Human-computer interaction method and device, and electronic device

Abstract

The present disclosure provides human-computer interaction methods, devices and electronic equipment, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, cloud computing, natural language processing, large model, computer vision and the like. The specific implementation scheme is: in the task execution process, the target interaction form and the target interaction content are determined according to the task context information; the target interaction form corresponds to the to-be-called file; the to-be-called file includes the calling logic of the human-computer interaction gateway; the to-be-called file is processed according to the target interaction content, the channel related information and the terminal device related information in the task context information, so as to call the human-computer interaction gateway to select the target transmission channel and the target terminal device, and to transmit the target interaction content; wherein, the active interaction strategy between the agent and the terminal device user can be realized; and the flexible selection of the interaction form, the transmission channel and the terminal device is realized, and the human-computer interaction efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the fields of deep learning, cloud computing, natural language processing, large models, and computer vision, and especially to a human-computer interaction method, device, and electronic device. Background Technology

[0002] Currently, the way intelligent agents deployed within virtual machines interact with external objects is as follows: the intelligent agent outputs content through the output interface provided by the virtual machine, and the host application where the virtual machine resides polls the output interface and calls the external notification service to transmit the content to the external object through the external notification service.

[0003] Currently, there is a lack of proactive interaction strategies between intelligent agents and external objects. Summary of the Invention

[0004] This disclosure provides a human-computer interaction method, apparatus, and electronic device.

[0005] According to one aspect of this disclosure, a human-computer interaction method is provided, applied to an intelligent agent. The method includes: during task execution, determining a target interaction form and target interaction content under the target interaction form based on task context information; the task context information includes channel-related information and terminal device-related information; determining a file to be invoked corresponding to the target interaction form; the file to be invoked includes invocation logic of a human-computer interaction gateway; and invoking the file to be invoked based on the target interaction content, the channel-related information, and the terminal device-related information, so as to invoke the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is a terminal device corresponding to a cloud phone on which an intelligent agent is deployed.

[0006] According to another aspect of this disclosure, a human-computer interaction method is provided, applied to a human-computer interaction gateway. The method includes: receiving a call request from an intelligent agent; the intelligent agent is an intelligent agent deployed in a cloud phone; the call request includes: a target interaction mode, target interaction content under the target interaction mode, channel-related information, and terminal-related information; selecting a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information; and transmitting the target interaction content to the target terminal device through the target transmission channel.

[0007] According to another aspect of this disclosure, a human-computer interaction device is provided, applied to an intelligent agent. The device includes: a first determining module, configured to determine a target interaction form and target interaction content under the target interaction form based on task context information during task execution; the task context information includes channel-related information and terminal device-related information; a second determining module, configured to determine a file to be invoked corresponding to the target interaction form; the file to be invoked includes invocation logic of a human-computer interaction gateway; and a first invocation module, configured to perform invocation processing on the file to be invoked based on the target interaction content, the channel-related information, and the terminal device-related information, so as to invoke the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is a terminal device corresponding to a cloud phone on which an intelligent agent is deployed.

[0008] According to another aspect of this disclosure, a human-computer interaction device is provided, applied to a human-computer interaction gateway. The device includes: a receiving module for receiving a call request from an intelligent agent; the intelligent agent is an intelligent agent deployed in a cloud phone; the call request includes: a target interaction mode, target interaction content under the target interaction mode, channel-related information, and terminal-related information; a selection module for selecting a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information; and a transmission module for transmitting the target interaction content to the target terminal device through the target transmission channel.

[0009] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the human-computer interaction method proposed above in this disclosure.

[0010] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing a computer to perform the human-computer interaction method proposed in this disclosure above.

[0011] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the human-computer interaction method proposed above in this disclosure.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0014] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure; Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure; Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure; Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure; Figure 5 This is a schematic diagram of asynchronous interaction between an intelligent agent and a terminal device; Figure 6 This is a schematic diagram according to the fifth embodiment of the present disclosure; Figure 7 This is a schematic diagram according to the sixth embodiment of the present disclosure; Figure 8 This is a block diagram of an electronic device used to implement the human-computer interaction method of the embodiments of this disclosure. Detailed Implementation

[0015] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0016] Currently, the interaction between agents deployed within virtual machines and external objects involves the agent outputting content through an output interface provided by the virtual machine. The host application on which the virtual machine resides polls the output interface and calls an external notification service to transmit the content to the external object. This entire process requires three cross-boundary transmissions and does not support the agent's autonomous selection of the notification channel.

[0017] Currently, there is a lack of proactive interaction strategies between intelligent agents and external objects.

[0018] To address the aforementioned issues, this disclosure proposes a human-computer interaction method, apparatus, and electronic device.

[0019] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure. It should be noted that the human-computer interaction method of the present disclosure can be applied to a human-computer interaction device, which can be configured in an electronic device so that the electronic device can perform human-computer interaction functions.

[0020] Among them, electronic devices can be any device with computing capabilities, such as personal computers (PCs), mobile terminals, servers, etc. Mobile terminals can be, for example, in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, smart speakers, servers, server clusters, and other hardware devices with various operating systems, touch screens and / or displays.

[0021] The human-computer interaction device can also be software within an electronic device, such as human-computer interaction software. For example, human-computer interaction software can be an intelligent agent deployed in a cloud phone on a server. The following embodiments will use an intelligent agent deployed in a cloud phone as an example for illustration.

[0022] like Figure 1 As shown, the human-computer interaction method may include the following steps: Step 101: During task execution, determine the target interaction form and the target interaction content under the target interaction form based on the task context information; the task context information includes channel-related information and terminal device-related information.

[0023] In this embodiment of the disclosure, the task context information may further include at least one of the following: interaction content-related information and interaction object-related information. The interaction content-related information includes at least one of the following: the urgency of the interaction content, the type of the interaction content, and the interaction time context; the interaction object-related information includes at least one of the following: the object profile of at least one terminal device and the object's historical response rate; the channel-related information includes: the channel cost of at least one transmission channel; and the terminal device-related information includes at least one of the following: the device occupancy status and the device online status of at least one terminal device. The object profile includes, for example, do-not-disturb periods, terminal preferences, region, and language.

[0024] The interaction form can include at least one of the following: Push notifications, Short Message Service (SMS) text messages, voice calls, emails, instant messaging bots, HTTP callbacks, two-way queries, rich forms, authorization, real-time streaming, and native terminal capabilities. The interaction form refers to the format of the interactive content transmitted by the intelligent agent to the terminal device.

[0025] The bidirectional query functionality can include multiple subclasses, such as single selection, multiple selection, text input, numeric input, slider, date selection, file / image selection, and voice input. Rich forms can include multiple subclasses, such as dynamic forms, wizard forms, conditional branches, and signature whiteboards. Authorization can include multiple subclasses, such as payment confirmation, biometrics, OAuth redirection, system permission requests, and two-way confirmation. Real-time streaming can include multiple subclasses, such as streaming text, streaming voice, screen sharing, and two-way voice calls. Native terminal capabilities can include multiple subclasses, such as camera capture, QR code scanning, location services, clipboard read / write, sharing panels, Live Activities, notification bar action buttons, widgets, and shortcuts.

[0026] The transmission channel may include at least one of the following: WebSocket long connection, server-sent events (SSE), vendor push, SMS / Voice over Public Switched Telephone Network (PSTN).

[0027] The term "cloud phone" can refer to either the hardware terminal device used when an object interacts with the cloud phone, or the application form used by the object to interact with the cloud phone within the hardware terminal device. Examples of hardware terminal devices include mobile terminals, personal computers, in-vehicle systems, displays, and wearable devices. Examples of application forms include H5 pages and mini-programs.

[0028] Among them, setting various relevant information in the task context information can improve the accuracy of the target interaction form and target interaction content determined by the intelligent agent.

[0029] In this embodiment of the disclosure, to further improve the accuracy of the determined target interaction form and enable the subsequent human-computer interaction gateway to select a suitable target terminal device and target transmission channel, the human-computer interaction gateway considers the correlation between the terminal device and transmission channel and the interaction form during the determination of the target interaction form. Correspondingly, the process by which the intelligent agent determines the target interaction form and the target interaction content under the target interaction form based on task context information can be, for example, as follows: determining at least one combination; the combination includes an interaction form, a transmission channel, and a terminal device identifier; selecting a target combination from the at least one combination based on the task context information; and determining the interaction form involved in the target combination as the target interaction form.

[0030] The process by which the agent selects a target combination from at least one combination based on task context information can be as follows: For each combination, determine the weight of each parameter in the task context information; determine the value of each parameter in the task context information based on the combination; wherein the content under each parameter can be represented by a numerical value; perform weighted summation of the values ​​of each parameter according to the weight of each parameter to obtain the score corresponding to the combination; sort the combinations according to the scores to obtain the combination with the highest score; and determine the combination with the highest score as the target combination.

[0031] In this embodiment of the disclosure, to further improve the accuracy of the subsequent selection of target terminal devices and target transmission channels by the human-computer interaction gateway, the task context information may also include preferred transmission channels and preferred terminal devices for the human-computer interaction gateway to refer to. The preferred transmission channel may be, for example, the transmission channel selected by the agent in the aforementioned combination; the preferred terminal device may be, for example, the terminal device selected by the agent in the aforementioned combination.

[0032] Step 102: Determine the file to be called corresponding to the target interaction mode; the file to be called includes the calling logic of the human-computer interaction gateway.

[0033] In this embodiment of the disclosure, the file to be invoked can be, for example, a skill file. In addition to the invocation logic of the human-computer interaction gateway, the file to be invoked may also include a declaration file. The declaration file may declare at least one of the following: the security level corresponding to the target interaction mode, the name of the file to be invoked, etc.

[0034] The invocation logic of the human-computer interaction gateway may include parameter fields required for the invocation. These parameter fields may include, for example, channel-related information fields, terminal device-related information fields, interaction mode fields, and interaction content fields, etc., without specific limitations here.

[0035] Step 103: Based on the target interaction content, channel-related information, and terminal device-related information, the file to be invoked is processed to invoke the human-computer interaction gateway to select the target transmission channel and target terminal device according to the channel-related information and terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to the cloud mobile phone with the intelligent agent deployed.

[0036] In this embodiment, after the intelligent agent processes the file to be invoked based on the target interaction content, channel-related information, and terminal device-related information, the invocation logic of the human-computer interaction gateway in the file to be invoked is executed, thereby invoking the human-computer interaction gateway to send an invocation request. The target interaction content, channel-related information, and terminal device-related information can be filled into the invocation request by the invocation logic of the human-computer interaction gateway during its execution.

[0037] In this embodiment of the disclosure, before step 101, when the agent receives a task, in order to further improve the efficiency of human-computer interaction and reduce the number of interactions between the agent and the terminal device object, the agent may also perform the following process: when the task is received, determine the initial interaction content under the first interaction mode according to the task; call the file to be called corresponding to the first interaction mode, so as to transmit the initial interaction content to the source terminal device through the human-computer interaction gateway.

[0038] The first interaction form can be, for example, a rich form. This first interaction form can be determined based on the initial interaction content.

[0039] In this embodiment of the disclosure, in order to achieve asynchronous interaction between the intelligent agent and the terminal device, enabling the intelligent agent to interact with multiple terminal devices simultaneously, the intelligent agent can obtain a session identifier after calling a file to be called, and then listen to the interaction response content including the session identifier; thus, it can call another file to be called even if it calls one file to be called and does not obtain the interaction response content. Correspondingly, after step 103, the intelligent agent can also perform the following process: obtain the session identifier of the target interaction content, and provide the session identifier to the human-computer interaction gateway, instructing the human-computer interaction gateway to store the obtained interaction response content including the session identifier in the file system; listen to the file system to obtain the interaction response content from the file system.

[0040] One way the human-computer interaction gateway stores the interaction response content, including the session identifier, into the file system is, for example, by using the Android Debug Bridge push (ADB push) method to write the interaction response content into the file system.

[0041] One possible way for an intelligent agent to monitor the file system is to poll the file system or listen for file system change notification events and read the interactive response content from the file system when a change notification event is detected.

[0042] In this embodiment of the disclosure, in order to further improve the efficiency of the intelligent agent in obtaining interactive response content, the file system can be a shared file system; the interactive response content under each interactive mode shares the storage area in the shared file system; the file system is located in the container where the cloud phone is located.

[0043] In cases where the interactive response content under various interaction modes shares the storage area in the shared file system, the agent can obtain the interactive response content from multiple sessions through a single storage area, thereby improving the efficiency of obtaining the interactive response content.

[0044] The human-computer interaction method of this disclosure determines the target interaction form and the target interaction content under the target interaction form based on task context information during task execution. The task context information includes channel-related information and terminal device-related information. A file to be called corresponding to the target interaction form is determined. The file to be called includes the calling logic of the human-computer interaction gateway. The file to be called is processed according to the target interaction content, channel-related information, and terminal device-related information to call the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and terminal device-related information, and to transmit the target interaction content to the target terminal device through the target transmission channel. The target terminal device is the terminal device corresponding to a cloud phone with an intelligent agent deployed. By processing the call to the file corresponding to the target interaction form, the human-computer interaction gateway can be called, and the target interaction content is transmitted to the target terminal device through the target transmission channel selected by the human-computer interaction gateway. This realizes an active interaction strategy between the intelligent agent and the terminal device corresponding to the cloud phone. Furthermore, the intelligent agent can select the interaction form according to the task context information, and the human-computer interaction gateway can select the transmission channel and terminal device, achieving flexible selection of the interaction form, transmission channel, and terminal device, thereby further improving the efficiency of human-computer interaction.

[0045] To further improve the interaction efficiency and security between the intelligent agent and the terminal device, and to enhance the accuracy of the target terminal device selected by the human-computer interaction gateway, the intelligent agent can combine a pre-configured page token to call the file to be called. This ensures that the call request received by the human-computer interaction gateway includes the page token, which can be used to determine the target terminal device and perform authentication processing. Figure 2 As shown, Figure 2 This is a schematic diagram based on the second embodiment of the present disclosure. Figure 2 The illustrated embodiment may include the following steps: Step 201: During task execution, determine the target interaction form and the target interaction content under the target interaction form based on the task context information; the task context information includes channel-related information and terminal device-related information.

[0046] Step 202: Determine the file to be called corresponding to the target interaction mode; the file to be called includes the calling logic of the human-computer interaction gateway.

[0047] Step 203: Obtain a pre-configured page token; the page token includes at least one of a terminal device identifier and an object identifier, used to determine the target terminal device and for authentication processing.

[0048] Terminal device identifiers include, for example, padCode and data center identifiers. Based on the terminal device identifier and the object identifier, the target terminal device can be uniquely identified.

[0049] The page token can be an HS256 encrypted and Base64 encoded page token. The HS256 decoding result and the various fields in the page token can be used for authentication processing. For example, signature verification can be performed based on the HS256 decoding result, i.e., agent key verification; signature verification of fields in the page token, etc.

[0050] To improve authentication flexibility, the file to be invoked may also include the security level corresponding to the target interaction mode, which is used to instruct the human-computer interaction gateway and / or the target terminal device to determine the authentication policy based on the page token according to the security level, and to perform authentication processing according to the authentication policy.

[0051] Among them, the number of authentication layers in the authentication strategy varies depending on the security level; the security level is positively correlated with the number of authentication layers; the authentication layer of the authentication strategy includes at least one of the following layers: agent key verification, field verification in page token, human-computer interaction gateway key verification, and one-time interaction token verification.

[0052] For example, security levels can be divided into four levels: L0, L1, L2, and L3. L0 is lower than L1, L1 is lower than L2, and L2 is lower than L3. An authentication strategy at level L0 could be agent key verification. That is, the human-machine interface gateway can perform Base64 and HS256 decoding on the page token in the call request to determine if the decoding was successful; if successful, the agent key verification is considered successful.

[0053] For example, the authentication strategy at L1 level could be agent key verification + page token field verification + human-computer interaction gateway key verification. That is, based on agent key verification, the human-computer interaction gateway can encrypt the page token using its own key, and when the target terminal device interacts for the first time, it decrypts the page token using the human-computer interaction gateway's key. Then, a "S agent identity link" display pops up in the application, showing at least one of the following: initiating agent, target terminal device, task identifier, time, and the last four digits of the terminal device's padCode identifier. The target terminal device verifies the format of each of these fields, and only after successful verification is the target interaction content displayed.

[0054] For example, an authentication strategy at Level 2 could be agent key verification + verification of fields in the page token + verification of the human-machine interaction gateway key + verification of a one-time interaction token. That is, the human-machine interaction gateway can also issue a one-time interaction token, allowing the target terminal device to encrypt the interaction response content before uploading it, and enabling the human-machine interaction gateway to perform verification processing using the one-time interaction token.

[0055] Among them, the authentication strategy at the L3 level, in addition to the authentication strategy at the L2 level, also adds an audit chain, which is used to write the target interaction content and interaction response content into the audit chain to facilitate subsequent traceability.

[0056] Among them, setting different authentication levels and numbers for different security levels can improve authentication efficiency while ensuring the security of different interactive content.

[0057] Step 204: Based on the target interaction content, channel-related information, terminal device-related information, and page token, the file to be invoked is processed to invoke the human-computer interaction gateway to select the target transmission channel and target terminal device based on the channel-related information, terminal device-related information, and page token, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to the cloud mobile phone with the intelligent agent deployed.

[0058] In the case where the intelligent agent calls the file to be called based on the target interaction content, channel-related information, terminal device-related information, and page token, the human-computer interaction gateway can receive a call request including the target interaction content, channel-related information, terminal device-related information, and page token. Then, it can select the target transmission channel and the target terminal device based on the information contained in the call request, and then perform the transmission processing of the target interaction content.

[0059] It should be noted that for details of steps 201 to 202, please refer to [the relevant documentation / reference]. Figure 1Steps 101 to 102 in the illustrated embodiment will not be described in detail here.

[0060] The human-computer interaction method of this disclosure, during task execution, determines the target interaction form and the target interaction content under the target interaction form based on task context information; the task context information includes channel-related information and terminal device-related information; determines the file to be called corresponding to the target interaction form; the file to be called includes the calling logic of the human-computer interaction gateway; obtains a pre-configured page token; the page token includes at least one of a terminal device identifier and an object identifier, used to determine the target terminal device and perform authentication processing; and performs calling processing on the file to be called based on the target interaction content, channel-related information, terminal device-related information, and page token, so as to call the human-computer interaction gateway to select the target transmission channel and the target terminal device based on the channel-related information, terminal device-related information, and page token, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to a cloud phone with an intelligent agent deployed; wherein, the intelligent agent can call the file to be called in combination with the pre-configured page token, so that the calling request received by the human-computer interaction gateway includes the page token, wherein the page token can be used to determine the target terminal device and perform authentication processing, thereby further improving the accuracy of target terminal device selection and further improving the interaction efficiency and interaction security between the intelligent agent and the terminal device.

[0061] To further improve the interaction efficiency between intelligent agents and terminal devices, it is necessary to ensure the accuracy of the files to be called for each interaction mode, and to avoid changes to the files to be called for each interaction mode. For example... Figure 3 As shown, Figure 3 This is a schematic diagram based on the third embodiment of the present disclosure. Figure 3 The illustrated embodiment may include the following steps: Step 301: During task execution, determine the target interaction form and the target interaction content under the target interaction form based on the task context information; the task context information includes channel-related information and terminal device-related information.

[0062] Step 302: Determine the file to be called corresponding to the target interaction mode; the file to be called includes the calling logic of the human-computer interaction gateway.

[0063] Step 303: Based on the target interaction content, channel-related information, and terminal device-related information, the file to be invoked is processed to invoke the human-computer interaction gateway to select the target transmission channel and target terminal device according to the channel-related information and terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to the cloud mobile phone with the intelligent agent deployed.

[0064] Step 304: Determine the protection strategy for the file to be called corresponding to each interaction mode; the protection strategy is used to indicate that no changes should be made to the file to be called.

[0065] In this embodiment of the disclosure, the process of the intelligent agent performing step 304 may be, for example, determining the configuration support capability of the cloud mobile phone on which the intelligent agent is deployed; the configuration support capability indicates the configuration supported by the cloud mobile phone; and determining a protection strategy based on the configuration support capability.

[0066] This includes configuration support capabilities such as whether it supports unchangeable attribute configurations. Specifically, if the cloud phone does not support unchangeable attribute configurations, the resulting protection strategy may not include configuring the attributes of the file to be called corresponding to the interaction mode as unchangeable.

[0067] Specifically, the protection strategy is determined based on the configuration support capabilities, and then the protection configuration is processed in conjunction with the protection strategy to ensure that the determined protection strategy can take effect; this avoids determining protection strategies that are difficult to take effect, thereby further improving the matching degree between the determined protection strategy and the cloud phone, and further improving the accuracy of the protection strategy determination.

[0068] In this embodiment of the disclosure, the protection strategy includes at least one of the following: for the file to be called corresponding to the interaction mode, an empty directory is created and configured as unmodifiable; the empty directory has a higher priority than the file to be called, and the name of the empty directory is the same as the name of the file to be called; the file to be called corresponding to the interaction mode is configured to be read-only; the file to be called corresponding to the interaction mode is configured to have unchangeable attributes; when the file to be called corresponding to the interaction mode is no longer used, the file to be called is configured to be allowed to be used.

[0069] Specifically, for the file to be called corresponding to the interactive mode, an empty directory is created and configured as unmodifiable; the empty directory has a higher priority than the file to be called, and its name is the same as the file to be called. By configuring protection for each file to be called according to this protection strategy, if a first file to be called with the same name and priority exists, the first file to be called will not be overwritten, thus preventing any changes to that file.

[0070] Specifically, configuring the file to be called corresponding to the interaction mode as read-only and configuring the file to be called corresponding to the interaction mode as having immutable attributes can prevent the intelligent agent or other devices from modifying the file to be called.

[0071] In this context, the file to be called corresponding to the interactive mode is generally in use. Therefore, when the file to be called corresponding to the interactive mode is taken out of use, it is essentially a modification to that file. To avoid this modification, it is necessary to configure the file to be called to be allowed to be used.

[0072] In addition, the protection strategy may include at least one of the following: adding the file to be invoked to the whitelist; stopping the addition of the file to be invoked to the blacklist; rebuilding the directory when the directory where the file to be invoked is located is corrupted; rebuilding the file to be invoked when the file to be invoked is corrupted, etc.

[0073] The protection strategies mentioned above cover various feasible ways to modify the file to be called. By setting these protection strategies, changes to the file to be called can be avoided, thereby ensuring the accuracy of the file to be called for each interaction mode and thus ensuring the interaction efficiency between the agent and the terminal device.

[0074] Step 305: Configure protection settings for each file to be called according to the protection policy.

[0075] It should be noted that for details of steps 301 to 303, please refer to [the relevant documentation / reference]. Figure 1 Steps 101 to 103 in the illustrated embodiment will not be described in detail here.

[0076] The human-computer interaction method of this disclosure, during task execution, determines the target interaction form and the target interaction content under the target interaction form based on task context information; the task context information includes channel-related information and terminal device-related information; determines the file to be called corresponding to the target interaction form; the file to be called includes the calling logic of the human-computer interaction gateway; and processes the file to be called based on the target interaction content, channel-related information, and terminal device-related information, so as to call the human-computer interaction gateway to select the target transmission channel and the target terminal device based on the channel-related information and the terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to a cloud mobile phone with an intelligent agent deployed; determines a protection strategy for the file to be called corresponding to each interaction form; the protection strategy is used to indicate that no changes are made to the file to be called; and performs protection configuration processing on each file to be called according to the protection strategy; wherein, the protection strategy ensures the accuracy of the file to be called corresponding to each interaction form and avoids changes to the file to be called corresponding to each interaction form, thereby further improving the interaction efficiency between the intelligent agent and the terminal device.

[0077] Figure 4This is a schematic diagram based on the fourth embodiment of the present disclosure. It should be noted that the human-computer interaction method of the present disclosure can be applied to a human-computer interaction device, which can be configured in an electronic device so that the electronic device can perform human-computer interaction functions.

[0078] Among them, electronic devices can be any device with computing capabilities, such as personal computers (PCs), mobile terminals, servers, etc. Mobile terminals can be, for example, in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, smart speakers, servers, server clusters, and other hardware devices with various operating systems, touch screens and / or displays.

[0079] The human-computer interaction device can also be software in an electronic device, such as human-computer interaction software. Human-computer interaction software can be, for example, a human-computer interaction gateway. In the following embodiments, the execution entity is a human-computer interaction gateway as an example for explanation.

[0080] like Figure 4 As shown, the human-computer interaction method may include the following steps: Step 401: Receive the invocation request of the intelligent agent; the intelligent agent is the intelligent agent deployed in the cloud phone; the invocation request includes: the target interaction form, the target interaction content under the target interaction form, channel-related information and terminal-related information.

[0081] In this embodiment of the disclosure, the target interaction form can be any of the following: Push notification, Short Message Service (SMS) text message, voice call, email, instant messaging robot, HTTP callback, two-way query, rich form, authorization, real-time streaming, or native terminal capabilities. Here, the interaction form refers to the format of the interactive content transmitted by the intelligent agent to the terminal device.

[0082] The channel-related information may include: the channel cost of at least one transmission channel. The terminal device-related information may include at least one of the following: the device occupancy status and the device online status of at least one terminal device.

[0083] Step 402: Select the target transmission channel and target terminal device based on the channel-related information and the terminal device-related information.

[0084] In this embodiment of the disclosure, the call request also includes a page token; the page token includes at least one of a terminal device identifier and an object identifier; the process of the human-computer interaction gateway performing step 402 may be, for example, obtaining channel constraint information corresponding to the target interaction mode; determining at least one candidate transmission channel corresponding to the target interaction mode based on the channel constraint information; selecting a target transmission channel from at least one candidate transmission channel based on channel-related information and terminal device-related information; and determining the target terminal device based on at least one of the terminal device identifier and the object identifier.

[0085] In cases where the page token is not included in the call request, the target terminal device can be selected from at least one candidate terminal device based on terminal device-related information.

[0086] Taking camera photography, a native capability of the terminal, as an example, the human-computer interaction gateway can determine whether the target terminal device is online based on its online status. If the target terminal device is online, the target transmission channel is determined to be a WebSocket long connection. If the target terminal device is offline, the target transmission channel is determined to be a manufacturer push wake-up + transmission via WebSocket long connection after going online.

[0087] Taking Push as an example, the human-computer interaction gateway can determine whether the target terminal device is online based on the device's online status. If the target terminal device is online, the target transmission channel is determined to be a WebSocket long connection; if the target terminal device is offline, the target transmission channel is determined to be a vendor Push.

[0088] For example, if the target interaction type is SMS (text message), the human-machine interaction gateway can determine that the target transmission channel is SMS. If the target interaction type is voice call, the human-machine interaction gateway can determine that the target transmission channel is the Public Switched Telephone Network (PSTN).

[0089] Among these methods, selecting the target transmission channel based on the channel constraint information, channel-related information, and terminal device-related information corresponding to the target interaction mode can further improve the accuracy of target transmission channel selection; determining the target terminal device based on at least one of the terminal device identifier and object identifier can further improve the accuracy of target terminal device selection.

[0090] Step 403: Transmit the target interactive content to the target terminal device through the target transmission channel.

[0091] In this embodiment of the disclosure, in order to further improve the success rate of transmission of target interactive content, before step 403, the human-computer interaction gateway may also perform the following process: obtain the component list file of the target terminal device; determine the interaction form degradation strategy according to the component list file; and adjust the target interaction form according to the interaction form degradation strategy.

[0092] The component manifest file may include all the components supported by the target terminal device, as well as the minimum supported version of each component. Based on the minimum supported version of each component, the capabilities supported by each component can be determined, thereby determining whether the target terminal device can parse, render, and display the target interactive content.

[0093] If, based on the minimum supported versions of each component, the target terminal device is determined to be capable of parsing, rendering, and displaying the target interactive content, then the interaction form degradation strategy can be determined to be no degradation adjustment to the target interactive form. However, if, based on the minimum supported versions of each component, some or all of the interactive content in the target interactive content is determined to be difficult to parse, render, and display, then the target interactive form can be adjusted.

[0094] Specifically, the interaction form degradation strategy is determined based on the component manifest file, and then the target interaction form is adjusted and processed to ensure that the target terminal device can parse, render and display the received target interaction content, thereby improving the success rate of displaying the target interaction content.

[0095] The human-computer interaction method of this disclosure involves receiving a call request from an intelligent agent deployed in a cloud phone. The call request includes: a target interaction form, target interaction content within the target interaction form, channel-related information, and terminal-related information. A target transmission channel and a target terminal device are selected based on the channel-related information and the terminal device-related information. The target interaction content is transmitted to the target terminal device through the target transmission channel. The human-computer interaction gateway can select the target transmission channel and the target terminal device based on the intelligent agent's call request, thereby implementing an active interaction strategy between the intelligent agent and the corresponding terminal device of the cloud phone. Furthermore, the human-computer interaction gateway can select the transmission channel and the terminal device based on the information in the call request, enabling flexible selection of the transmission channel and the terminal device, thus further improving the efficiency of human-computer interaction.

[0096] The following example illustrates this. For example... Figure 5 The diagram shown illustrates the asynchronous interaction between an intelligent agent and a terminal device. Figure 5 This may include the following steps: Step 501: The Agent (i.e., the intelligent agent) calls hci.ask / hci.form / hci / auth (i.e., the file to be called), etc., to create a call request, and sends it to the Operator (i.e., the human-computer interaction gateway), instructing the Operator to select a route (i.e., select the target terminal device and the target transmission channel) and deliver it to the terminal (i.e., the target terminal device). If a timeout occurs and delivery is not completed, the process ends.

[0097] Step 502: The Operator selects a route and delivers the data to the terminal, then waits for the APP (i.e., the target terminal device) renderer to report a `rendered` event. The `rendered` event indicates whether rendering was successful. If no `rendered` event occurs within the timeout period, the process ends.

[0098] Step 503: The app renderer reports a `rendered` event and then waits for the user to interact, such as initial input / click, to obtain the user-submitted content (i.e., the interaction response content). The process ends if the user does not submit within the timeout period.

[0099] Step 504: If the timeout has not occurred, the Agent sandbox can read the receipt (i.e., the interaction response content) and terminate.

[0100] To implement the above embodiments, this disclosure also provides a human-computer interaction device. For example... Figure 6 As shown, Figure 6 This is a schematic diagram according to the fifth embodiment of the present disclosure. The human-computer interaction device 60, applied to an intelligent agent, may include: a first determining module 601, a second determining module 602, and a first calling module 603.

[0101] The first determining module 601 is used to determine the target interaction form and the target interaction content under the target interaction form according to the task context information during task execution; the task context information includes channel-related information and terminal device-related information; the second determining module 602 is used to determine the file to be called corresponding to the target interaction form; the file to be called includes the calling logic of the human-computer interaction gateway; the first calling module 603 is used to call the file to be called according to the target interaction content, the channel-related information and the terminal device-related information, so as to call the human-computer interaction gateway to select the target transmission channel and the target terminal device according to the channel-related information and the terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to a cloud mobile phone with an intelligent agent deployed.

[0102] As one possible implementation of this disclosure, the task context information further includes at least one of the following: interaction content-related information and interaction object-related information; the interaction content-related information includes at least one of the following: interaction content urgency, interaction content type, and interaction time context; the interaction object-related information includes at least one of the following: object profile and historical response rate of at least one terminal device; the channel-related information includes: channel cost of at least one transmission channel; the terminal device-related information includes at least one of the following: device occupancy status and device online status of at least one terminal device.

[0103] As one possible implementation of this disclosure, the first determining module 601 is specifically used to: determine at least one combination; the combination includes an interaction mode, a transmission channel and a terminal device identifier; select a target combination from the at least one combination according to the task context information; and determine the interaction mode involved in the target combination as the target interaction mode.

[0104] As one possible implementation of this disclosure, the first invocation module 603 is specifically used to: obtain a pre-configured page token; the page token includes at least one of a terminal device identifier and an object identifier, used to determine the target terminal device and perform authentication processing; and perform invocation processing on the file to be invoked based on the target interaction content, the channel-related information, the terminal device-related information, and the page token.

[0105] As one possible implementation of this disclosure, the file to be invoked includes a security level corresponding to the target interaction mode, which is used to instruct the human-computer interaction gateway and / or the target terminal device to determine an authentication policy based on the page token according to the security level, and to perform authentication processing according to the authentication policy.

[0106] As one possible implementation of this disclosure, the number of authentication layers in the authentication strategy corresponding to different security levels is different; the security level is positively correlated with the number of authentication layers; the authentication layer of the authentication strategy includes at least one of the following layers: agent key verification, field verification in page token, human-computer interaction gateway key verification, and one-time interaction token verification.

[0107] As one possible implementation of this disclosure, the apparatus further includes: a third determining module and a configuration processing module; the third determining module is configured to determine a protection strategy for the files to be invoked corresponding to each interaction mode; the protection strategy is configured to instruct the cessation of modification processing on the files to be invoked; the configuration processing module is configured to perform protection configuration processing on each of the files to be invoked according to the protection strategy.

[0108] As one possible implementation of this disclosure, the third determining module is specifically used to: determine the configuration support capability of the cloud phone on which the intelligent agent is deployed; the configuration support capability indicates the configuration supported by the cloud phone; and determine the protection strategy based on the configuration support capability.

[0109] As one possible implementation of this disclosure, the protection strategy includes at least one of the following: creating an empty directory for the file to be called corresponding to the interaction mode and configuring the empty directory as unmodifiable; the empty directory has a higher priority than the file to be called, and the name of the empty directory is the same as the name of the file to be called; configuring the file to be called corresponding to the interaction mode as read-only; configuring the file to be called corresponding to the interaction mode as having unchangeable attributes; and configuring the file to be called as usable when the file to be called corresponding to the interaction mode is no longer used.

[0110] As one possible implementation of this disclosure, the apparatus further includes: an acquisition module and a monitoring module; the acquisition module is configured to acquire a session identifier of the target interactive content and provide the session identifier to the human-computer interaction gateway, instructing the human-computer interaction gateway to store the acquired interactive response content including the session identifier in a file system; the monitoring module is configured to monitor the file system to acquire the interactive response content from the file system.

[0111] As one possible implementation of this disclosure, the file system is a shared file system; the interactive response content under each interactive mode shares the storage area in the shared file system; the file system is located in the container where the cloud phone is located.

[0112] As one possible implementation of this disclosure, the apparatus further includes: a fourth determining module and a second calling module; the fourth determining module is used to determine initial interaction content under a first interaction mode according to the task when a task is received; the second calling module is used to call the file to be called corresponding to the first interaction mode, so as to transmit the initial interaction content to the source terminal device of the task through the human-computer interaction gateway.

[0113] The human-computer interaction device of this disclosure determines the target interaction form and the target interaction content under the target interaction form based on task context information during task execution. The task context information includes channel-related information and terminal device-related information. A file to be called corresponding to the target interaction form is determined. The file to be called includes the calling logic of the human-computer interaction gateway. The file to be called is processed according to the target interaction content, channel-related information, and terminal device-related information to call the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and terminal device-related information, and to transmit the target interaction content to the target terminal device through the target transmission channel. The target terminal device is the terminal device corresponding to a cloud phone with an intelligent agent deployed. By processing the call to the file corresponding to the target interaction form, the human-computer interaction gateway can be called, and the target interaction content is transmitted to the target terminal device through the target transmission channel selected by the human-computer interaction gateway. This realizes an active interaction strategy between the intelligent agent and the terminal device corresponding to the cloud phone. Furthermore, the intelligent agent can select the interaction form according to the task context information, and the human-computer interaction gateway can select the transmission channel and terminal device, achieving flexible selection of the interaction form, transmission channel, and terminal device, thereby further improving the efficiency of human-computer interaction.

[0114] To implement the above embodiments, this disclosure also provides a human-computer interaction device. For example... Figure 7 As shown, Figure 7 This is a schematic diagram according to the sixth embodiment of the present disclosure. The human-computer interaction device 70, applied to a human-computer interaction gateway, may include: a receiving module 701, a selection module 702, and a transmission module 703.

[0115] The receiving module 701 is used to receive a call request from an intelligent agent; the intelligent agent is an intelligent agent deployed in a cloud phone; the call request includes: a target interaction mode, target interaction content under the target interaction mode, channel-related information, and terminal-related information; the selection module 702 is used to select a target transmission channel and a target terminal device according to the channel-related information and the terminal device-related information; the transmission module 703 is used to transmit the target interaction content to the target terminal device through the target transmission channel.

[0116] As one possible implementation of this disclosure, the invocation request further includes a page token; the page token includes at least one of a terminal device identifier and an object identifier; the selection module 702 is specifically used to: obtain channel constraint information corresponding to the target interaction mode; determine at least one candidate transmission channel corresponding to the target interaction mode based on the channel constraint information; select the target transmission channel from the at least one candidate transmission channel based on the channel-related information and the terminal device-related information; and determine the target terminal device based on at least one of the terminal device identifier and the object identifier.

[0117] As one possible implementation of this disclosure, the apparatus further includes: an acquisition module, a determination module, and an adjustment processing module; the acquisition module is used to acquire a component list file of the target terminal device; the determination module is used to determine an interaction mode degradation strategy based on the component list file; and the adjustment processing module is used to adjust the target interaction mode according to the interaction mode degradation strategy.

[0118] The human-computer interaction device of this embodiment receives a call request from an intelligent agent; the intelligent agent is an intelligent agent deployed in a cloud phone; the call request includes: a target interaction form, target interaction content under the target interaction form, channel-related information, and terminal-related information; a target transmission channel and a target terminal device are selected based on the channel-related information and the terminal device-related information; the target interaction content is transmitted to the target terminal device through the target transmission channel; wherein, the human-computer interaction gateway can select the target transmission channel and the target terminal device according to the call request of the intelligent agent, thereby realizing an active interaction strategy between the intelligent agent and the terminal device corresponding to the cloud phone; and the human-computer interaction gateway can select the transmission channel and the terminal device according to the information in the call request, realizing flexible selection of the transmission channel and the terminal device, thereby further improving the efficiency of human-computer interaction.

[0119] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, and disclosure of users' personal information are all carried out with the consent of the users, and all comply with the provisions of relevant laws and regulations, and do not violate public order and good morals.

[0120] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0121] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0122] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0123] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0124] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as human-computer interaction methods. For example, in some embodiments, the human-computer interaction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the human-computer interaction method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the human-computer interaction method by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0129] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0130] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0131] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0132] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A human-computer interaction method applied to an intelligent agent, the method comprising: During task execution, the target interaction form and the target interaction content under the target interaction form are determined based on the task context information. The task context information includes channel-related information and terminal device-related information; Determine the file to be called corresponding to the target interaction mode; The file to be invoked includes the invocation logic of the human-computer interaction gateway; The file to be invoked is processed according to the target interaction content, the channel-related information, and the terminal device-related information to invoke the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information, and to transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to a cloud phone with an intelligent agent deployed.

2. The method according to claim 1, wherein, The task context information also includes at least one of the following: information related to the interaction content and information related to the interaction object; The information related to the interactive content includes at least one of the following: the urgency of the interactive content, the type of the interactive content, and the time context of the interaction. The information related to the interactive object includes at least one of the following: the object profile and historical response rate of at least one terminal device; The channel-related information includes: the channel cost of at least one transmission channel; The terminal device related information includes at least one of the following: the device occupancy status and the device online status of at least one terminal device.

3. The method according to claim 1 or 2, wherein, Determining the target interaction form and the target interaction content under the target interaction form based on the task context information includes: Determine at least one combination; the combination includes an interaction mode, a transmission channel, and a terminal device identifier; Select a target combination from the at least one combination based on the task context information; The interaction patterns involved in the target combination are defined as the target interaction patterns.

4. The method according to claim 1, wherein, The step of calling the file to be called based on the target interaction content, the channel-related information, and the terminal device-related information includes: Obtain a pre-configured page token; the page token includes at least one of a terminal device identifier and an object identifier, used to identify the target terminal device and perform authentication processing; The file to be invoked is processed based on the target interactive content, the channel-related information, the terminal device-related information, and the page token.

5. The method according to claim 4, wherein, The file to be invoked includes the security level corresponding to the target interaction mode, which is used to instruct the human-computer interaction gateway and / or the target terminal device to determine the authentication policy based on the page token according to the security level, and to perform authentication processing according to the authentication policy.

6. The method according to claim 5, wherein, Different security levels correspond to different numbers of authentication layers in their authentication strategies; the security level is positively correlated with the number of authentication layers. The authentication strategy includes at least one of the following authentication levels: agent key verification, field verification in page token, human-computer interaction gateway key verification, and one-time interaction token verification.

7. The method according to claim 1, wherein, The method further includes: Determine a protection strategy for the file to be invoked corresponding to each interaction mode; the protection strategy is used to indicate that no changes should be made to the file to be invoked. The protection configuration is performed on each of the files to be invoked according to the protection policy.

8. The method according to claim 7, wherein, The determination of the protection strategy for the files to be called corresponding to each interaction mode includes: Determine the configuration support capabilities of the cloud phone on which the intelligent agent is deployed; the configuration support capabilities indicate the configurations supported by the cloud phone; The protection strategy is determined based on the configuration support capabilities.

9. The method according to claim 7, wherein, The protection strategy includes at least one of the following: For the file to be called corresponding to the interactive mode, an empty directory is created and the empty directory is configured to be unmodifiable; the priority of the empty directory is higher than the priority of the file to be called, and the name of the empty directory is the same as the name of the file to be called; Configure the file to be called corresponding to the interaction mode as read-only; The attributes of the file to be called corresponding to the aforementioned interaction mode shall be configured to be immutable. When the file to be called corresponding to the interaction mode is no longer used, the file to be called is configured to be allowed to be used.

10. The method according to claim 1, wherein, After processing the file to be invoked based on the target interaction content, the channel-related information, and the terminal device-related information, the method further includes: Obtain the session identifier of the target interactive content and provide the session identifier to the human-computer interaction gateway, instructing the human-computer interaction gateway to store the obtained interactive response content including the session identifier into the file system; Monitor the file system to obtain the interactive response content from the file system.

11. The method according to claim 10, wherein, The file system is a shared file system; the interactive response content under each interactive mode shares the storage area in the shared file system. The file system is located in the container where the cloud phone is located.

12. The method according to claim 1, wherein, The method further includes: Upon receiving a task, the initial interaction content in the first interaction mode is determined based on the task. The file to be called corresponding to the first interaction mode is invoked so that the initial interaction content can be transmitted to the source terminal device of the task through the human-computer interaction gateway.

13. A human-computer interaction method, applied to a human-computer interaction gateway, the method comprising: Receive invocation requests from intelligent agents; The intelligent agent is an intelligent agent deployed in a cloud phone; The invocation request includes: the target interaction mode, the target interaction content under the target interaction mode, channel-related information, and terminal-related information; Select the target transmission channel and the target terminal device based on the channel-related information and the terminal device-related information; The target interactive content is transmitted to the target terminal device through the target transmission channel.

14. The method according to claim 13, wherein, The invocation request also includes a page token; the page token includes at least one of a terminal device identifier and an object identifier; the step of selecting the target transmission channel and the target terminal device based on the channel-related information and the terminal device-related information includes: Obtain the channel constraint information corresponding to the target interaction pattern; Based on the channel constraint information, at least one candidate transmission channel corresponding to the target interaction pattern is determined; The target transmission channel is selected from the at least one candidate transmission channel based on the channel-related information and the terminal device-related information; The target terminal device is determined based on at least one of the terminal device identifier and the object identifier.

15. The method according to claim 13, wherein, Before transmitting the target interactive content to the target terminal device through the target transmission channel, the method further includes: Obtain the component manifest file of the target terminal device; Based on the component manifest file, determine the interaction mode degradation strategy; The target interaction form is adjusted according to the interaction form degradation strategy.

16. A human-computer interaction device, applied to an intelligent agent, the device comprising: The first determining module is used to determine the target interaction form and the target interaction content under the target interaction form based on the task context information during task execution. The task context information includes channel-related information and terminal device-related information; The second determining module is used to determine the file to be called corresponding to the target interaction mode; The file to be invoked includes the invocation logic of the human-computer interaction gateway; The first invocation module is used to process the file to be invoked based on the target interaction content, the channel-related information, and the terminal device-related information, so as to invoke the human-computer interaction gateway to select a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information, and transmit the target interaction content to the target terminal device through the target transmission channel; the target terminal device is the terminal device corresponding to a cloud phone with an intelligent agent deployed.

17. A human-computer interaction device, applied to a human-computer interaction gateway, the device comprising: The receiving module is used to receive invocation requests from intelligent agents; The intelligent agent is an intelligent agent deployed in a cloud phone; The invocation request includes: the target interaction mode, the target interaction content under the target interaction mode, channel-related information, and terminal-related information; The selection module is used to select a target transmission channel and a target terminal device based on the channel-related information and the terminal device-related information. A transmission module is used to transmit the target interactive content to the target terminal device through the target transmission channel.

18. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the method of any one of claims 1 to 12; Alternatively, the method described in any one of claims 13 to 15 may be performed.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 12; or to perform the method according to any one of claims 13 to 15.

20. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 12; or implements the method according to any one of claims 13 to 15.

Images