Cooperative office method, electronic equipment, storage medium and program product

Abstract

The invention provides a collaborative office method, electronic equipment, a storage medium and a program product, relates to the technical field of office automation, and can realize efficient automatic collaborative office. The method comprises the following steps: receiving a multi-mode instruction input by a user; determining a target task based on the multi-modal instruction; and calling at least one vertical application to execute the target task.

Description

Technical Field

[0001] The present application relates to the field of office automation technology, and in particular to a collaborative office method, electronic equipment, storage medium and program product. Background Art

[0002] At present, the collaborative office platforms on the market are mainly divided into two main product types: traditional office software and entry-level platforms. With the release of the demand for mobile office in government and enterprises, some traditional office software companies have also begun to join the platform ecology of entry-level platforms, and distribute government and enterprise office services and attract customers by establishing strategic partnerships with vertical office application manufacturers. The entry-level collaborative office platforms, with DingTalk, WeChat for Enterprise, and Feishu as the mainstream, have deeply integrated instant messaging, documents, network disks, process approval, intelligent personnel, meetings, etc., and fully support the full-link digitalization of government and enterprise management.

[0003] With the continuous development and application of current digital, networked, and intelligent technologies, enterprises' demand for collaborative office has evolved from meeting the communication management needs in the office process to being able to complete the high integration of different office contents, realize timely communication and data sharing between departments, and strengthen internal security management of the enterprise. However, after the existing collaborative office applications are connected to the external workbench applications, they are usually only integrated at the entry level, and the internal office process is still completed through manual operation. This method requires users to have an operation manual and be familiar with the operation process before they can smoothly use the collaborative office application to complete office tasks. Therefore, when using such collaborative office applications, there is often a problem of relatively low work efficiency. Summary of the invention

[0004] The present application provides a collaborative office method, electronic device, storage medium and program product, which can realize efficient and automated collaborative office.

[0005] In a first aspect, the present application provides a collaborative office method, which is applied to a collaborative office platform, where the collaborative office platform is connected to multiple vertical applications. The method includes: receiving multimodal instructions input by a user; determining a target task based on the multimodal instructions; and calling at least one vertical application to execute the target task.

[0006] The technical solution provided by the present application brings at least the following beneficial effects: by analyzing the multimodal instructions input by the user, identifying the target tasks indicated by the multimodal instructions, and then analyzing and determining the vertical applications related to completing the target tasks, and finally calling these vertical applications to perform the above-mentioned target tasks, the automated execution of office tasks and the rapid transmission of information are realized, which can improve the work efficiency of the collaborative office platform.

[0007] A possible implementation method is to determine a target task based on a multimodal instruction, including: determining at least one office task corresponding to the multimodal instruction; receiving a first trigger operation, the first trigger operation being used to indicate any office task among the at least one office task; and determining the target task based on the first trigger operation.

[0008] Another possible implementation method is to determine at least one office task corresponding to the multimodal instruction, including: inputting the multimodal instruction into a task recognition model to obtain at least one task corresponding to the multimodal instruction; wherein the task recognition model is used to identify tasks related to the input multimodal instruction.

[0009] Another possible implementation method is that the target task includes at least one subtask, and the method also includes: determining at least one vertical application required to be called to execute the at least one subtask; calling at least one vertical application to execute the target task, including: generating at least one control instruction corresponding to each subtask based on the at least one subtask, the control instruction being used to instruct the vertical application corresponding to the subtask to execute the subtask; and sending the corresponding control instructions to the at least one vertical application respectively.

[0010] Another possible implementation manner is to send the corresponding control instructions to at least one vertical application respectively, including: encrypting the control instructions to obtain encrypted control instructions; and sending the corresponding encrypted control instructions to at least one vertical application respectively.

[0011] In another possible implementation, the collaborative office platform includes identity authentication information of registered users, and the method further includes: sending the identity authentication information of registered users to multiple vertical applications respectively.

[0012] Another possible implementation method is that the multimodal instructions include voice instructions, and determining the target task based on the multimodal instructions includes: performing timbre recognition on the voice instructions to obtain the timbre characteristics of the voice instructions; comparing the timbre characteristics of the voice instructions with the recorded timbre characteristics; and determining the target task based on the voice instructions when the recorded timbre characteristics include the timbre characteristics of the voice instructions.

[0013] In a second aspect, the present application provides a collaborative office device, a receiving module, an analyzing module, and a controlling module. In some embodiments, the collaborative office device further includes a communication module.

[0014] A receiving module, used for receiving a multimodal instruction input by a user;

[0015] An analysis module for determining a target task based on multimodal instructions;

[0016] The control module is used to call at least one vertical application to execute a target task.

[0017] In a possible implementation, an analysis module is specifically used to determine at least one office task corresponding to the multimodal instruction; a first trigger operation is received, and the first trigger operation is used to indicate any office task among the at least one office task; and a target task is determined based on the first trigger operation.

[0018] Another possible implementation is that the analysis module is specifically used to input the multimodal instruction into a task identification model to obtain at least one task corresponding to the multimodal instruction; wherein the task identification model is used to identify tasks related to the input multimodal instruction.

[0019] In another possible implementation, the target task includes at least one subtask; the analysis module is further used to determine at least one vertical application required to be called to execute the at least one subtask; the control module is specifically used to generate a control instruction corresponding to at least one subtask according to the at least one subtask, the control instruction being used to instruct the vertical application corresponding to the subtask to execute the subtask; and the corresponding control instructions are sent to the at least one vertical application respectively.

[0020] In another possible implementation, the control module is specifically configured to encrypt the control instruction to obtain the encrypted control instruction; and send the corresponding encrypted control instruction to at least one vertical application respectively.

[0021] In another possible implementation, the collaborative office platform includes identity authentication information of registered users, and a communication module for sending the identity authentication information of registered users to multiple vertical applications respectively.

[0022] In another possible implementation, the multimodal instruction includes a voice instruction, and the analysis module is specifically used to perform timbre recognition on the voice instruction to obtain the timbre characteristics of the voice instruction; compare the timbre characteristics of the voice instruction with the recorded timbre characteristics; and when the recorded timbre characteristics include the timbre characteristics of the voice instruction, determine the target task based on the voice instruction.

[0023] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method of the first aspect above.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, which includes: computer software instructions; when the computer software instructions are executed in an electronic device, the electronic device implements the method of the first aspect above.

[0025] In a fifth aspect, the present application provides a computer program product, which includes a computer program; when the computer program runs in an electronic device, the electronic device implements the method of the first aspect.

[0026] The beneficial effects of the second to fifth aspects mentioned above refer to the corresponding description of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of an application environment of a collaborative office method provided for this application;

[0028] Figure 2 A schematic diagram of a collaborative office platform provided for this application;

[0029] Figure 3 A schematic diagram of the composition of a collaborative office platform provided for this application;

[0030] Figure 4 A flowchart of a collaborative working method provided for this application;

[0031] Figure 5 A flowchart of another collaborative working method provided for this application;

[0032] Figure 6 A flowchart of another collaborative working method provided for this application;

[0033] Figure 7 A schematic diagram of another collaborative office platform provided for this application;

[0034] Figure 8 A schematic diagram of the composition of a collaborative office device provided for this application;

[0035] Fig. 9 A schematic diagram of the composition of an electronic device provided in this application. DETAILED DESCRIPTION

[0036] A call bill data recording method provided by the present application will be described in detail below with reference to the accompanying drawings.

[0037] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0038] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0039] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0040] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0041] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical items or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order.

[0042] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0043] According to the description of the background technology, as the demand for collaborative office increases, the definition of collaborative office has been expanded and promoted to the category of intelligent office. Most enterprises not only need to solve the routine collaborative functions such as daily office, asset management, business management, information exchange, etc., but also put forward further requirements in terms of instant communication, data sharing, mobile office, etc. In addition, many enterprises are also seeking a comprehensive management application platform with low cost, high performance, high integration and intelligent management of enterprises, thus forming a series of collaborative office systems.

[0044] However, the overall operating efficiency of existing collaborative office platforms is low, and existing collaborative office platforms can only process instructions in the form of text input by users, and there is no specific processing solution for other forms of input instructions.

[0045] In response to the above technical problems, the present application provides a collaborative office method, the idea of ​​which is: by analyzing the multimodal instructions input by the user, identifying the target tasks indicated by the multimodal instructions, and then analyzing and determining the vertical applications related to completing the target tasks, and finally calling these vertical applications to perform the above target tasks, thereby realizing the automated execution of office tasks and the rapid transmission of information, which can improve the work efficiency of the collaborative office platform.

[0046] The collaborative office method provided in the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0047] Figure 1 A schematic diagram of an application environment of a collaborative office method provided in an embodiment of the present application. Figure 1 As shown, the application environment includes: a terminal device 101 and a processing device 102. The terminal device 101 and the processing device 102 are connected to each other.

[0048] In some embodiments, the terminal device 101 includes a display for displaying a user interface of the collaborative office system to facilitate interaction with the user.

[0049] In some embodiments, the terminal device 101 receives user multimodal instructions through the multimodal instruction input box of the control window, displays tasks related to the multimodal instructions, and sends the user's subsequent operation data (mainly the user's trigger operation data for tasks related to the multimodal instructions in this application) to the processing device 102.

[0050] In some embodiments, the terminal device 101 is used to display a user interaction interface that can provide the front-end capabilities of the collaborative office system, for example, Figure 2 As shown, the front-end capabilities of the collaborative office system include but are not limited to video conferencing, online documents, emails, express services, project management, and process approval.

[0051] Exemplarily, the terminal device 101 may be a device with display function and interactive function, such as a mobile phone, a tablet computer, a notebook computer, a computer device, etc. The present application does not limit the specific device form of the terminal device 101. Figure 1 In the figure, the terminal device is taken as a computer device as an example.

[0052] In some embodiments, the processing device 102 is used to implement the backend capabilities of the collaborative office platform.

[0053] In some embodiments, Figure 2 As shown, the backend capabilities of the collaborative office platform include distributed control. Exemplarily, the processing device 102 is used to determine the tasks related to the multimodal instructions based on the multimodal instructions input by the user, and send the data of the tasks related to the multimodal instructions to the terminal device 101, so that the terminal device 101 can complete the interaction with the user; and determine the target task according to the user's operation data, and determine the different vertical applications required to complete the target task based on the target task, and then generate control instructions for different vertical applications and send them to the corresponding vertical applications to instruct the vertical applications to perform the target task, thereby realizing the distributed control of different vertical applications by the collaborative office system.

[0054] In some embodiments, Figure 2 As shown, the backend capabilities of the collaborative office system include encryption services. Exemplarily, the processing device 102 is used to encrypt the above control instructions using domestic cryptographic algorithms and quantum key technology.

[0055] In some embodiments, Figure 2 As shown, the back-end capabilities of the collaborative office system also include data sandbox, access control, identity authentication, zero-trust access, etc.

[0056] Exemplarily, the processing device 102 may be a server cluster composed of multiple servers, or a single server, or a computer, or a processor or processing chip in a server or computer, etc. The embodiment of the present application does not limit the specific device form of the processing device 102. Figure 1 In the figure, the processing device 102 is taken as a single server as an example.

[0057] Figure 3 A schematic diagram of the composition of a collaborative office platform provided in an embodiment of the present application. Figure 2 As shown, the collaborative office platform includes an interaction layer, an access layer, and a security management and control layer.

[0058] The interaction layer provides a user interface for users to interact with.

[0059] In some embodiments, the interaction layer includes a master control page and a vertical application control page. The master control page provides a master control window, and the vertical application control page provides a sub-control window. In the present application, both the master control window and the sub-control window receive user instructions through multimodal instruction input. The master control window can call the sub-control windows of multiple vertical applications according to the multimodal instruction to perform the office tasks indicated by the multimodal instruction, and the sub-control window is only responsible for performing office tasks related to the vertical application.

[0060] In some embodiments, the interaction layer also provides interaction entry controls for vertical applications.

[0061] In some embodiments, the interaction layer also includes user interaction controls for services provided by the collaborative office platform. Exemplarily, the services provided by the collaborative office platform include encrypted calls, encrypted messages, encrypted files, and a personal center.

[0062] The access layer integrates and accesses different vertical applications through interfaces to form control nodes for different vertical applications. Different vertical applications include vertical applications that have been integrated within the collaborative office platform and other non-integrated vertical applications that are logged into the collaborative office platform device.

[0063] Exemplary vertical applications include, but are not limited to: finance, video conferencing, online documents, process approval, intelligent decision-making, cloud disk, map services, project management, knowledge management and other functional applications.

[0064] The security management and control layer has unified security capabilities and mainly provides back-end distributed control of different vertical applications and security management of the collaborative office platform.

[0065] Among them, the distributed control of different vertical applications has been described in detail in the previous article and will not be repeated here.

[0066] In some embodiments, the unified security capability includes unified identity authentication. After detecting the registered user's login operation, the security management and control layer sends the registered user's identity authentication information to multiple vertical applications to complete the user's identity authentication in multiple vertical applications.

[0067] In some embodiments, the unified security capabilities include encryption services. The security management and control layer uses a quantum random number generator to generate true random numbers as data encryption keys (i.e., quantum keys). Quantum keys can be distributed to user terminals through online distribution or offline pre-filling to meet different data encryption requirements.

[0068] In some embodiments, unified security capabilities include zero-trust access and data sandbox. The security management and control layer integrates zero-trust access and data sandbox security capabilities, which can provide users with cross-network security access authentication and communication between public networks and intranets or private networks, and combined with the data sandbox to meet data leakage prevention functions.

[0069] In some embodiments, the security management and control layer also provides data security control measures including message watermarking, message withdrawal, self-destruction after reading, anti-screenshot, anti-recording, etc.

[0070] It should be noted that the application scenarios of the embodiments of the present disclosure are not limited. The system architecture and business scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute limitations on the technical solutions provided by the embodiments of the present disclosure. It is known to those skilled in the art that with the evolution of technology and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0071] The collaborative office method provided by the embodiment of the present disclosure is specifically introduced below.

[0072] Figure 4 A flowchart of a collaborative office method provided in an embodiment of the present application, applied to Figure 3 The collaborative office platform shown in Figure 4 As shown, the method comprises the following steps:

[0073] S101: Receive a multimodal instruction input by a user.

[0074] Among them, multimodal instructions include but are not limited to text instructions, voice instructions, picture instructions and video instructions.

[0075] In some embodiments, the present application receives a multimodal instruction input by a user through a multimodal instruction input window.

[0076] In some embodiments, the collaborative office platform includes identity authentication information of registered users. Before step S101, the method further includes: after detecting a login operation of the user, sending the identity authentication information of the registered user to multiple vertical applications respectively.

[0077] Exemplarily, the identity authentication information of a registered user may include user name, user work number, user mobile phone number, user voice characteristics, etc.

[0078] It is understandable that when the user is a registered user of the collaborative office platform, once the user's login operation is detected, the current user's identity authentication information will be sent to each vertical application, thereby completing the unified identity authentication of the current user, thereby reducing office processes and improving office efficiency.

[0079] S102: Determine a target task based on the multimodal instruction.

[0080] Exemplarily, step S102 may be implemented as the following steps S201-S203, which will not be described in detail herein.

[0081] In some embodiments, when the multimodal instruction is a voice instruction, step S102 also includes: performing timbre recognition on the voice instruction to obtain the timbre characteristics of the voice instruction; comparing the timbre characteristics of the voice instruction with the recorded timbre characteristics; and when the recorded timbre characteristics include the timbre characteristics of the voice instruction, determining the target task based on the voice instruction.

[0082] It is understandable that determining whether the identity of the person issuing the instruction is valid through voice recognition can enhance the security of office processes.

[0083] S103: Call at least one vertical application to execute a target task.

[0084] It should be noted that vertical applications are a type of application with strong functional orientation. Their functions are relatively simple, and the realization of the target task may include multiple execution processes, that is, multiple sub-tasks. Different sub-tasks have different functional requirements, that is, different sub-tasks may need to be executed by one or more different vertical applications. Therefore, when executing the target task, it may be necessary to call multiple vertical applications.

[0085] It can be understood that the present application analyzes the multimodal instructions input by the user, identifies the target tasks indicated by the multimodal instructions, and then analyzes and determines the vertical applications related to completing the target tasks, and finally calls these vertical applications to perform the above-mentioned target tasks, thereby realizing the automated execution of office tasks and the rapid transmission of information, which can improve the work efficiency of the collaborative office platform.

[0086] In some embodiments, Figure 5 As shown, step S102 can be specifically implemented as the following steps S201-S203:

[0087] S201. Determine at least one office task corresponding to the multimodal instruction.

[0088] Optionally, step S201 includes: inputting the multimodal instruction into a task identification model to obtain at least one task corresponding to the multimodal instruction, wherein the task identification model is used to identify tasks related to the input multimodal instruction.

[0089] S202: Receive a first trigger operation.

[0090] The first trigger operation is used to indicate any office task among the at least one office task.

[0091] Exemplarily, the first trigger operation may include at least one of the following: a click operation, a touch operation, a gesture operation, a command trigger operation, etc., which is not limited in the embodiments of the present application.

[0092] S203: Determine a target task based on the first trigger operation.

[0093] Exemplarily, after determining at least one office task corresponding to the multimodal instruction, the at least one office task can be displayed on the interface of the front-end device, and then, in response to a first trigger operation of the user (such as a click operation), the office task indicated by the first trigger operation is used as the target task.

[0094] It should be noted that in actual applications, the user's multimodal instructions cannot be directly recognized by vertical applications, so it is necessary to input the multimodal instructions into the task recognition model to form office tasks related to the multimodal instructions, and display the above office tasks on the collaborative office platform interactive interface. Among them, the office tasks related to the multimodal instructions are displayed in the form of standardized instructions; the first trigger operation is the user's trigger operation, and the first trigger operation indicates the user's selection of the standardized instruction.

[0095] In some embodiments, in addition to the above-mentioned standardized instructions, the collaborative office platform analyzes the multimodal instructions input by the user. When the multimodal instructions are unclear or lack key elements, the instruction suggestions output by the task recognition model are displayed on the page to help the user complete the instructions.

[0096] Exemplarily, assuming that the multimodal instruction indicates an office task including a time element, if it is detected that the time element contained in the multimodal instruction input by the user conflicts with the execution time of the booked office task, a message pop-up window prompting the time conflict will be displayed on the interactive interface.

[0097] It is understandable that analyzing the user's multimodal instructions and then generating standardized instructions and rational suggestions can help complete the target office tasks more accurately.

[0098] In some embodiments, the target task includes at least one subtask, such as Figure 6 As shown, before step S103, the method further includes:

[0099] S21. Determine at least one vertical application that needs to be called to execute at least one subtask.

[0100] It can be understood that for each subtask in at least one subtask, one or more vertical applications may be called when executing each task. Therefore, the embodiment of the present application determines at least one vertical application required to be called to execute the above at least one subtask based on the one or more vertical applications required to be called to execute each subtask.

[0101] Furthermore, based on the above step S21, as Figure 6 As shown, the above step S103 can be implemented as the following steps:

[0102] S31. Generate a control instruction corresponding to at least one subtask according to at least one subtask.

[0103] The control instruction is used to instruct the vertical application corresponding to the subtask to execute the subtask. It can be understood that the vertical application corresponding to the subtask described in the embodiment of the present application refers to the vertical application required to be called to execute the subtask.

[0104] Exemplarily, assuming that the multimodal instruction is a text instruction "book a video conference", the text instruction is input into the task recognition model, and the task recognition model detects that the related tasks of "book a video conference task" include sub-tasks "book a reminder alarm" and sub-tasks "book a video conference room", among which the vertical application corresponding to the sub-task "book a reminder alarm" is "alarm clock", and the vertical application corresponding to the sub-task "book a video conference room" is "video conference", then control instructions for the application "alarm clock" and the application "video conference" are generated respectively.

[0105] S32. Send corresponding control instructions to at least one vertical application respectively.

[0106] Exemplarily, for the instruction "book a video conference" in step S31, corresponding control instructions are sent to the applications "alarm clock" and "video conference" respectively, so that the application "alarm clock" executes the task "book a reminder alarm clock" and the application "video conference" executes the task "book a video conference room".

[0107] In some embodiments, the above step S32 can also be implemented as follows: encrypting the control instruction to obtain the encrypted control instruction; and sending the encrypted control instructions corresponding to each vertical application. Exemplarily, the collaborative office platform uses a domestic cryptographic algorithm and a quantum key to encrypt the control instruction.

[0108] It can be understood that the collaborative office method provided in the embodiment of the present application analyzes the multimodal instructions input by the user, identifies the tasks related to the instructions and returns them to the user, determines the target task according to the user's selection, generates and encrypts the corresponding control instructions, and then sends the encrypted control instructions to the corresponding vertical application to instruct the vertical application to complete the relevant target tasks, thereby realizing the automated execution of office tasks and the secure transmission of information, which can improve the work efficiency and security of the collaborative office platform.

[0109] Figure 7 A schematic diagram of a collaborative office platform provided by an exemplary embodiment is shown in FIG. Figure 7 As shown in the figure, the collaborative office platform includes:

[0110] Page 1 is the main page of the collaborative office platform, including multiple user interaction controls, exemplarily including a search bar, a "master control window", "messages", "address book", "console" and "me".

[0111] Page 2 is the main control window page, including the main dialogue window and the multi-modal command input box.

[0112] Page 3 is a vertical application 1-point control page, including a vertical application 1-point dialog window and a multi-modal instruction input box.

[0113] Page 4 is a vertical application 2-part control page, including a vertical application 2-part dialog window and a multi-modal instruction input box.

[0114] Page 5 is the vertical application work page, including a manual work window.

[0115] Page 6 is the vertical application console page, which includes entrances to various vertical applications.

[0116] like Figure 7As shown, page 6 includes multiple user interaction controls. Exemplarily, the user interaction controls include: "Process Approval", "Video Conference", "Map Service", "Online Document", "Network Disk", "Email", "Project Management", etc.

[0117] The collaborative office method provided by this application is introduced below in conjunction with a specific embodiment.

[0118] Exemplarily, the collaborative office method provided in the embodiment of the present application may include the following process:

[0119] S1. After logging into the collaborative office platform, the user enters page 1 and clicks the “Master Control Window” option.

[0120] S2. Enter page 2 and enter the multimodal command in the multimodal command input box.

[0121] S3. The collaborative office platform identifies tasks related to the multimodal instructions input by the user.

[0122] Exemplarily, the collaborative office platform inputs the multimodal instructions input by the user into a task recognition model to perform task recognition.

[0123] S4. The collaborative office platform displays the standardized instructions of the relevant tasks on the general dialogue page in page 2.

[0124] S5. The user clicks on a standardized instruction option for a task that the user actually wants to complete.

[0125] S6. The collaborative office platform determines the final target task based on the user's selection, generates and encrypts the corresponding control instructions, and sends the encrypted control instructions to the corresponding vertical application.

[0126] S7. If the vertical application corresponding to the target task is vertical application 1, jump to page 3, and vertical application 1 automatically completes the corresponding office task according to the control instruction. If the vertical application corresponding to the target task is vertical application 2, jump to page 4, and vertical application 2 automatically completes the corresponding office task according to the control instruction.

[0127] In some embodiments, when a vertical application detects that there is an office task that cannot be completed automatically, the collaborative office platform jumps to the operation page of the vertical application, such as Figure 7 Page 5 in the figure is where the user manually completes the office task.

[0128] In other embodiments, after the user clicks the "Console" option on page 1, the user enters page 6. The user selects the vertical application he wants to enter on page 6, thereby entering the corresponding page for the vertical application (for example, page 3 or page 4). The user then enters multimodal instructions in the multimodal instruction input box as needed, so that the vertical application executes the office tasks indicated by the multimodal instructions.

[0129] It can be seen that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the embodiment of the present application provides a hardware structure and / or software module corresponding to each function. It should be easily appreciated by those skilled in the art that, in combination with the modules and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0130] The embodiment of the present application can divide the functional modules of the collaborative office device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0131] Figure 8 This is a schematic diagram of the composition of a collaborative office device provided in an embodiment of the present application, which is applied to a collaborative office platform and can implement the collaborative office method provided in the above method embodiment. Figure 8 As shown, the collaborative office device 400 includes: a receiving module 401 , an analyzing module 402 , and a controlling module 403 . In some embodiments, the collaborative office device 400 further includes a communication module 404 .

[0132] The receiving module 401 is used to receive a multi-modal instruction input by a user;

[0133] An analysis module 402, for determining a target task based on the multimodal instruction;

[0134] A control module 403 is used to call at least one vertical application to execute a target task;

[0135] In a possible implementation, the analysis module 402 is specifically used to determine at least one office task corresponding to the multimodal instruction; receive a first trigger operation, the first trigger operation is used to indicate any office task in the at least one office task; and determine the target task based on the first trigger operation.

[0136] In another possible implementation, the analysis module 402 is specifically configured to input the multimodal instruction into a task identification model to obtain at least one task corresponding to the multimodal instruction; wherein the task identification model is configured to identify tasks related to the input multimodal instruction.

[0137] In another possible implementation, the target task includes at least one subtask, and the analysis module 402 is further used to determine at least one vertical application required to be called to execute the at least one subtask; the control module 403 is specifically used to generate a control instruction corresponding to at least one subtask according to the at least one subtask, and the control instruction is used to instruct the vertical application corresponding to the subtask to execute the subtask; and the corresponding control instructions are sent to the at least one vertical application respectively.

[0138] In another possible implementation, the control module 403 is specifically configured to encrypt the control instruction to obtain the encrypted control instruction; and send the encrypted control instruction corresponding to each of the at least one vertical application.

[0139] In another possible implementation, the collaborative office platform includes identity authentication information of registered users, and the communication module 404 is used to send the identity authentication information of registered users to multiple vertical applications respectively.

[0140] In another possible implementation, the multimodal instruction includes a voice instruction, and the analysis module 402 is specifically used to perform timbre recognition on the voice instruction to obtain the timbre characteristics of the voice instruction; compare the timbre characteristics of the voice instruction with the recorded timbre characteristics; and when the recorded timbre characteristics include the timbre characteristics of the voice instruction, determine the target task based on the voice instruction.

[0141] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiment of the present invention provides a possible composition diagram of the electronic device involved in the above-mentioned embodiment. Fig. 9 As shown, the electronic device 900 includes: a processor 902 , a communication interface 903 , and a bus 904 . Optionally, the electronic device 900 may further include a memory 901 .

[0142] The processor 902 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor 902 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor 902 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0143] The communication interface 903 is used to connect with other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0144] The memory 901 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0145] As a possible implementation, the memory 901 may exist independently of the processor 902, and the memory 901 may be connected to the processor 902 via a bus 904 to store instructions or program codes. When the processor 902 calls and executes the instructions or program codes stored in the memory 901, the collaborative office method provided in the embodiment of the present invention can be implemented.

[0146] In another possible implementation, the memory 901 may also be integrated with the processor 902 .

[0147] The bus 904 may be an extended industry standard architecture (EISA) bus, etc. The bus 904 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0148] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0149] The present application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be completed by computer program instructions to instruct related hardware, and the program can be stored in the above computer-readable storage medium. When the computer program instructions are executed on a computer, the computer executes the collaborative office method described in any of the above embodiments.

[0150] Exemplarily, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks or magnetic tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), etc.), smart cards and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks or key drives, etc.). The various computer-readable storage media described in the present disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.

[0151] An embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program product is run on a computer, the computer is enabled to execute any one of the collaborative office methods provided in the above embodiments.

[0152] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A collaborative office method, characterized in that: Applied to a collaborative office platform, the collaborative office platform is connected with multiple vertical applications, and the method includes: Receiving multimodal instructions input by a user; determining a target task based on the multimodal instruction; At least one of the vertical applications is called to execute the target task.

2. The method according to claim 1, characterized in that The determining of the target task based on the multimodal instruction comprises: determining at least one office task corresponding to the multimodal instruction; receiving a first trigger operation, where the first trigger operation is used to indicate any office task among the at least one office task; Based on the first triggering operation, the target task is determined.

3. The method according to claim 2, characterized in that The determining of at least one office task corresponding to the multimodal instruction comprises: The multimodal instruction is input into a task identification model to obtain at least one task corresponding to the multimodal instruction; wherein the task identification model is used to identify tasks related to the input multimodal instruction.

4. The method according to claim 1, characterized in that: The target task includes at least one subtask. Before determining the target task based on the multimodal instruction, the method further includes: Determine at least one of the vertical applications that needs to be called to execute the at least one subtask; The calling of the at least one vertical application to execute the target task includes: Generate, according to the at least one subtask, a control instruction corresponding to each of the at least one subtask, wherein the control instruction is used to instruct the vertical application corresponding to the subtask to execute the subtask; The control instructions corresponding to each of the vertical applications are sent respectively.

5. The method according to claim 4, characterized in that The sending the control instructions corresponding to each of the at least one vertical application respectively includes: Encrypting the control instruction to obtain the encrypted control instruction; The encrypted control instructions corresponding to each of the vertical applications are respectively sent to at least one of the vertical applications.

6. The method according to claim 1, characterized in that The collaborative office platform includes identity authentication information of registered users, and the method further includes: The identity authentication information of the registered user is sent to the multiple vertical applications respectively.

7. The method according to claim 1, characterized in that The multimodal instruction includes a voice instruction, and determining the target task based on the multimodal instruction includes: Performing timbre recognition on the voice command to obtain timbre characteristics of the voice command; Comparing the timbre characteristics of the voice command with the recorded timbre characteristics; In a case where the recorded timbre features include the timbre features of the voice instruction, the target task is determined based on the voice instruction.

8. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable the computer device to implement the collaborative office method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer is enabled to execute the collaborative office method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed on an electronic device, the electronic device is enabled to execute the collaborative office method according to any one of claims 1 to 7.

Images