provides specific information of one or more types. For example, if the storage configuration indicates that the user's "food taste" type of information is to be stored, then when the user's interaction information provides information such as "I like to eat hot pot", it means that the interaction information includes the "food taste" type of information indicated by the configuration information.

[0048] The interaction information 210 depends on one or more types of information indicated by the storage configuration 212, which means that further responses to the interaction information 210 need to be determined based on one or more types of stored information. For example, if the interaction information input by the user is "please recommend some restaurants to me", then when determining the response to the user, the digital assistant may need to use information related to the user's "food taste" in order to provide the user with a more accurate response.

[0049] If it is determined that the interaction information 210 includes the first type of information and the first type of information has not been stored, the assistant application platform 130 writes the first type of information into the storage area corresponding to the first type. If it is determined that the interaction information 210 depends on the first type of information and the first type of information has been stored, the stored first type of information is read from the storage area corresponding to the first type.

[0050] Reference Figure 2 ,exist Figure 2 In the example, one or more types of information indicated by the storage configuration may be stored in the storage device 230, and each type of information is allocated a corresponding storage area 232 in the storage device 230 for storing information of each type. Figure 2 As shown, different storage areas 232 are respectively used to store information 1 corresponding to type 1, information corresponding to type 2, and finally information N corresponding to type N. Depending on the specific interaction situation between the user 135 and the digital assistant 120, one or more types of information indicated by the storage configuration 212 may have been stored (for example, for type 1 and type N), or may not have been stored (for example, for type 2).

[0051] The storage device 230 may be any type of device capable of storing data in a long-term and persistent manner. The storage device 230 may be any appropriate data repository or storage system, such as a remote dictionary server (Remote Dictionary Server, Redis), etc. The embodiments of the present disclosure do not limit the specific type of the storage device 230.

[0052] In some embodiments, the digital assistant 120 can use the model to determine whether the interaction information 210 includes or depends on one or more types of information indicated by the storage configuration 212. Specifically, a prompt input for the model can be constructed based on the storage configuration 212 and the interaction information 210. The prompt input is used to guide the model to determine whether the interaction information 210 hits one or more types indicated by the storage configuration 212. The prompt input may, for example, include a system prompt for the model. The prompt input will be provided to the model to obtain the output of the model. The output of the model indicates whether the interaction information 210 includes or depends on one or more types of information indicated by the persistent storage configuration.

[0053] In some embodiments, the digital assistant 120 may also be registered with a corresponding plug-in to perform writing and reading of various types of information indicated by the storage configuration 212. In this article, the plug-in is named "read-write plug-in" 220. The read-write plug-in 220 may be configured with corresponding tools (or functions) for implementing the writing and reading of various types of information indicated by the storage configuration 212. In some embodiments, in addition to the storage configuration 212 of the digital assistant and the current interaction information 210, a prompt word input for the model may also be constructed based on the description 214 of the read-write plug-in. In this way, the prompt word input can guide the model to write one or some types of information mentioned in the interaction information 210 into the corresponding storage area, or read from the corresponding storage area.

[0054] In some embodiments, the read-write plug-in 220 can be configured as one or more functions to implement writing and reading of information. Figure 2 2 shows example functions that can be called by the read-write plug-in 220. For example, the setMemory function 222 can be configured to set (write) a specific type of information, the getMemory function 224 can be configured to obtain (read) a specific type of information, the appendMemory function 226 can be configured to write one-to-many type information, the listMemory function 228 can be configured to write many-to-many type information, and so on. Note that only some example functions are given here. In actual applications, different functions can be set for the read-write plug-in 220 as needed to realize the reading and writing of information of different data structures.

[0055] In some embodiments, the description 214 of the read-write plug-in includes a description of the read-write tasks that the read-write plug-in can implement, the tools or functions included in the read-write plug-in (e.g. Figure 2 In some embodiments, the description 214 of the read-write plug-in may be provided for constructing the prompt word input of the model. Such construction of the prompt word input may be defined in the creation phase of the digital assistant, or may also be defined in the application phase of the digital assistant.

[0056] Thus, by calling the read-write plug-in 220 of the digital assistant 120, one or more types of information indicated in the storage configuration 212 can be written into the corresponding storage area. Alternatively, by calling the read-write plug-in 220 of the digital assistant 120, one or more types of information stored can be read from the corresponding storage area.

[0057] Further, the digital assistant 120 determines a reply to the user 135 based on the stored or read first type of information. Figure 2 In the embodiment of the present invention, if it is determined that the interaction information 210 includes information of the first type, the digital assistant 120 can (for example, with the help of the read-write plug-in 220) extract the information corresponding to the first type from the interaction information 210, and write the extracted information to the storage area 232 corresponding to the persistent storage device 230. Further, the digital assistant 120 can also determine the digital assistant's reply 240 to the user 135 based on the information of the first type. If it is determined that the interaction information 210 depends on the information of the first type, the digital assistant 120 can (for example, with the help of the read-write plug-in 220) read the information 242 corresponding to the first type from the storage area 232 corresponding to the persistent storage device 230. Further, the digital assistant 120 can also determine the digital assistant's reply 245 to the user 135 based on the information of the first type.

[0058] Figure 4 An example of an interaction interface 400 between a user 135 and a digital assistant 120 according to some embodiments of the present disclosure is shown. In this example, it is assumed that the digital assistant 120 can be invoked to interact with the user in a message interaction application. By selecting the digital assistant 120 in the contact area 420, a conversation window 410 corresponding to the digital assistant 120 can be presented. The user can enter a conversation message in the conversation window 410, and can view the reply of the digital assistant 120 in the conversation window 410.

[0059] exist Figure 4 In the example, it is assumed that the persistent storage configuration of the digital assistant 120 indicates at least the type "food taste". In the interaction between the user and the digital assistant 120, the user enters a conversation message 430, which matches the type of "food taste" in the persistent storage configuration. In this way, the information "hot pot" corresponding to the type can be extracted from the conversation message 430 and stored in the storage area of ​​the persistent storage device 230. In addition, in this interaction, the digital assistant 120 will also determine the reply message 432 to the user based on the stored information.

[0060] In subsequent interactions, the information "hot pot" corresponding to this type is always recorded and can be read and used by the digital assistant 120 at any time, and will not be forgotten as the interaction passes too long. In a subsequent interaction, the user continues to input a conversation message 434, which matches the previously stored type of "food taste" in the persistent storage configuration. At this time, since the information "hot pot" corresponding to this type has been stored previously, the digital assistant 120 can read the information of this type from the corresponding storage area, and determine the reply message 436 to the user based on this information.

[0061] In some embodiments, if a certain type of information in the persistent storage configuration is provided again in the interaction between the user 135 and the digital assistant 120, the previously stored information of that type may be updated. For example, if it is determined that the interaction information between the user 135 and the digital assistant 120 includes information of the first type, but the stored information of the first type is different from the information in the current interaction information, the stored information may be updated with the information of the first type included in the interaction information 210. Thus, as the interaction proceeds, the latest information provided by the user 135 may be continuously updated and recorded to implement the interaction of the digital assistant.

[0062] In some embodiments, if it is determined that the interaction information 210 depends on the first type of information and the first type of information is not stored, prompt information is provided to the user 135 to prompt the user 135 to provide the first type of information. In this way, the user can be prompted to actively provide the required information to improve the accuracy of the interaction. Figure 4 In the interaction example, assuming that the user does not provide the conversation message 430, but directly asks for restaurant recommendations in the conversation message 434, the reply message of the digital assistant 120 may prompt the user to first provide information about the type of "food taste" so as to complete the restaurant recommendation desired by the user. After the user provides information about the type of "food taste" according to the prompt information, the digital assistant 120 may not only record the information under the corresponding type, but also complete the restaurant recommendation based on the obtained information.

[0063] Figure 5 1 is a flowchart of a process 500 for digital assistant interaction according to some embodiments of the present disclosure. The process 500 may be implemented at the assistant application platform 130. Figure 1 Process 500 is described.

[0064] In box 510, the assistant application platform 130 determines whether the interaction information between the user and the digital assistant includes or depends on the first type of information indicated by the storage configuration based on the storage configuration of the digital assistant.

[0065] In block 520 , if the assistant application platform 130 determines that the interaction information includes the first type of information and the first type of information has not been stored, the assistant application platform 130 writes the first type of information into a storage area corresponding to the first type.

[0066] In block 530 , if the assistant application platform 130 determines that the interaction information depends on the information of the first type and the information of the first type has been stored, the assistant application platform 130 reads the stored information of the first type from the storage area corresponding to the first type.

[0067] In box 540, the assistant application platform 130 determines the digital assistant's reply to the user based on the stored or read first type of information.

[0068] In some embodiments, the storage configuration includes a definition of one or more types of information to be stored for the digital assistant, the one or more types including a first type.

[0069] In some embodiments, process 500 further includes: if the stored information of the first type is different from the information of the first type included in the interaction information, updating the stored information with the information of the first type included in the interaction information.

[0070] In some embodiments, process 500 further includes: if it is determined that the interaction information depends on the first type of information and the first type of information is not stored, providing prompt information to the user to prompt the user to provide the first type of information.

[0071] In some embodiments, determining whether the interaction information includes or depends on the first type of information indicated by the storage configuration includes: constructing a prompt word input for the model based on the storage configuration and the interaction information; and obtaining an output of the model by providing the prompt word input to the model, the output of the model indicating whether the interaction information includes or depends on the first type of information indicated by the storage configuration.

[0072] In some embodiments, the storage area corresponding to the first type includes a storage area in a storage device.

[0073] In some embodiments, writing the first type of information into the storage area corresponding to the first type includes: writing the first type of information into the storage area corresponding to the first type by calling a read-write plug-in of the digital assistant.

[0074] In some embodiments, reading the stored first type of information from the storage area corresponding to the first type includes: reading the stored first type of information from the storage area corresponding to the first type by calling a read-write plug-in of the digital assistant.

[0075] Figure 6 A block diagram of an apparatus 600 for digital assistant interaction according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented in or included in the assistant application platform 130, for example. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0076] As shown in the figure, the device 600 includes an information determination module 610, which is configured to determine whether the interaction information between the user and the digital assistant includes or depends on the first type of information indicated by the storage configuration based on the storage configuration of the digital assistant. The device 600 also includes an information writing module 620, which is configured to write the first type of information into the storage area corresponding to the first type if it is determined that the interaction information includes the first type of information and the first type of information is not stored.

[0077] The device 600 also includes an information reading module 630, which is configured to read the stored first type of information from the storage area corresponding to the first type if it is determined that the interaction information depends on the first type of information and the first type of information has been stored. The device 600 also includes a reply determination module 640, which is configured to determine the digital assistant's reply to the user based on the stored or read first type of information.

[0078] In some embodiments, the storage configuration includes a definition of one or more types of information to be stored for the digital assistant, the one or more types including a first type.

[0079] In some embodiments, the apparatus 600 further includes an information updating module configured to: if the stored information of the first type is different from the information of the first type included in the interaction information, update the stored information with the information of the first type included in the interaction information.

[0080] In some embodiments, the apparatus 600 further comprises an information prompt module configured to: if it is determined that the interaction information depends on the first type of information and the first type of information is not stored, provide prompt information to the user to prompt the user to provide the first type of information.

[0081] In some embodiments, the information determination module 610 includes: a prompt word construction module, configured to construct a prompt word input for the model based on the storage configuration and the interaction information; and an output acquisition module, configured to obtain the output of the model by providing the prompt word input to the model, and the output of the model indicates whether the interaction information includes or depends on the first type of information indicated by the storage configuration.

[0082] In some embodiments, the storage area corresponding to the first type includes a storage area in a storage device.

[0083] In some embodiments, the information writing module 620 is configured to write the first type of information into a storage area corresponding to the first type by calling a read-write plug-in of the digital assistant.

[0084] In some embodiments, the information reading module 630 is configured to read the stored first type of information from the storage area corresponding to the first type by calling the read-write plug-in of the digital assistant.

[0085] 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 Assistant creation platform 110 and / or assistant application platform 130, and / or Figure 6 Device 600.

[0086] 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.

[0087] 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.

[0088] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7As 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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 an update, 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 the opposite order, depending on the function 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.

[0096] 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 digital assistant interaction, comprising: Based on a storage configuration of the digital assistant, determining whether interaction information between the user and the digital assistant includes or depends on a first type of information indicated by the storage configuration; If it is determined that the interaction information includes the first type of information and the first type of information is not stored, writing the first type of information into a storage area corresponding to the first type; If it is determined that the interaction information depends on the information of the first type and the information of the first type has been stored, reading the stored information of the first type from the storage area corresponding to the first type; as well as The digital assistant determines a reply to the user based on the stored or read first type of information.

2. A method according to claim 1, wherein the storage configuration includes a definition of one or more types of information to be stored for the digital assistant, the one or more types including the first type.

3. The method according to claim 1, further comprising: If the stored information of the first type is different from the information of the first type included in the interaction information, the stored information is updated with the information of the first type included in the interaction information.

4. The method according to claim 1, further comprising: If it is determined that the interaction information depends on the first type of information and the first type of information is not stored, prompt information is provided to the user to prompt the user to provide the first type of information.

5. The method of claim 1 , wherein determining whether the interaction information includes or depends on the first type of information indicated by the storage configuration comprises: constructing a prompt word input for a model based on the storage configuration and the interaction information; as well as By providing the cue word input to the model, an output of the model is obtained, the output of the model indicating whether the interaction information includes or depends on the first type of information indicated by the storage configuration. The method according to claim 1 , wherein the storage area corresponding to the first type comprises a storage area in a storage device.

7. The method according to claim 1, wherein writing the information of the first type into a storage area corresponding to the first type comprises: Writing the information of the first type into a storage area corresponding to the first type by calling the read-write plug-in of the digital assistant; and The step of reading the stored information of the first type from the storage area corresponding to the first type includes: By calling the read-write plug-in of the digital assistant, the stored information of the first type is read from the storage area corresponding to the first type.

8. A device for digital assistant interaction, comprising: an information determination module configured to determine, based on a storage configuration of the digital assistant, whether interaction information between the user and the digital assistant includes or depends on information of a first type indicated by the storage configuration; an information writing module, configured to write the first type of information into a storage area corresponding to the first type if it is determined that the interaction information includes the first type of information and the first type of information has not been stored; an information reading module, configured to read the stored information of the first type from the storage area corresponding to the first type if it is determined that the interaction information depends on the information of the first type and the information of the first type has been stored; as well as A reply determination module is configured to determine the digital assistant's reply to the user based on the stored or read first type of information.

9. 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 7 when executed by the at least one processing unit.

10. 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 7.

Images